uncertainty_intervals.ipynb (prophet-0.7) | : | uncertainty_intervals.ipynb (prophet-1.0) | ||
---|---|---|---|---|
{ | { | |||
"cells": [ | "cells": [ | |||
{ | { | |||
"cell_type": "code", | "cell_type": "code", | |||
"execution_count": 1, | "execution_count": 1, | |||
"metadata": { | "metadata": { | |||
"block_hidden": true, | "block_hidden": true | |||
"collapsed": true | ||||
}, | }, | |||
"outputs": [], | "outputs": [], | |||
"source": [ | "source": [ | |||
"%load_ext rpy2.ipython\n", | "%load_ext rpy2.ipython\n", | |||
"%matplotlib inline\n", | "%matplotlib inline\n", | |||
"from fbprophet import Prophet\n", | "from prophet import Prophet\n", | |||
"import pandas as pd\n", | "import pandas as pd\n", | |||
"from matplotlib import pyplot as plt\n", | "from matplotlib import pyplot as plt\n", | |||
"import numpy as np\n", | "import numpy as np\n", | |||
"import logging\n", | "import logging\n", | |||
"logging.getLogger('fbprophet').setLevel(logging.ERROR)\n", | "logging.getLogger('prophet').setLevel(logging.ERROR)\n", | |||
"import warnings\n", | "import warnings\n", | |||
"warnings.filterwarnings(\"ignore\")\n", | "warnings.filterwarnings(\"ignore\")" | |||
] | ||||
}, | ||||
{ | ||||
"cell_type": "code", | ||||
"execution_count": 2, | ||||
"metadata": { | ||||
"block_hidden": true | ||||
}, | ||||
"outputs": [ | ||||
{ | ||||
"name": "stderr", | ||||
"output_type": "stream", | ||||
"text": [ | ||||
"INFO:numexpr.utils:NumExpr defaulting to 8 threads.\n" | ||||
] | ||||
} | ||||
], | ||||
"source": [ | ||||
"df = pd.read_csv('../examples/example_wp_log_peyton_manning.csv')\n", | "df = pd.read_csv('../examples/example_wp_log_peyton_manning.csv')\n", | |||
"df = df.loc[:180,] # Limit to first six months\n", | "df = df.loc[:180,] # Limit to first six months\n", | |||
"m = Prophet()\n", | "m = Prophet()\n", | |||
"m.fit(df)\n", | "m.fit(df)\n", | |||
"future = m.make_future_dataframe(periods=60)" | "future = m.make_future_dataframe(periods=60)" | |||
] | ] | |||
}, | }, | |||
{ | { | |||
"cell_type": "code", | "cell_type": "code", | |||
"execution_count": 2, | "execution_count": 2, | |||
"metadata": { | "metadata": { | |||
"block_hidden": true | "block_hidden": true | |||
}, | }, | |||
"outputs": [ | "outputs": [ | |||
{ | { | |||
"data": { | "name": "stderr", | |||
"text/plain": [ | "output_type": "stream", | |||
"Initial log joint probability = -2.43365\n", | "text": [ | |||
"Optimization terminated normally: \n", | "R[write to console]: Loading required package: Rcpp\n", | |||
" Convergence detected: absolute parameter change was below tolerance\n" | "\n", | |||
] | "R[write to console]: Loading required package: rlang\n", | |||
}, | "\n", | |||
"metadata": {}, | "R[write to console]: Disabling yearly seasonality. Run prophet with yearl | |||
"output_type": "display_data" | y.seasonality=TRUE to override this.\n", | |||
"\n", | ||||
"R[write to console]: Disabling daily seasonality. Run prophet with daily. | ||||
seasonality=TRUE to override this.\n", | ||||
"\n" | ||||
] | ||||
} | } | |||
], | ], | |||
"source": [ | "source": [ | |||
"%%R\n", | "%%R\n", | |||
"library(prophet)\n", | "library(prophet)\n", | |||
"df <- read.csv('../examples/example_wp_log_peyton_manning.csv')\n", | "df <- read.csv('../examples/example_wp_log_peyton_manning.csv')\n", | |||
"df <- df[1:180,]\n", | "df <- df[1:180,]\n", | |||
"m <- prophet(df)\n", | "m <- prophet(df)\n", | |||
"future <- make_future_dataframe(m, periods=60)" | "future <- make_future_dataframe(m, periods=60)" | |||
] | ] | |||
skipping to change at line 81 | skipping to change at line 101 | |||
] | ] | |||
}, | }, | |||
{ | { | |||
"cell_type": "code", | "cell_type": "code", | |||
"execution_count": 3, | "execution_count": 3, | |||
"metadata": { | "metadata": { | |||
"output_hidden": true | "output_hidden": true | |||
}, | }, | |||
"outputs": [ | "outputs": [ | |||
{ | { | |||
"data": { | "name": "stderr", | |||
"text/plain": [ | "output_type": "stream", | |||
"Initial log joint probability = -2.43365\n", | "text": [ | |||
"Optimization terminated normally: \n", | "R[write to console]: Disabling yearly seasonality. Run prophet with yearl | |||
" Convergence detected: absolute parameter change was below tolerance\n" | y.seasonality=TRUE to override this.\n", | |||
] | "\n", | |||
}, | "R[write to console]: Disabling daily seasonality. Run prophet with daily. | |||
"metadata": {}, | seasonality=TRUE to override this.\n", | |||
"output_type": "display_data" | "\n" | |||
] | ||||
} | } | |||
], | ], | |||
"source": [ | "source": [ | |||
"%%R\n", | "%%R\n", | |||
"m <- prophet(df, interval.width = 0.95)\n", | "m <- prophet(df, interval.width = 0.95)\n", | |||
"forecast <- predict(m, future)" | "forecast <- predict(m, future)" | |||
] | ] | |||
}, | }, | |||
{ | { | |||
"cell_type": "code", | "cell_type": "code", | |||
"execution_count": 4, | "execution_count": 3, | |||
"metadata": { | "metadata": {}, | |||
"collapsed": true | ||||
}, | ||||
"outputs": [], | "outputs": [], | |||
"source": [ | "source": [ | |||
"forecast = Prophet(interval_width=0.95).fit(df).predict(future)" | "forecast = Prophet(interval_width=0.95).fit(df).predict(future)" | |||
] | ] | |||
}, | }, | |||
{ | { | |||
"cell_type": "markdown", | "cell_type": "markdown", | |||
"metadata": {}, | "metadata": {}, | |||
"source": [ | "source": [ | |||
"Again, these intervals assume that the future will see the same frequency a nd magnitude of rate changes as the past. This assumption is probably not true, so you should not expect to get accurate coverage on these uncertainty intervals .\n", | "Again, these intervals assume that the future will see the same frequency a nd magnitude of rate changes as the past. This assumption is probably not true, so you should not expect to get accurate coverage on these uncertainty intervals .\n", | |||
"\n", | "\n", | |||
"### Uncertainty in seasonality\n", | "### Uncertainty in seasonality\n", | |||
"By default Prophet will only return uncertainty in the trend and observatio n noise. To get uncertainty in seasonality, you must do full Bayesian sampling. This is done using the parameter `mcmc.samples` (which defaults to 0). We do thi s here for the first six months of the Peyton Manning data from the Quickstart:" | "By default Prophet will only return uncertainty in the trend and observatio n noise. To get uncertainty in seasonality, you must do full Bayesian sampling. This is done using the parameter `mcmc.samples` (which defaults to 0). We do thi s here for the first six months of the Peyton Manning data from the Quickstart:" | |||
] | ] | |||
}, | }, | |||
{ | { | |||
"cell_type": "code", | "cell_type": "code", | |||
"execution_count": 5, | "execution_count": 4, | |||
"metadata": { | "metadata": { | |||
"output_hidden": true | "output_hidden": true | |||
}, | }, | |||
"outputs": [ | "outputs": [ | |||
{ | { | |||
"data": { | "name": "stderr", | |||
"text/plain": [ | "output_type": "stream", | |||
"\n", | "text": [ | |||
"SAMPLING FOR MODEL 'prophet' NOW (CHAIN 1).\n", | "R[write to console]: Disabling yearly seasonality. Run prophet with yearl | |||
"\n", | y.seasonality=TRUE to override this.\n", | |||
"Gradient evaluation took 5.3e-05 seconds\n", | "\n", | |||
"1000 transitions using 10 leapfrog steps per transition would take 0.53 | "R[write to console]: Disabling daily seasonality. Run prophet with daily. | |||
seconds.\n", | seasonality=TRUE to override this.\n", | |||
"Adjust your expectations accordingly!\n", | "\n" | |||
"\n", | ] | |||
"\n", | }, | |||
"Iteration: 1 / 300 [ 0%] (Warmup)\n", | { | |||
"Iteration: 30 / 300 [ 10%] (Warmup)\n", | "name": "stdout", | |||
"Iteration: 60 / 300 [ 20%] (Warmup)\n", | "output_type": "stream", | |||
"Iteration: 90 / 300 [ 30%] (Warmup)\n", | "text": [ | |||
"Iteration: 120 / 300 [ 40%] (Warmup)\n", | "\n", | |||
"Iteration: 150 / 300 [ 50%] (Warmup)\n", | "SAMPLING FOR MODEL 'prophet' NOW (CHAIN 1).\n", | |||
"Iteration: 151 / 300 [ 50%] (Sampling)\n", | "Chain 1: \n", | |||
"Iteration: 180 / 300 [ 60%] (Sampling)\n", | "Chain 1: Gradient evaluation took 8.6e-05 seconds\n", | |||
"Iteration: 210 / 300 [ 70%] (Sampling)\n", | "Chain 1: 1000 transitions using 10 leapfrog steps per transition would ta | |||
"Iteration: 240 / 300 [ 80%] (Sampling)\n", | ke 0.86 seconds.\n", | |||
"Iteration: 270 / 300 [ 90%] (Sampling)\n", | "Chain 1: Adjust your expectations accordingly!\n", | |||
"Iteration: 300 / 300 [100%] (Sampling)\n", | "Chain 1: \n", | |||
"\n", | "Chain 1: \n", | |||
" Elapsed Time: 1.61713 seconds (Warm-up)\n", | "Chain 1: Iteration: 1 / 300 [ 0%] (Warmup)\n", | |||
" 1.46049 seconds (Sampling)\n", | "Chain 1: Iteration: 30 / 300 [ 10%] (Warmup)\n", | |||
" 3.07762 seconds (Total)\n", | "Chain 1: Iteration: 60 / 300 [ 20%] (Warmup)\n", | |||
"\n", | "Chain 1: Iteration: 90 / 300 [ 30%] (Warmup)\n", | |||
"\n", | "Chain 1: Iteration: 120 / 300 [ 40%] (Warmup)\n", | |||
"SAMPLING FOR MODEL 'prophet' NOW (CHAIN 2).\n", | "Chain 1: Iteration: 150 / 300 [ 50%] (Warmup)\n", | |||
"\n", | "Chain 1: Iteration: 151 / 300 [ 50%] (Sampling)\n", | |||
"Gradient evaluation took 4.9e-05 seconds\n", | "Chain 1: Iteration: 180 / 300 [ 60%] (Sampling)\n", | |||
"1000 transitions using 10 leapfrog steps per transition would take 0.49 | "Chain 1: Iteration: 210 / 300 [ 70%] (Sampling)\n", | |||
seconds.\n", | "Chain 1: Iteration: 240 / 300 [ 80%] (Sampling)\n", | |||
"Adjust your expectations accordingly!\n", | "Chain 1: Iteration: 270 / 300 [ 90%] (Sampling)\n", | |||
"\n", | "Chain 1: Iteration: 300 / 300 [100%] (Sampling)\n", | |||
"\n", | "Chain 1: \n", | |||
"Iteration: 1 / 300 [ 0%] (Warmup)\n", | "Chain 1: Elapsed Time: 2.10541 seconds (Warm-up)\n", | |||
"Iteration: 30 / 300 [ 10%] (Warmup)\n", | "Chain 1: 2.37589 seconds (Sampling)\n", | |||
"Iteration: 60 / 300 [ 20%] (Warmup)\n", | "Chain 1: 4.4813 seconds (Total)\n", | |||
"Iteration: 90 / 300 [ 30%] (Warmup)\n", | "Chain 1: \n", | |||
"Iteration: 120 / 300 [ 40%] (Warmup)\n", | "\n", | |||
"Iteration: 150 / 300 [ 50%] (Warmup)\n", | "SAMPLING FOR MODEL 'prophet' NOW (CHAIN 2).\n", | |||
"Iteration: 151 / 300 [ 50%] (Sampling)\n", | "Chain 2: \n", | |||
"Iteration: 180 / 300 [ 60%] (Sampling)\n", | "Chain 2: Gradient evaluation took 7.4e-05 seconds\n", | |||
"Iteration: 210 / 300 [ 70%] (Sampling)\n", | "Chain 2: 1000 transitions using 10 leapfrog steps per transition would ta | |||
"Iteration: 240 / 300 [ 80%] (Sampling)\n", | ke 0.74 seconds.\n", | |||
"Iteration: 270 / 300 [ 90%] (Sampling)\n", | "Chain 2: Adjust your expectations accordingly!\n", | |||
"Iteration: 300 / 300 [100%] (Sampling)\n", | "Chain 2: \n", | |||
"\n", | "Chain 2: \n", | |||
" Elapsed Time: 1.56343 seconds (Warm-up)\n", | "Chain 2: Iteration: 1 / 300 [ 0%] (Warmup)\n", | |||
" 1.62792 seconds (Sampling)\n", | "Chain 2: Iteration: 30 / 300 [ 10%] (Warmup)\n", | |||
" 3.19134 seconds (Total)\n", | "Chain 2: Iteration: 60 / 300 [ 20%] (Warmup)\n", | |||
"\n", | "Chain 2: Iteration: 90 / 300 [ 30%] (Warmup)\n", | |||
"\n", | "Chain 2: Iteration: 120 / 300 [ 40%] (Warmup)\n", | |||
"SAMPLING FOR MODEL 'prophet' NOW (CHAIN 3).\n", | "Chain 2: Iteration: 150 / 300 [ 50%] (Warmup)\n", | |||
"\n", | "Chain 2: Iteration: 151 / 300 [ 50%] (Sampling)\n", | |||
"Gradient evaluation took 4.9e-05 seconds\n", | "Chain 2: Iteration: 180 / 300 [ 60%] (Sampling)\n", | |||
"1000 transitions using 10 leapfrog steps per transition would take 0.49 | "Chain 2: Iteration: 210 / 300 [ 70%] (Sampling)\n", | |||
seconds.\n", | "Chain 2: Iteration: 240 / 300 [ 80%] (Sampling)\n", | |||
"Adjust your expectations accordingly!\n", | "Chain 2: Iteration: 270 / 300 [ 90%] (Sampling)\n", | |||
"\n", | "Chain 2: Iteration: 300 / 300 [100%] (Sampling)\n", | |||
"\n", | "Chain 2: \n", | |||
"Iteration: 1 / 300 [ 0%] (Warmup)\n", | "Chain 2: Elapsed Time: 2.04288 seconds (Warm-up)\n", | |||
"Iteration: 30 / 300 [ 10%] (Warmup)\n", | "Chain 2: 2.12795 seconds (Sampling)\n", | |||
"Iteration: 60 / 300 [ 20%] (Warmup)\n", | "Chain 2: 4.17083 seconds (Total)\n", | |||
"Iteration: 90 / 300 [ 30%] (Warmup)\n", | "Chain 2: \n", | |||
"Iteration: 120 / 300 [ 40%] (Warmup)\n", | "\n", | |||
"Iteration: 150 / 300 [ 50%] (Warmup)\n", | "SAMPLING FOR MODEL 'prophet' NOW (CHAIN 3).\n", | |||
"Iteration: 151 / 300 [ 50%] (Sampling)\n", | "Chain 3: \n", | |||
"Iteration: 180 / 300 [ 60%] (Sampling)\n", | "Chain 3: Gradient evaluation took 7.1e-05 seconds\n", | |||
"Iteration: 210 / 300 [ 70%] (Sampling)\n", | "Chain 3: 1000 transitions using 10 leapfrog steps per transition would ta | |||
"Iteration: 240 / 300 [ 80%] (Sampling)\n", | ke 0.71 seconds.\n", | |||
"Iteration: 270 / 300 [ 90%] (Sampling)\n", | "Chain 3: Adjust your expectations accordingly!\n", | |||
"Iteration: 300 / 300 [100%] (Sampling)\n", | "Chain 3: \n", | |||
"\n", | "Chain 3: \n", | |||
" Elapsed Time: 1.67866 seconds (Warm-up)\n", | "Chain 3: Iteration: 1 / 300 [ 0%] (Warmup)\n", | |||
" 1.68797 seconds (Sampling)\n", | "Chain 3: Iteration: 30 / 300 [ 10%] (Warmup)\n", | |||
" 3.36663 seconds (Total)\n", | "Chain 3: Iteration: 60 / 300 [ 20%] (Warmup)\n", | |||
"\n", | "Chain 3: Iteration: 90 / 300 [ 30%] (Warmup)\n", | |||
"\n", | "Chain 3: Iteration: 120 / 300 [ 40%] (Warmup)\n", | |||
"SAMPLING FOR MODEL 'prophet' NOW (CHAIN 4).\n", | "Chain 3: Iteration: 150 / 300 [ 50%] (Warmup)\n", | |||
"\n", | "Chain 3: Iteration: 151 / 300 [ 50%] (Sampling)\n", | |||
"Gradient evaluation took 4.7e-05 seconds\n", | "Chain 3: Iteration: 180 / 300 [ 60%] (Sampling)\n", | |||
"1000 transitions using 10 leapfrog steps per transition would take 0.47 | "Chain 3: Iteration: 210 / 300 [ 70%] (Sampling)\n", | |||
seconds.\n", | "Chain 3: Iteration: 240 / 300 [ 80%] (Sampling)\n", | |||
"Adjust your expectations accordingly!\n", | "Chain 3: Iteration: 270 / 300 [ 90%] (Sampling)\n", | |||
"\n", | "Chain 3: Iteration: 300 / 300 [100%] (Sampling)\n", | |||
"\n", | "Chain 3: \n", | |||
"Iteration: 1 / 300 [ 0%] (Warmup)\n", | "Chain 3: Elapsed Time: 2.24488 seconds (Warm-up)\n", | |||
"Iteration: 30 / 300 [ 10%] (Warmup)\n", | "Chain 3: 2.5196 seconds (Sampling)\n", | |||
"Iteration: 60 / 300 [ 20%] (Warmup)\n", | "Chain 3: 4.76448 seconds (Total)\n", | |||
"Iteration: 90 / 300 [ 30%] (Warmup)\n", | "Chain 3: \n", | |||
"Iteration: 120 / 300 [ 40%] (Warmup)\n", | "\n", | |||
"Iteration: 150 / 300 [ 50%] (Warmup)\n", | "SAMPLING FOR MODEL 'prophet' NOW (CHAIN 4).\n", | |||
"Iteration: 151 / 300 [ 50%] (Sampling)\n", | "Chain 4: \n", | |||
"Iteration: 180 / 300 [ 60%] (Sampling)\n", | "Chain 4: Gradient evaluation took 6.5e-05 seconds\n", | |||
"Iteration: 210 / 300 [ 70%] (Sampling)\n", | "Chain 4: 1000 transitions using 10 leapfrog steps per transition would ta | |||
"Iteration: 240 / 300 [ 80%] (Sampling)\n", | ke 0.65 seconds.\n", | |||
"Iteration: 270 / 300 [ 90%] (Sampling)\n", | "Chain 4: Adjust your expectations accordingly!\n", | |||
"Iteration: 300 / 300 [100%] (Sampling)\n", | "Chain 4: \n", | |||
"\n", | "Chain 4: \n", | |||
" Elapsed Time: 1.65952 seconds (Warm-up)\n", | "Chain 4: Iteration: 1 / 300 [ 0%] (Warmup)\n", | |||
" 1.51409 seconds (Sampling)\n", | "Chain 4: Iteration: 30 / 300 [ 10%] (Warmup)\n", | |||
" 3.17361 seconds (Total)\n", | "Chain 4: Iteration: 60 / 300 [ 20%] (Warmup)\n", | |||
"\n" | "Chain 4: Iteration: 90 / 300 [ 30%] (Warmup)\n", | |||
] | "Chain 4: Iteration: 120 / 300 [ 40%] (Warmup)\n", | |||
}, | "Chain 4: Iteration: 150 / 300 [ 50%] (Warmup)\n", | |||
"metadata": {}, | "Chain 4: Iteration: 151 / 300 [ 50%] (Sampling)\n", | |||
"output_type": "display_data" | "Chain 4: Iteration: 180 / 300 [ 60%] (Sampling)\n", | |||
"Chain 4: Iteration: 210 / 300 [ 70%] (Sampling)\n", | ||||
"Chain 4: Iteration: 240 / 300 [ 80%] (Sampling)\n", | ||||
"Chain 4: Iteration: 270 / 300 [ 90%] (Sampling)\n", | ||||
"Chain 4: Iteration: 300 / 300 [100%] (Sampling)\n", | ||||
"Chain 4: \n", | ||||
"Chain 4: Elapsed Time: 2.2803 seconds (Warm-up)\n", | ||||
"Chain 4: 2.73488 seconds (Sampling)\n", | ||||
"Chain 4: 5.01518 seconds (Total)\n", | ||||
"Chain 4: \n" | ||||
] | ||||
} | } | |||
], | ], | |||
"source": [ | "source": [ | |||
"%%R\n", | "%%R\n", | |||
"m <- prophet(df, mcmc.samples = 300)\n", | "m <- prophet(df, mcmc.samples = 300)\n", | |||
"forecast <- predict(m, future)" | "forecast <- predict(m, future)" | |||
] | ] | |||
}, | }, | |||
{ | { | |||
"cell_type": "code", | "cell_type": "code", | |||
"execution_count": 6, | "execution_count": 4, | |||
"metadata": { | "metadata": {}, | |||
"collapsed": true | ||||
}, | ||||
"outputs": [], | "outputs": [], | |||
"source": [ | "source": [ | |||
"m = Prophet(mcmc_samples=300)\n", | "m = Prophet(mcmc_samples=300)\n", | |||
"forecast = m.fit(df).predict(future)" | "forecast = m.fit(df).predict(future)" | |||
] | ] | |||
}, | }, | |||
{ | { | |||
"cell_type": "markdown", | "cell_type": "markdown", | |||
"metadata": {}, | "metadata": {}, | |||
"source": [ | "source": [ | |||
"This replaces the typical MAP estimation with MCMC sampling, and can take m uch longer depending on how many observations there are - expect several minutes instead of several seconds. If you do full sampling, then you will see the unce rtainty in seasonal components when you plot them:" | "This replaces the typical MAP estimation with MCMC sampling, and can take m uch longer depending on how many observations there are - expect several minutes instead of several seconds. If you do full sampling, then you will see the unce rtainty in seasonal components when you plot them:" | |||
] | ] | |||
}, | }, | |||
{ | { | |||
"cell_type": "code", | "cell_type": "code", | |||
"execution_count": 7, | "execution_count": 5, | |||
"metadata": { | "metadata": { | |||
"output_hidden": true | "output_hidden": true | |||
}, | }, | |||
"outputs": [ | "outputs": [ | |||
{ | { | |||
"data": { | "data": { | |||
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAogAAAGwCAIAAACl6gOwAAAACXBIWXMAAAsS AAALEgHS3X78AAAg\nAElEQVR4nOzdd3wb9f0/8M8NSac9vPeI7SRkTzJIgBB2GQlf6KaBhrZAW0pLv/ BtaUrbL6UQfqxA\nC236LaUNhQ5GoIUSSLNJGjIbArETW/F2PDQsa55Ovz8UjCPL63TSnaTX89FHH/hi nz6WT3rp/bnP\noCKRCAEAAABloOVuAAAAAHwKwQwAAKAgCGYAAAAFQTADAAAoCJuk8w4MDCTpzIqiUq l4nscAugmh\naToSieBJmxCGYQgh4XBY7oakGYZh8KRNCEVRLMuGQiG5G5JmErzS9Hr90C+TFcw+ny9J Z1YUjuO8\nXi/P83I3JJ1wHBcMBgVBkLsh6USn01EUlSUvK6lQFMVxHJ60CWEYhuM4t9std0PSjF6vT+ RKkyyY\n+/v7H330Ub/fP3ny5FtvvVX0eQAAAGCQ+HvMb7755gUXXPDwww/39PScPn1awjYBAABkLfEV c2dn\n58KFCwkhtbW1DQ0NFRUVhJCjR4/6/X6VSlVdXS1ZGxUsej+Goii5G5JOGIZRqVToyp6Q6D1mlU ol\nd0PSCUVR0YtN7oakE5qmKYrCkzZRNE2LftKGvxmKD+aqqqqtW7caDIbdu3cvW7YsevCPf/xjR0eH \n1Wp97LHHRJ85jVAUpdVqMY5pQhK5grMWTdPkk3iG8aNpmmWTNZImI1EURVFUzC1PGBNN06Jfnn6/\n P+YIJTpUeJ7/29/+1tnZSQiZMWPGihUrhv5rT0+PuNOmF6vV2t/fj8FfE4LBXyJEB39lyWQHqWDw\nlw gMw5jN5r6+Prkbkmb0en0iL8/c3NyhX4q/x1xfXz9z5sy77rrL7/dPnTpV9HkAAABgkPhOnsrK\nyqee euq1116rra0tKiqSsE0AAABZS3ww63S6++67T8KmQOKOdHhG/4ZZRYbUtAQAAMTBsIj0M2b6\njvNnEd IAAAqEYE4PiYTxeM6JkAYAUAgEs3IlI4xHfyzEMwCA7BDMyiJ5GEciJBKJ0PS4lkBBPAMA\nyA7BrAgT zWOnnz/Z5/cEwgOhsCfAe0OCNyR4Q2FfUPDwwkAg7AsJA6GwLyR4Q2GOpWtytHW52sm5\nurocbalJM/ pKZYhnAAAZIZhlNs5I5gWhsc9//Iz3ox7vR2d83d5QlZUzaWidijVoaB1LGzVsgUGt\nU9EGNaNT0TpV 9P9pnZoZCIbre/31Pd5/nnRs2NsuRCJ1Odq6XO2UXF1drrbQoB6lYYhnAIAUQzDL\nYzx53OcNHe/2He 8e+OiMt77XZ9awU/J00wp0103JrcnVqsfXO00IMaiZAoN6WYUp+mW7O3iix3ui\nx/va8d6GPp+KpqYV 6FaflzsnXgYjngEAUgzBnFJj5vGpPv+RTs9H3d4Pz3idvlBtru68PN3qaXlT\n87S5OmnWly42qYtN6o urLYQQQYi0uAP/bu3/xY6WQqP6S7PyF5QYR2k2EhoAINkQzCkySiQLkcjx\nbt8uu3PXabePF+YWG87L 099wXm5NDsfS4tdMHQ+apiosXIWFu+683LdO9D2+u82mY784M39RmSnu\nfWgU0AAAySZ+E4vRYROLqF HyOCQIhzsGdp52vd/sVjP00nLTBRXm6fm6cY6gToaQILxz0vmnI2cM\nGuaLs/KXlpvoEcaJJZLN2MRC BGxiIQI2sRABm1iII+0mFgjmhIwUzKPksZ8X/t3m2XXaua/Fk6tj\nl1aYLqgw1+VoRbdhzIyc6JBvXh C2Nro2HTmjZqgvzipYXilxPCOYRUAwi4BgFgHBLA6CWUFignmU\nCAwKkb0t/e+dcnzQ1l9p4S6oMF1Q YS4za8bzKBJ2HY8/pAUhsrXJ+eKRbkLIF2blXVxlYeKV8iLa\nhmAWAcEsAoJZBASzOAhmBYkG84EW50 jfEImQD7u9W046tttdRQbVpTXWCypM+fr4M5SGSs193DFz\nWohEdtjdm450BcKRL87Mv2SSefht74k2 FcEsAoJZBASzCAhmcRDMSnGkw2MymQYGBsLh8PB/bXMH\n3z3lePeUgxcil0yyrqy2VFq50U8o46Cq0R M6EiG7m91/PNLlCYQ/Pyv/shqLKoF4RjCLgGAWAcEs\nAoJZHASz/AZjbHgwuwPhbY3Od5uc9j7/BZXm ldWW2UX6ke7REuWNcB4loSMRsrfFvenoGZef/+9l\n5TMKdDHfMM7fBcEsAoJZBASzCAhmcaQNZkyXmo DRh1j/u9Wz5aTj3639Mwt1103JuaDcpGFHnOyk\ntDweFG1Y3N+UosjictPictM7DX3r3rNfPdn2lTn5 Q0vnIx0exf5eAADpAhXz2EbJY5PJdNDe/Y/6\n3m2Nzlwde2mN9ZJqi23klUDSK7dG+cW7PMGHd7QO8P x9y8qrhnXRj/5romIWARWzCKiYRUDFLA66\nslNk9Nuu7kD43VOOd066ugcCl0yyXFFrqx75FnJ65XGM kZ4HIRL5y7HuTUe7vzKnYPXU3Jje+lF+\nZQSzCAhmERDMIiCYxUFXdnKNnseCEPmgw/P2ib69rf2zi/ RrF5XNLeDoSPyMSes8HjRS5zZNUZ+d\nkb+gxPTQjua9ze7vLysdOtoc3doAAOIkq2Lu7+9PxmmT53D7 GA1udfnfru9960SvhqWvnJxzRW1O\nnkE9UvE3uzjOitMZIO6zFOCF3+xve/tE73cuKF9ZY4v51+FPhU qlCofDqJgnRKPREEICgYDcDUkn\nFEWpVKpgMCh3Q9IJTdM6nc7jkXhj+Iyn0WhEvzx5nrdarUOPJCuY nc4Rp/YqxJhJHBXgI9ubnP+o\n76nv8S2vslxVZ5tRYBjsttXr9X6/f3BUdqbmcYy4T92hjv5fbG+eXq D/zpIyo4YZ+k8xT4tGowmF\nQgjmCeE4jqIo9MpOCEVRGo3G7/fL3ZB0QtO00Wh0uVxyNyTNcBwn+koT BMFmO6ekybp7zONf+ur4\nGe/bJ/u2NbkqrdwVNdaLKi06dewo6+h0qen54hfUTF/Dn0lPMPz03vbDnZ 7vX1A679wwHtqtjXvM\nIuAeswi4xywC7jGLg3vMYow/j88MBN895dxy0jkQCq+cZHn66ppyy4gLZ84t Nff306NsYpHBht97\nNqiZ+5aXbW9yPbi95ZJqy23zC9XM2Y8y2JYKAGCcMjmYJ7R5Q4AXdp52vXPK+W HXwKIy0+0Li+YX\nG0ba6AkBM2hWkSHmeb6wyjy9QLd+V+s3Np/8wYVlNbZPuxMwIgwAYEwZ1ZU90W2U yCdrWf+zoW+7\n3VVp4S6dZL2o2mxUMyN9f0yujLntY/aIefIjEfL6x72/O9j1lTn5q86dTHV+VS66si cKXdkioCtb\nBHRli4Ou7E+JSOJBXZ7gllPOd046gmHh0knWpz9TUz7qXk8o9UYXUzpTFLl+as7MQv2D 25o/aOv/\n72VlFu7sxXaozc3z/PAVPQEAgKRdxZxIEkd5Q8Iuu3PLKefxbu/SctNltba5hfqRuqzJWH mMinm4\nmL9RgBee2de+t7X/vmWlc4uNhBC1Ws3zvCAI+KwzfqiYRUDFLAIqZnGyt2JOJJVDgrC/1fNe o3Nv\ni7s2R3tpjfWBFRX6kbusCUpksWIGhWlY+rtLS3fYXf+7rSW6vPbgKiS45QwAMFw6BbMIQiRyrM v7\nXqNzp92Vo2NXVFu+Nr+wwDDadsiICknE9GwvrzRPztX+fEfL3f9o+sllk3I5jNYGAIgvnbqyJ1Qx \nN/b53210bGt0EYqsqLasqLaMspZ1lIh4QFf2mIb+1cJC5IXDXZs/7rtrcclFVeah34ZsHh26skVA\n V7YI6MoWJ3u7ssej0xPc2ujc2ujs8/LLK833XVg2PV83ynbIBJGQZENLZ4ambplbeH6F7afvndrf\n5v 7WohKORekMAHCODKmYe7yhHXbXvxpdTQ7f4nLTiirL/FLD0K2C40o8BlAxj9PQv51are71+Nfv\nbGlx BX540TkTnQmyeQSomEVAxSwCKmZxUDF/yuUPb7c7tzW6TvR655cYV5+Xs6TcpGHHyGOCd/+U\nixkRZu bYn6yoeP2jnu+91RQz0RmlMwBkubQMZk8wvPu0+19NjqOdA7MKDVfUWn62cowh1oPwji+j\nod3aFEWu Py93ZqHhf7c3H2jzfH9Z6eBEZ4IB2wCQxdKpK3tfi3tPs3tbk+uDtv6pebqLqy3LK80m\nzbjymCQnkt GVLQLHcftP9w2u/BXghV/+u2NPs+u7S0oXl5uGfieyeRC6skVAV7YI6MoWJ0u7sg+0\n9//Xn45X52gv qjTftbg4R6ca/8/i/V1pZhUZDrW5o/+tYem7l5QsKjU+tqd1cavp9gXFWhVGhAFA\n9kqbijkQjmxvdI w+BXm4ZL+no2IWYXDbx5jRfE4//9juNrvDf9/ysvPyz1mwE9mMilkEVMwioGIW\nR9qKeexxUgqhYagJ pfKsIgPezRUu5m9k4difXlLxuZl5P3jX/vzBLn7ILhdHOjyJr8YKAJAW0iaY\nxw+RnF5i/lhX1dl+eU 3NwU7PXX9vbHEFhv4TshkAskFGBTMiOU3F/NWKjerHr6heXG765punNn/U\nO/RmC0pnAMh4aTP4axQI 4wwQM9GZoakvzcpfWGJ4aEfr3hb3PReU2oYM98OgMADIYOIrZq/Xu27d\nuh/+8IdPPPFEkkaQjQfenT NJzF+zLlf37LU1hSbNba83/KvRGfPNKJ0BICOJD+adO3fOnj37wQcf\njEQiDQ0NErZpnNBxnZFi/qwa lv72ouL/ubB844HOH2xp6vIEh34zerYBIPOID+a8vLzm5maHw9HT\n02OxWCRs05gQyRkv5u87v9jw21 V1FRbuttcb/nysOyyc00ODbAaATCJ+HrPb7b7//vv1er1arb7/\n/vtVKhUh5I477mhra8vJyfnNb34j aTsJIeRgq2tuqXns70shhmEEQZCxJz8dURRFCBnnk3aw1TX0\ny4/PeH7+3kkhQu5fWTMlP/bDmdIuDw nRNE0IEYZMIYPxoGkaT9pEMQwTDoflbkWaSeRK8/v9er1+\n6BHxwbxx48bZs2fPnz//lVdeMRqNl156 KSGksbExEAioVKqY6dKZymQyDQwM4CKeELVazfP8+C/i\nw+39Q78UIpFXPux5/mDnVXW2W+YVDS4TFj W72ChZQ5WE4ziKorBWxoRQFKVWqwOBwNjfCp+gadpo\nNLpcrrG/FYbQarWiX56CINhstqFHxI/KDoVC 0VAXBGFw6avq6urofyRjrWwFikQi4XAYK39NCMuy\nEwrm6fnamM7qVVNtS8sMT77fvuZvH317UfGisk 9X2D7Q4iSZOCRQEASKonClTQhFUdGLTe6GpBOG\nYSKRCJ60iRqag4kTXzGfOXPmySefZBiG47jvfe97 Go1m6L9mSTBjSU4RBpfknOgPDr+XvL3J9cy+\ntukFhm+eX2Qbtnx6JsUzluQUAUtyioAlOcWRdknOtF krW5kQzCKIDmYSL5s9wfDGDzq32123zi28\nerKVHtzY+ROZEc8IZhEQzCIgmMXJ0rWyAUi8AfkGNfOd JSX/u7Ly9Y97vvOPRrvDH/MjmFIFAOkF\nwQzpZ3gRPC1f96traxaWGr/9j1PPH+wKCrH9QIhnAEgXCG ZIS8NLZxVNf2lW/rPX1n7U4137Sv3B\nc8dyRyGbAUD5EMyQxoaXzsVG9S8urfrS7Pz/3dby6K5Wtz/2 9j9KZwBQOAQzpLfhpTNFkctqrP+3\nuo4XIl95pf7Fo2f8fOxAM8QzACgWghkywfDS2cKx9y0ve/iyys OdA1/8y8cvHT0Two1nAEgHCGbI\nEHFXUK/L1T1yWdVPLql8v7V/zd9O/L2+T0A8A4CyIZgho8SdtTw9 X/fElZO+vqDoL8e673jz5Adt\n8ceFIZ4BQAnEL8kJoEzRbI5JWYoiyyvNS8tN/zzpeHR3a5lJ89V5hV PydDE/e6TDkxkLkgBA+kIw\nQ2aaVWQYXgEzNHVVnW3lJMurx3t+sMU+q1B/y7zCcvM5q8kO/hQSGgBk ga5syFgj7dutZujPzsh/\n4b8ml5o133zj5P/b3XpmIDj829C5DQCyQDBDhovG8/CENqiZr84r/L/VdT RFrX214dcfdLgDcbbv\njMYzEhoAUgbBDNkibjzn6lR3Lyn51bW1XZ7QV/52Iu6k5ygkNACkBu4xQ3aJ OzSsxKT+0UXl9T3e\njQe7Xvuo97Mz8i6dZDVpmLhnwE1oAEgqBDNko7hDw6KTng+2e/76Yff/HehcWm 66otY2u0g/fCvJ\nqKFnQEgDZLZUfiJHMEOWils6E0LmFhvmFhu6vaF/Njge291KCLmiznZ5rTVPpxrl bAhpgIwky90r\nBDNktZHiOU+n+tKs/C/MzDvcMfBWQ9+av52YVai/ss62uMzI0mOMzEBfN0Bak30oCY IZYMR4pikq\nWkC7A+H3Tjn/cKjryT1tl9ZYr6y1lVs08c50jtFf3sqMbQnfkpT5CwKMRPY8HkRFIrFL B0uip6cn\nGadVGqvV2t/fz/OxewvCKDiOCwaDghB/8LO8xnxlnujxvlXv2NrkrLJyV9Xazi8zWjgpP9 2OFGY6\nnY6iqIGBgdF/XDnvLKNLTWZTFMVxnM/nS8FjZQyGYcxmc19fn9wNSRERL5m4V69erx/z5TmK 3Nzc\noV/GBvOTTz45/GesVuvNN988oYdBMMNIlBzMUWO+VgO8sL3J+c4p54dnvIUG9bR83cxC/bR8fY lJ\nnaQmcRxHUVSmZkySchrBLEKWBHMiH2FTEMyxH/b9fj8h5OjRo7t27brpppsYhvnLX/4y0VSOtlJ0 \nE9MITdNarVbJGaNALMuyLJukrhpJLKk5e/UeanPH/QYtIdfN1F83syTAhz86M3Cko3/H6f5n/t2h\n YaiZRcZZRcZZRcaaHB1Dxx/OLQLLsoQQrVYr1QkVpd4Zu7TLnBJT4qelKIphGHqsMQEwFEVRFEVl\n8B t49EWdyEsp7pOjUqlEP2mhUCjmSPyu7PPPP//NN9/My8sjhPT19V199dXvv//+hB4JFTOMRPkV\n83Dj +XwtCBG7M3C003PsjPfYmYGBoDA1X1dj5XL0KgvH5ulUFo7N0bF6dfzp0aOTtmIOhoVAOOIJ\nhCOEeI JhQog3GBYikQAfCQkRXoj4eCESIZ4ATwjxhgSGpjQMRQjRqRmGphiK6FQMIYRjaZYmhFAG\nDUMI0TCU hVOZNMwI88vEE1dSo2IWIVMr5mQPnkhuxRzV2dlpsVii/200Gs+cOSP68QAywEijw4ai\naaraxlXbuO vPI4SQTk/wP10Dzc7AqT6/wxvq8Yacft7p51U0ZdWqcnQqm5bN1assHJurY61aVjVy\nec3StFkvUBTx BwKCEPGGwoQQbygiRCIhIRJdqswT4CMREgxHgkIkyAuBcMQTDEf/1RsMB3nBxwu+\nkBASyECQJ4RQFD GoWUKITkXTFOFYWkVTLEtzLE2Ts7lr0NAUobQsFeZJXzhCCOkP+AkhvBDxhwUS\njXMhwkcivpBACPHz gjsQjhBi1jAWjjVzrE3LmjSsRcuaNaxNx5o5Nl/P5unUE03umGcew8pgnNJl\n1EWM+MF8xRVXXHfddb fffjtFUc8999zll1+e4mYBKNBgHozn1V5oUBcaYm85h4WI08/3+vg+b6jP\nx/d6eYePr+/1Of08P8JS oISQ/mCYomlCSEQQCCFGNUMI0bC0iqVpEtGpzuYrQ1MqhuJY2qBhbTQx\ncloVRTgVo1PRapbmWFqnYl Q00amZaAyLfRrG4A6EnT7eGeBd/rDDG3IGwk4/39jnd/p5l5/v9AQj\nkUiJSVNs0pQY1cUmTbFRXWJS 5+lVIy3kMhxyGkaRpmE8VPyu7FAo9Nvf/nb79u00TV944YW33HKL\nSjXa6grDoSsbRpKOXdlxpfL1n0 mDv3q8oXZ3sM0daO8PtrkCbZ5AmysYjkSKjZoSs6bEqC42akpM\n6korZ9OKHPEejWp0ZYuQpl3ZqXwx yjAqO8rj8bz33nvRgWCEEJZlb7jhhgk9DIIZRpIxwTwoBW8K\nmRTMcfV5Q639wXZ3oL0/1OoKtLr9La 6gVkVXW7lKK1dl5SotXKVFM6E79BRFqdXqQCBAUFWPWxoF\ns1yVsWz3mG+99dZAIFBdXR39kqbpiQYz QPYY+kLNgG40Wdh0KptONbPg03GtYSHS6g7YHYFGh29/\na//L/+nu7A/m6lWVZk2VTVtp1VRZuXILpx 5fn/xIfxcEdnrJktdX/GDmef71119PcVMAMoCiQlr2\n1EnkGWBoqsLCVVi4C6vM0SPBsGB3Bux9Prsz 8N4pp93p7/PxxUZ1lYWrsnKVNm2VRVNsVE9ollrc\nFsr+vGUt2V8yChE/mGtqapxO5+DAbAAQQcL390 9W/hIz1UpGYz4DE3ojVjN0XY62LufTGaj9wbDd\nEbA7/E1O/2sf9tidfh8frrCc7feuztHW5pmsE1/0 ZZRWIbOlhSSOK34wt7W1FRcXL1682GazRY/8\n5S9/SWGrACArxM258b9ZG9XMjALdjALd4JFeb6jJ4W 9y+O1O/47T7mZXM0NRFRZNlZWrsnIVFs0k\nm3aknbbHA5mdICTxeMQf/LV79+6YI0uXLp3QeTH4C0aS eYO/UmCca2VnKnHv5hRFqVQqe6+nyeE/\n7fQ39vntTn+rO2hU01U2baVZU3k2rTmdKhWrg6VFcks4+C tTM1i2UdmEkE2bNu3fv//RRx/dvHnz\n6tWrJ/owCGYYCYJZhCwP5rjGfN8fOip7UEgQWl3BJoff7gzY Hf4mh6/LE8rXq6psXKXl7PDvMota\nldqFPJWT2SKCOVMDeCSyjcr+8Y9/vH//frvdTlHUM888s2/fvo cfflj0QwIASG74++N4EkJF09Fu\n7cEjvpBw2ulvcvibnP63TzrsfT5XIFxq0lRauWorV2Hhqq1coXEC 65+IoPBB49kWvbKLXzFPnjz5\nwIEDq1at2rJlSygUqq2ttdvtEzovKmYYCSpmEVAxi0BR1Ee9wZiKeT zcfr7JGWjq89mdgSan3+4I\nhMJCpUVTaeWiaV1p5XJ1E1tzSV7jnyxA07TBYHC742/fAkTGijkYDA7u d+H3+zN1TxsAyGxzSkwx\nq7KMp/gzceysQnZW4aeTqs94gnZXoKnPZ3f4/9XoPO30a1gmGtVVFi4a2I mMKUs2lLzpJX4w33nn\nnZdddpnD4Vi/fv2mTZtuv/32FDcLACAZxE00zzeo8w3qhSXG6JeCEGn3hJoc frvDf7hz4LWPetv6\nAxaOrfpkkbIqq6bCwmlY7DgJYow4+Gvr1q3btm3T6XQrV66cP3/+RM+LrmwYCb qyRUBXtggi1soW\nXVmGhEizM9Dk8NmdgaY+v93p7x4IFRrVZ+doWbUVFk2pWc0qfnNodGWPSZ6u7L6+ vl//+tf33Xff\nihUrRD8MAEDaEb1wm4qmJtm4SbZPx5R5g4Ld6W9y+pv6/G+e6D3V5/fxQplJHe33rr Rw1TauQD/h\nHTAhG8QJZrPZ/Mc//vGzn/1sVVVV6hsEAKAECa6uqlPT5+Xrzsv/dPETh4+PltR2h//9 5v7TTn+E\nkAqLpvpsVGsqrVrRG2pBJolzETAMM23atDlz5ixZskSvPzv8ASt/AUDWkmQJdKuWtWqNc4 vP3qiO\nREjXQDDa7/1xj/fthr4WV1DL0tU28RtqQWbAyl8JwT1mEXCPWQTcYxYhBfsxSzvaeeiGWqed gUaH\nP5ENtcTBPeYxyTZd6sUXX3zmmWcGv1yzZs1EgxkAIOPFvEcnmNMjbqjl8Nsdfqk21ALliw3mqV On\nEkKam5u3bt0aPcLzfNxtpv7617/u27ePEOLxeBYuXHjLLbckuakAAIom+aafo22o5Yi3oZZNW2HR \nFBgmvqMWKElsV3Zvby8h5I477vjlL385eNBisTDMiPc5nnnmmRtuuKGwsHDoQXRlw0jQlS0CurJF\n SEFX9jgldX2PoRtqNTkCp51+lqZFb6iFruwxybmJxTg1Nze/++67t956a/TLLVu29Pf3a7XaZcuW\nJX LadKHT6fx+PzJmQlQqFc/zCV542UatVlMUJWJ1yWxGURTLsoOLGCrEobbkZl6EkI7+QGOvr8nh\nP9Xr bXL4WlwBk4aptumqrNoqGzcpR1tp1WpHWPyEpmmNRqOETzOKNafENPygRqMR/fIc3i2d6ND8\nv/71r7 fddtvgl0ePHu3u7jabzVkyBzr6ykfGTAjDMBSV6CfCbBPtslKp0ml9ZtlRFEUrb0GPhZU5\ng/99sNWV jIcot7LlVv1Fn3zJCxG7w9fU5z3V63+/2f3Hw52d7kChUVOdo6226attXLVNV2nTsjRF\nCKEoihDCsp i1NaK4L0OapkW/PIe/GSb07A8MDPh8PqPROHjke9/7XvQ/sqcr2+v1oit7QtCVLQK6\nskVQTlf2SGrN n35uSGp3d7GWFJfolpboCLGRTzbUanT47U7/5uOuoRtqTbJppxRZCzVCsjfUSl/9\n/XE+7SXYlT00Rk mCwXzgwIGZM2cmcgYAACBJGDg2Cq2KnpKnm5L36eInbj/f6PDbHf7TruCBQ20n\nuwfSfUOttJZQMO/f v/+mm26SqikAAEBSG9JRJo6dXWSYXWQYHPw1uKFWU9+wDbWsZ5dAMWLxk+RI\n1q2+7OnKxqjsiUJXtg joyhZB+V3ZE5KahB5pVPbghlpNDr+9z9fkDLRn64Zasi0wAgAAipL6Mnoo\nmqZKTepSk3pZxdkxySEh ctrptzv8dmdgu935wuFA90Co0KCusnGVFk11+myopUAIZgCANDMY0qlP\n6EEqmqqxaWtsny5+MhAMn3 YGmpz+Jof/jRO9jeduqFVl4aqwodb4IJgBANKVvGV0DL2aibehlt/u\n9Ec31LI7/eTcDbWqrForNtQa Bs8IAEAmUEIZHcOqZa1aw9zisw2L3VCrvq/Ffc6GWlUWrgIbaiGY\nAQAyjAITOoqiSKFBXWhQLy4/e6 OaF4RWV/C0M9Do8O1v7X/5P92d/cE8varCoqmyaiutmkoLV2FN\n7oZaCoRgBgDITIrq6I6LpenoHejB DbUCvHDa6Y/uqfXeKedpp7/Xx5cYNVUWTc3bRuoAACAASURB\nVKVNW2nlsmFDLQQzAEDmi4a0MuN5KA 1L1+Xq6nI/vVEd3VCryeGzOwKvtX+6oVaVhau0aqqsGbih\nFoIZACBbKLaXexRGNTOjQDej4NOoHtxQ q8nh3253n7OhlkVTaeWqJ7KhlgIhmAEAsk66FNBx5ehU\nOTrV/JKz60sLkUinJ9Tk8J92+v9zxvtmfV +rO2hU01U2baVZE11StMLCaVVpM6MawQwAkKXSsYAe\njqaoYqO62KheWj64+InQ4gpGFz/Z29L/4pEz ZwZC+XpVlS26SBlXaeXKzGqVUhc/QTADAGS7wYT+\nT5dX3pZIQkXT1Vau2soNHoluqBWdVP32SYe9z+ cOCiVG9WA9XW3llLOhFoIZAADOml1sNJvN//ow\ndq3sdBdnQ61AuLHPF62q/93Wb3cEeEGosHDRjTrk 3VALwQwAAOfIjC7u0Zk0THRDrcEjZzxBuzPQ\n5DhnQ60qC1dp5SqtmlRuqIVgBgCA+NJ6jNhE5RvU+Q b1wtJPxpQJkXZPKLpN9eF2z6vHe9v7A1fU\n2p6/YXKyW4JgBgCA0WRVPA8a3FBr+ZANtQaC4RQ8NIIZ AADGlg3926NT0ZSFS0VoKnSwOAAAKNOs\nIsPQxT5BcghmAACYMMRz8qArGwAAREL/djIkK5g5jhv7m9 IfRVFqtZpl8flmAlQqFUVRkUhE7oak\nE5ZlKYrKkpeVVCiKUqlUuNImhKZpcVfa+VUcIeRQW6ZNgB4u 7pPDMIzolyfP8zFHkpUooVAoSWdW\nmnA4PPxphVHQNM3zvCAIcjcknUSDOXteVpKgKIqmaTxpE8IwDE ngDXx6vpYQcri9X8o2KUzcJ4dl\nWdFP2vA3w2QFczicijHlsotEIuFwOEt+WakIghAOhxHMEyIIAkVR uNImhKKo6MUmd0PSTPRtLZEz\nRHeCytTO7bhPTuJP2lAY/AUAANLD0DDREMwAAJAUGLktDkYtAQBAEm Hk9kShYgYAgFRAAT1OCGYA\nAEgdxPOYEMwAAJBqiOdRIJgBAEAeyOa4EMwAACAblM7DIZgBAEBmiOeh EMwAAKAIiOcoBDMAACgI\nshnBDAAAypLlpTNW/gIAACXK2iXDUDEDAICiZVv1jGAGAACly6rObQQzAA CkhyyJZwQzAACkk4yP\nZwQzAACknwyOZwQzAACkq4yMZ/HTpSKRyG9+85szZ86YTKZvfetbFEVJ2CwA AIBximZzxsyqEl8x\nf/DBB3q9/v77758zZ05XV5eEbQIAAJiojKmexQfz8ePHw+HwU0895fP5CgsLJW wTAACAOBmQzeK7\nsj0ez8DAwJo1a5577rm8vLw5c+YQQm6++ebW1tbc3NyXX35ZukYqF0VRZrNZ7lak H71eL3cT0kz0\nVhHHcXI3JP3odDq5m5BmKIrKycmRuxUJWZGTQwg50OJMxslzcixxj4t+efp8vpgj4o NZr9cvXrw4\nPz9/2bJlp06digbz+vXreZ5nGMbpTMozojRms3lgYIDnebkbkk40Gk0wGIxEInI3JJ1o tVqKorxe\nr9wNSScURanV6kAgIHdD0gnDMEajMTPewCcZCSHkcHu/tKeN+9xotdrh+TpOgiDEfHwUH8 w1NTUn\nT56cO3duU1NTTU1N9GBBQUH0P3p6ekSfOY1EIpFwOBwOh+VuSDoRPiF3Q9KJIAgUReFKmxCK oqKv\nULkbkmYy7EmbUaCTdlBY3CdH2idN/D3mRYsWNTU1/eAHP+jp6VmyZIlUDQIAAJBQ2g0KE18xsy x7\n7733StgUAACAJJlVZEiX+VRYYAQAALJCupTOCGYAAMgiys9mBDMAAGQXhWczghkAALKOkru1EcwA \nAJCllBnPCGYAAMhqSstmBDMAAGQ7RZXOCGYAAABCFBPPCGYAAIBPyZ7NCGYAAIBzyFs6I5gBAADi\n kCubEcwAAADxyZLNCGYAAIARpb5bG8EMAAAwhlTGM4IZAABgXFKTzQhmAAAABUEwAwAAKAiCGQAA\nQE EQzAAAAAqCYAYAAFAQNknn1ev1STqzotA0rdVqBUGQuyHphGVZlmUjkYjcDUknKpWKZM3LSioU\nRTEM Q9MoPyaAoiiKonClTZRKpRL9pIVCoZgjyQrmgYGBJJ1ZUdRqtc/n43le7oakE47jgsEgPs1M\niE6noy gqS15WUqEoiuM4n88nd0PSCcMwarUaV9pE6fV6CZ80CoVLIr7+9a/fc889tbW1cjcEMtyL\nL77o8/m+ +tWvyt0QyHDt7e333nvvH/7wB7kbktWSVTFnia6uruG9EACS6+/vRxEDKcDzfEdHh9yt\nyHYI5oQUFB REb/4BJJXRaGRZvFoh6ViWLSoqkrsV2Q5d2QAAAAqC8YoAAAAKgmCesP7+/h/+8Idy\ntwIy37p16x57 7DG5WwHZIu4729tvv71nzx5Z2pPNcNcKQIn6+/u9Xm9PTw/P8yPdXfb5fFqtNsUN\nA4BkQzCL1NfX9+ yzzxJCNBrN3Xff/d577zU2NqpUqq6urnvuuQcjwiBB+/btW7RoUWdn59GjR+fO\nnfvCCy/4/X6KohwO x7e//e2dO3cePHiQ47i77rpL7pZCRnnjjTeKiormz5//pz/9afbs2XI3J0uh\nK1ukvr6+1atX/+AHPx AEobu7mxCi0WhuvfXWysrK48ePy906SHu7d+9etGjRggULBjsS8/Lybrvt\ntqlTp7777ruEEIvFglQG yEgI5gk4evQoISS6ZJXFYtmyZcuvfvWr5ubm6Mj26upqQohWqw2Hw/K2\nE9LdwMDAsWPHNm3a9M9//n Pfvn3RSy56gVVXV3d2dhJC6urqZG4lZIqh72yDsDafjBDME/D88887\nHI729na9Xv/6669fdNFFt99+ u9VqjQYzRVFyNxAyxL59+66//vp777133bp106dPj/bB1NfXE0I+\n/vjj4uJiQgimNYNUhr6z0TTt8X gIIR9//LHc7cpeeG1PwOrVqx988EFCyNq1a3mef+2117Zs2VJY\nWLh9+/acnJzo96hUKp1OJ2szIe3t 2bPnS1/6UvS/ly5dumfPHo7jTp48+Ytf/ILn+XvuuWfnzp3y\nthAyydB3ttzc3Mcff3zPnj15eXkYKy MXLDACkAZeeOGFJUuW1NTUyN0QAEg6dGUDAAAoCCpmAAAA\nBUHFDAAAoCAIZgAAAAVBMAMAACgIghkg Kzz88MNPPvmk3K0AgLEhmAEAABQEwQyQsUKh0O23315Z\nWXn++edHl110u93XXHNNWVlZbW3t1q1b5W 4gAMSBYAbIWL/97W/tdnt9ff0bb7yxa9cuQsimTZus\nVmtLS8uvfvWrzZs3y91AAIgDwQyQsbZv337H HXeo1er8/PybbrqJELJkyZKdO3f+6Ec/MhgMTzzx\nhNwNBIA4EMwAGYum6cG9VRiGIYTMmjXr0KFDJS UlDzzwwOrVq2VtHQDEh5W/ADLWr3/96zfeeOPV\nV191u90LFy781re+5XK5wuHwT37yk46Ojrq6Orfb jV3RAJQGu0sBZKxbbrnl0KFDkydPzsvL+/KX\nv2y1Wq+99trPfe5zv//971Uq1YYNG5DKAAqEihkAAE BBcI8ZAABAQRDMAAAACoJgBgAAUBAEMwAA\ngIIgmAEAABQEwQwAAKAgCGYAAAAFQTADAAAoCIIZAABA QWReknNgYEDeBgwXXes/HA7L3ZBUoyiK\nZdlQKCR3Q2TAsqwgCIIgyN2QVKNpmqZpnuflbogMVCoVz/ NZuPRh1r7FEULUanUwGJS7FXHo9fqh\nX8oczD6fT94GDGcwGARBUGDDko1hGI7j3G633A2RgdlsDgQC ynzFJpVGo+E4LguvdkKIVqsdGBjI\nwnzS6XQ0TWfhH52iKL1e73K55G5IHDHBjK5sAAAABUEwAwAAKA iCGQAAQEEQzAAAAAqCYAYAAFAQ\nBDMAAICCIJgBAAAUROZ5zKAch9v7De6I2+2ZVWSQuy0AANkLFTMQ QsiRDk/c/wYAgBRDxZzt4sZw\n9CBKZwCA1EPFnNVGL45ROgMApB4q5iw1ztBF6QwAkGKomLPRREthlM 4AACmDYM464lL2SIcH8QwA\nkAII5iySeLgimwEAkg3BnC2kylSUzgAASYVgzgqSRymyGQAgSTAqO8Ml L0ExYBsAIBlQMWeyFNS1\nKJ0BAKSFijkzpTIvUToDAEhI5mBWqVTyNmA4mqaJIhs2fofb+1l2wn/Z6C 8u4gejPuz2zy42ivtZ\n2VEUxbJsJBKRuyGpxjAMRVFpfbWLFv2jRy/7rELTNE3TWfhHpyiKKPK9XRCE mCNZd1FmvMPt/TI+\ntIyPDgCQGWSumEOhkLwNGE6j0QiCoMCGjSnB7uto6cDzfILN+KDZkXbd2pFIhO f5dPyjJ4im6Ugk\nkoW/OPnkjx4Oh+VuSKpFS8Ys/KNHK+a0+MVRMWcIRQ3CwlxnAADREMxpT6oUfOek 47a//uc/Xd7E\nTxWFbAYAEAHBnN4kCT9vSHhoR/PvDnQsLreue8/+9N52Px87GEEclM4AABOFYE5jkm RefY/3G5sb\nAnzk19dPvnVh6W9X1fV4Q199tf6gdMO4kM0AAOOHecxpSZKoi0TIqx/1PH+oa82cgtXn 5UYHf9m0\n7AMrKnbYXQ9ub1lYYrxjUbFRzST+WJjrDAAwTqiY048kqez08z98t+nvJ/qeuGrS6vNyY/ 51eaX5\nt6vqArzw1Vfr9zS7E3+4KJTOAABjQjCnGUmy7WB7/9debzBr2F9eU1Nt5eJ+j4Vj162ouHtx yZPv\nt/30X81uf6LTqKJw1xkAYHQI5rQhSaSFhcgLh7p+tq3lzoXF9y4v07BjXACLy00bV9UZNcza1+ p3\nnkbpDACQdLjHnB4kSbIuT/DBHS0kQn51bU2hQT3OnzKqmbuXlCwtNz2+p/Vfjc67FpeYOdx1BgBI \nFlTMSidV3+8Ou+v2N07OLzI8cWX1+FN50MJS48br64wa5pZXTvy9vi/x9kShdAYAiIGKWdGkmqa8\n 4f22I50DP1lROaNAJ/o8ejVz95KSZZXmx3a3vt/s/s6SklydBMvBo3QGABgKFbNySTVN+fbNDT5e\neP a62kRSedD8YsPvVtVVWrmvvdaA0hkAQHKomJUoGdOUEz/hIA1Lr51XuKjM9Oiull12191LS/L1\nE+4b Hw6lMwAAQcWsQJKksssfHmWasiSm5+t+fV3tpBzt118/+ff6Pqn2MkbpDABZDhWzgkiVSQfb\nPb/Y2T KvyPDjiyvGnBCVCDVDr51XuKTM9Oiu1vdOOu+5oLTYhNIZACAhqJiVQpJU/mSacvMd45um\nLInz8nXP Xl97XoHuG5sbXjp6RpCodkbpDADZCRWzIsg4TVkSappaO6/w4irL+l0t77f237O0tMys\nSfy0KJ0BIA uhYpaZQqYpS2KSjXv6M5MWlxq/+eapl46eEQSUzgAAEyZlxczz/FNPPeXxeMrLy9es\nWRM96HA4Hn74 YYqiCgoK7rrrLoqiJHzEdCftNOUHVlTMLNAnfsJEsDT9uZn5C8tMj+5s2dPSf8/S\n0nILSmcAgAmQsm Leu3dvcXHxunXrOjo6Wltbowe3bNmycuXKhx56KBAINDY2Svhw6U6aacq9vts3\nN3h54dnramVP5UHV Vm7DZ2qWlBnvfPPkxgOdvCBIclqUzgCQDaSsmBsaGqZNm0YIqa6ubmhoKC0t\nJYQsX77cbDb39PS43W 6LxRL9zq6uLp7nGYbRaCQop6RFURRFUQwjwXLQIznc3k8Iie5/nIi/fdj9\nu4Odt8wtvGFaXuKtiv7K ibcqiqbJF2YXLqm0PLKj+c62/v++oLw2V5v4af/T5SWEzC42Jn6qoSiK\nomk6qX90ZaJpOtlXu5Jl5y +egrc4ZYr21yrwFxeGlS5SBrPX683NzSWE5OTkeDxni5vCwsJAIPDI\nI4+wLKvXny3pvv/977e2tubm 5r788ssSNkASFEVFIhGOi78ZYuIOtDiNxkRzxeEL/eSd+na3f+NN\ns2pzpSmU55VZKIqKRKwHWpySnJ AQMsNofOELua8d6/ze26dumFn09UUVKkaCexmn+sm8Mkvi5xlE\nUdTgxZltKIoa/MScVSiKSvyVmKYo ilKr5RmJIjsFXu0+ny/mCBWRamEIQn73u99Nnz59wYIFL7/8\ncn5+/sUXX0wIiUQi0c8pzzzzzJQpUy 655JKhP9LT0yPVo0vFYDAIguD1eiU/s+TTlL+zpESqCVGz\nigwMw5jN5r6+PpKETuP2/uD/29XqDvD3 XFA6OVeClUGjpLrrbDabfT5fMBiU5GxpRKPRcBzncrnk\nbogMbDaby+UKh8NyNyTVdDodTdODtVP2oC gqJydHgaFDCInWtIOkvMdcW1trt9sJIc3NzTU1NdGD\nGzZs+PjjjwkhVqtVqm7SdKTYacqzigzD4y3u wUQUG9WPXlF9/Xm5975j33igM4gB2wAAI5CyK3vR\nokVPP/30+vXr8/Pzy8rK6uvr33nnnVWrVm3YsE Gr1RoMhhtvvFHCh0sjip2mPHr6Rv9VqvCjKHJ1\nnW1eseGx3a1rX62/54JSSUarYcA2AGQYKbuyRVBg r4K0XdlSpdoOu+uJ99uun5LzpVn5NC3NlLOY\nMBvalR1D2sI0EiH/aOj79f7Oi6rMty8s4qTrjRf9s+ jKlrshMkBXttwNSbU06srGyl9JJNU05ef2\nd+xv7ZdwmvJEMywZpfOiUuOT77ff9lr9d5eWzpGi3kXp DACZIXtv+iaVVOt5RacpO/28hNOURUeX\ntJmXo1P99JKK2+YX/exfzY/vafOGMNcZAIAQBHMySLWb8i vHe+55u/G6qTk/WVFh0kgz9y7BcJV8\nUNjySvPGVXUuP3/ba/UH2vslOadUn4oAAGSBrmyJSbWb8sM7 mzs9oSeumlRtlWZGtYSBOqvIIGHy\n2bTsAysqdthdD25rmV1k+M6SEkk+hRzp8KBbGwDSESpmyUhVqB 1s93zt9Xqzhv3VNTUKTOXBE0pe\nOv/f6joNQ619rX53s1uSc6J0BoB0hIpZGlJNU9505MyrH/Xetbjk oipz4ickSR4MJe2gMAvH3ru8\n7P1m9xPvt713yonSGQCyEypmCUg1Tfnutxo/aPf86tqatEjlJD3K4n LTb1fVGTXMV189sfM0SmcA\nyDqomBMi7TTlq+psa+bksxKtj5bKMlHa0tmgZu5eUrK03PT4ntZ/NTrv Wlxi5lA6A0C2QMUsnlTT\nlB/f0/bsvzseWFGxdl6hJKks+Q3g8T+uhGdbWGrceH2dUcPc8sqJv9fHWf ZEBJTOAKB8qJjFkOrN\nvb7X9+C25kor9+y1NSZOmr+FvEWhtKWzXs3cvaRkWYXp8T1te067715akqtT JX5alM4AoGSomCdM\n8mnKD1xckRmpPEjakn1+ifH/VtVV2bivvdbw9/o+SdaQRekMAIqFinlipJqm/M jOlg5P8IkrJ1Xb\nFDohKnESTnfWsPTaeYWLykyP7mrZZXfdvaQkX4ptPFA6A4ACoWIeL6lqrEMdnq+9 Xm/SML+8piaD\nUzlK2tJ5er7u19fVTsrRfn3zyVeO9whS1M4onQFAaVAxj4u005S/vaj44mpL4ickCo 7koSQsndUM\nvXZe4ZIy06O7W3faXfdcUFZikqB0PtjqCgQCoVAoLZ5PAMhsCOYxSJUoXZ7gg9tbIinc TVlRpB0U\ndl6+7tnral86cuaON05+fkbuTTPyaEqarTCHtzCNnmQAyAwI5tFINk35tPuJPa3pO01ZKh LGs5qm\nbp5TcEGF+ZFdLXta+u+5oLTcrEn8tMMhqgEgxRDMI5IkP4Jh4TcfdO4+7ZZxN2WlkbBnu9rG Pf2Z\nSX891vOtN099fkbuTdPzaFqa0nkUiGoASCoEcxyH2tx+vz/x8zT0+h7c3lxuyZxpylKRsHRmaf pz\nM/PPLzOt39W6p6X/e0tLKizSDKkbP0Q1AEiIikgyLVQsj0dxA2I1Gs2BFmcoFErwPH891rVxf/va \nBcX/Nb1AkoYRQuaUmKQ61XA0TWu12oGBgeQ9xHCH2qRZDZsQEo6Ql490/v5gx6ppeWsXlLATKZ05\n juN5nud5qRozXFL/dqKxLKtSqXw+n9wNkYFer/f5fIIgyN2QVFOr1RRFBQIBuRuSahRF6fV6BYYO\nz/ MWyznDgWUOZofDIeOjx6XT6Q60OBO5ap1+/pEdLe39gR9dXDlJoglRs4uNkpxnFAzDGAwGl8uV\n7Aca 7nB7v1Snsjv963e0BMLCfy8rr8vVjvOn9Hp9IBBIajAPl4K/6ZjUarVGo+nvl+z5TyNms9nj\n8YTDYb kbkmocx9E07fV65W5IqlEUZbFYFBg6giDk5OQMPSJzV7YCXxWRSCQSiYj+HH2ow/OLHS1z\niwy/vKaG Y2lJPo/PKjKk7ImS5S8yo0An1V3ncpP6yaur32pwfO+tU9dMsX1lToFqHKVzgn90cQ62\nxn4GSn0HuC AIkUhEgS/D1AiHw1n4u0ev9iz8xSmKIooMneHiB3N3d3deXl6Km5LusnaasiQkvOtM\nU9TVdba5RYb/ t7v1js0N91xQOjlXl/hpUwD3qgGAjBTM8+fPnzdv3po1a6688kqVSoJtAzLe4DTl\nX15TU2TMumnKUp EwnouM6vWXV/+joe/ed+yXTrKsnVeoYdNvnTtENUAWiv9W1djY+PWvf/3Pf/5z\nXV3dd7/73SNHjqS4 Wellx2n37ZtPTs7VPn5VFVI5cVL97hRFrq6zPXdtzWlX4LbXGo52pnRcW5JE\n1xAd+j+5WwQAEhtt8J fL5dq0adN9993HMEx1dfWGDRuWLFki7cP39PRIe8LEGQyGAy3OcU6Xik5T\n3nXa9T8Xlqf7NGWGYcxm c1+fNDsfS0Kq1IlEyJZTjmf3dyyrMH9jQZFWFft51GAwRJfklOThZDf+\nS0ij0XAcJ8uIP9nZbDaXy5 UWdxylpdPpaJpW4ODkZKMoKicnR4GhQwjJzc0d+mX8ivnFF1+87rrr\nZsyYcezYsTfffLO3t3fjxo03 33xzSlqYNhp6fV97vaFrIPTctbXpnsrKJGHpfFmNdeN1tQ4/f9tr\n9YcyvcpEVQ2Q1uLfY966des3v/ nNFStWMAwTPTJnzpyf//znKWyYokUi5NWPep4/1LVmTsGqqbkS\nrdOMVI5DwrvONp3qpysqdthdP/tX 87JK89cXFOmGlc6ZCveqAdJIbFf25z//+bjf96c//SkZD6/A\nXoUxu7LP7qbcH7z/ovJM2rdRgV3ZMa Sq/Pp8/Ib32+t7vd9dWjKv2Egyrit7/NRqtVqtlrxXUwnX\n85jQlS13Q1ItjbqyYyvmtWvXprAx6Wdw mvKPLq7hJBrlmxbvYkog1SLbNi374xXlO+yun29vmVVo\n+M6SEgP+ApJKi85z0wBdY0r6yuoAIsQG8y WXXEIICYfDg53YhJC9e/emtFGKhGnKSiBhz/bySvPM\nQv1z/+5Y++qJe1fULCqRZpQApJHD7f1DV5XB 6xEUIv495i984QubNm1iWbanp+d//ud/tmzZYrfb\nU9swZenoD/58ewtNk2evrSnIvt2UlUaq0tnCsf cuL9t52vXwtkaWkHKLutqqrbBwlVZNhYWTqkcE\n0sXQiwovT5BR/GCeNm3aDTfccMUVV/zsZz+75ZZb jh8/nuJmKcrWRueGve3XTcn58ux8RqJdBfGy\nT5CEpfOyCvMlU4pOdLpO9njsjsAOu+uFw/7ugVCBQV Vp5SotXJWVq7Bw5RbNeFb3hMwQc2nhBQup\nFD+Y161b9+ijj95777379u2bOnVqitukHIPTlH+yomJm ISZEKY5U8axm6LpcXZX500XuQkKkzRWo\n7/U1uwJbG52nnf4zA6F8varCwlVauXKzptLKVVo5NaI6Oy CnIZVig/n73//+4H/n5+ffeeed8+bN\nI4SsX78+pe1SgCaH/+fbm4tMmueurcVuykomVc/2UCqaikbv 4JGBYLitP2h3+JtdgR1218YDne5A\nOE/HVli4uhxtNK3LzRoaUZ0F0OkNSRWbN9OnT4/731klEiGvHM c05XQiYc/2SPRqpi5HW5fz6VaS\n/cHwaWfgtNNvd/jfrO871evzhoRio7rCwlVaNGej2qKhpbqAQJFQ TIPkRlySc9OmTfv373/00Uc3\nb968evXqJD28AqeUBWjNjX841O7y//Ci8mpr5kxTHpPy5zGPh7hslm oe8xlP8LQr0NTntzv9dmeg\n2emnaaryk5yutGgqLZxNp6BdYZI0jzktmEwmj8eT7L0+FfjaxzxmuRsS xxjzmKN+/OMf79+/3263\nUxT1zDPP7Nu37+GHH05J8+TH0FS1TXv/8lKpNiNS4Cszg6WgdB5FvkGdb1 AvKDFGvxQikU5PyO7w\n253+j7u9bzf0tbiCWpautHCVVq7SqolmtlQ3SkCBUE+DCPEr5smTJx84cGDV qlVbtmwJhUK1tbVJ\nmi6lwA8vE9rEYnTp9SLMjIp50ISyOWUrf4WFyJmBkN3hP+30n+0Gd/o1LFNu0V RauAqLptKimWTT\nmTlm7HNJARVzsivmUcj1/oCKWe6GxDGuijkYDA6+Sfn9fq1WG/fbYBTplcqZR97S eSQMTRUZ1UVG\n9eJyU/QILwjdA7zd4W/o9R3r8v79RF+LO2Dh2EorV2HWVFq5Cgs3ycoN3xEL0h2KaR hJ/GC+8847\nL7vsMofDsX79+k2bNt1+++3jORfP80899ZTH4ykvL1+zZs0oBzMeXmMKocx4Hoql6Zio DglCmyvY\n7ArYHf4DbZ5XPuxpcQUs2rNRXZujjd6uVjOI6oyCnIZB8YP5nnvumTt37rZt28Lh8MaNG+ fPnz+e\nc+3du7e4uPhzn/vcQw891NraWlpaOtLBDIaXkwIlYz5V8qhoOjpTa3mlOXrEGxRa+wODM7X+ cLhr\n+KTqKiuH9U8yCWZkZbMRR510dHS43e5169Zt3rx5nMHc0NAwbdo0Qkh1dXVDQ0M0g+MePHr0qN /v\nV6lU1dXV0vwe0qFpmqZplhUzHmd2sVHy9qRMdHV0lUpBY4YlNL/cSgg5cW68pwAAHFFJREFU3N4f \n918pimIYZqQZCrIzseQ8nfq8gk+vLk8w3O4O2B3+Ez3e9xpdTY5OdyBcajq77Emlhau0asczU4um\n aYqixF3t6S76i8t4j3n8Puw+Z8hLgu8z0be4TH2lj4KiKKLIt7jhF6GUo7K9Xm/0DnZOTs7gyIK4\nB/ /4xz92dHRYrdbHHntM9C+TJNFUHrqHxzjNLTUnoz0pQ1EUTdN6fSbv5bC0Vn+w1TX8OE3TarVa\nga/Y kWi1JM9smFX26RF3gG/q9TY5fKd6Bv7R4Kjvbh0IhkvNXHWOrsqmnZJnqM7RF5s0MUlNURRF\nUdk5iI SiKI7jFPtpbBQnHPzQLyf6zkPTNCEks1/po1DgLz58rHH8YH7ppZeio7IZhnn77bdra2vH\nE8w6na63 t7e6urq3tzc/P3+Ug4888kj0PxQ4QM5gMASDwQmNyo52NDmdzqQ1KhWio7LT/bcYU7WB\nkGH38zJgP2 aKkGojVW3UXVKuix7p9YZOO/12Z+C00/u+ve9Ur4+mqVKjusLCVVg00W7wihwDRmXL\n3ZBEbf/onH6g Mfu9s3xUtjLf4gznbj0r5ajs6KyqBQsWNDc3L1myZJSDmQS3f9KR8geFJS5Hp8rR\nqeYWD5lU3R9qcv pPO/2nHP73Gp2t7qBORReZOCEcJoQYNAwZ1vWtZ5nh3eEcS6mGDT3TMJR62NR/\nlqI4NvbnaZrSq2N7 pChCDMMOEkJ0qjiLnHIswzKxRzmGVg07qGKo4QsSsBSVwaPccXM6A0g5KnvR\nokVPP/30+vXr8/Pzy8 rK6uvr33nnnW984xtDD0raeJnhok936TUoLEE0RRWb1MUm9dIhM7XO+CLO\nQMTv9/EC8fOxtSMvRHzD DkYixBPgyTBePiIM6xZ2B8MOf+zBAC8Ew7EHQ4IQGHaQD0f8oXDMQYGQ\ngWDsQUKIJxin9h0IhQUhfm c1TVGlZs2UPN2UHO2UPG21jWPpTEtrjPROUyMuybl169Zt27bpdLqV\nK1eOc/CXCMrsyh7PAiOZd4ln 2AIjE3Kqn6R7V7Y42bnAiJ8XQkJErzcea+v5qMvzcbf/454Bl5+v\nyY2GtG5Krq7YJM226wrEcRxN07 XmTPsUMqa0X2Dky1/+8pVXXvmtb30rLy8vJa1KM5mXyllubqnZ\n5/MFg8HsKaCzGcfSHCEmLTu70DAz /+wt+T5v6ESPr6HXt7XR+fTedj4SqbJyMwr00/J0U/N1loxb\nNjV6qeOtTJniX20rV6587733HnjgAY vFcsUVV1xxxRUZeXtYBFzHmS3m74uczh42nWpxuWpwmZeO\n/uB/ugYaen0vHeuu7/EaNWxdjnZ6vm56 oaEuh8uY1V0Gr3C8synKiF3ZhJCenp6XXnrpkUceaW1t\nTdLYRQX2KozSlZ3Z1242d2WbzWcr5jG/M8 OiOju7sqPGPyqbF4RGR+BY10BDj6++19fWHywxquty\ntLW52ukF+hobl147e0a7sr1e7/B/yuy3uLTv yr7jjjt27txJUdSFF174+OOPL1++PCVtU7TMvmRh\nnIZfBhkW1TAcS9NDt+IeCIZP9HiPdXkPtns2HT kTCkeqbFxdjrY2RzuzUF9oSOOb0+jfVoj4wXzk\nyBG/33/ppZcuXrx44cKFWX6nGZcpjAK939lGr2bm FhsH56H1ekP1Pb4Pu71/r+97Yk+bQcNEU7w2\nRzu9UG+MNwdM4dC/Lbv4wbx7926/379///7t27ffd9 99FEWdPn06xS1TCFyaMCEoqbNNzpCb02Eh\n0uIK1Pf6Pjzj3X6gc2ind12ubnIup0qrGVkooOUSP5gP HDiwffv2bdu2HT58eN68eZdffnmKm6UE\nuBxBEojq7MHQVHS58stqrIQQb0hodPjre7zHurx/OnrGFx ImfVJM1+VoK62c3O0dFxTQqRd/8Nf8\n+fMvv/zyyy+/fMmSJUld4F6B9+Gjg78mWzNtdsSYMPhrPIO/ kkSuqMbgr1QuyRnt9G7o9R3r9h7v\nGmAZui5XOz1PV5ujnZavM6VqRtYog7/GI33jOY0Gf402KjsFFP gcGQwGQRBEX7XpC8EsYzDHSFlO\nI5jlWitbECLNrkB9r6+h11ff6zvR4zNpmOn5+ukFurpcXV2uVp20 TTwTDOaodIznNArmrKsLAZQP\nvd8Zjz6309sXEk45/PU93oYe399P9EVvTk8v0E/L19XlaCssnNImZK F/O6kQzABpAFGd2bQqenq+\nbvqwZch22F3P/rtDycuQYYBYMijoDwwA44dpWhls/MuQ1dq44dtnpR7i WVoIZoBMgJI6gxUZ1UVG\ndbTTe+gyZFtOORW1DBn6t6WCYAbITIjqjDR8GbImZ+BYp0dRy5ChgE4Qgh kgW6D3O/Po1czQm9OK\nWoYMBbRoCGaALDWryKDRaDiOc7mS9RDI/hQbugwZLwin+vwfd/tO9Hi3Nbna +gPlZs2UPN2MItP5\n5RZzCt/7UUBPFIIZAJJFUe/F2fYpgaXpybm6ybk6QnIIIZ5g+ESP9+Nu3+7Tzg 17WuYXG1dNy5lZ\noE9ZexDP44dgBoCsEBMJNpvF5aLC4XD0y4yPbYOamVdsnFds5DhuICi8fqz9F9tb jBx97ZTcSydZ\nUrbDNPq3x0Pmlb98Pp+Mjx6XSqWKRCI8z8vdkFSjaVqtVsfdiDrjaTQanucH36OzB8 MwLMsGAgG5\nGyIDjuMCgcBIb4CH2twpbk/KMAxDURTP86GwsNPuePlIZ7s7cNWUvBtnFOTqUz1YbE6J KWWPRVEU\nx3EKDJ1QKGQynfM8YEnOWFiSU+6GyEBpS3KmzCf3mJN2k1nBbDaby+Ua/6exjCmphy/JWd /re/XD\nnp2nXcsqzDfOyKuWY3eNFBTQWJITACCjZPCY9roc7b3Ly9Z6C/9+ou+etxrLLJobzsu9oNxE J229\n7uFwB3ooBDMAwIRlXk7n6FQ3zym4cXre1ibn7w91/eaDjqvrbJ+ZkmNI4SQrxHMUghkAIFEZs5 yL\nVkVfXWe7stZ6uMPzyvHeF//TfXGV5b+m5ZaZNSlrAwaIIZgBAKSX1iU1TVFzi41zi42t7uDrH/Xc \n8cbJWYX61eflzC02prIZWVtAI5gBAJIuTXO61KS+8/ziL80qeKu+d/2uVjPHXjMl59Iaa/K2ix4u\n CwtoBDMAQKqlV06bOeZzM/NvmJ77fnP/X4/3PH+w8/Ja26qpOTk6VSqbkT0FNIIZAEBmaXGLWkXT\nyy vNyyvN0elVX/nbCVmmV2VDPCOYAQAUR8kltXKmV5EMTWgEMwCA0ikwp4dOr3r+UNfGDzqvqrOm\neHoV ydACGsEMAJBmlNP1PXx61eU11v+alluQ2q2gMyyeEcwAAGlP3pJ6cHpViyuw+ePeta81yDi9\niqR/Qi OYAQAyjVw5XWbWyD69iqR/AY1gBgDIcEMjSqfTJTunz5le9WHP8wc7r5mcc93UXDMnw+1n\nkoYJjWAG AMguc0pMHg+d7HiOmV71xb98tKzCfNOMvKqU714V/U1np7ZfPREp2hwbAAAUZVaRIfq/\nZD9QdHrVxl V1OXrV995qvOsfp3bYXYKQ6h2HlTCUfZwQzAAAWS018VxoUK+dV7jpximX1VifP9S1\n5pX6l46e8QTH ux92VkFXNgAAnL0Rm+yyUiHTqxQOwQwAAGelJp4Hp1c19vlfl296lWIhmAEA4Byp\niWdCSLWNu3tJyS 1zC96u71u/q9XCsZ+RY3qV0kgZzDzPP/XUUx6Pp7y8fM2aNdGDDofj4Ycfpiiq\noKDgrrvuoqisfroB ANJFyuLZwrHDp1ddf16uSZPS6VXKIeXgr7179xYXF69bt66jo6O1tTV6cMuW\nLStXrnzooYcCgUBjY6 OEDwcAAMmWmqFh5JPpVU9dPenBS6s6+oNf+PNHD+9oaXL4U/DQSiNlxdzQ\n0DBt2jRCSHV1dUNDQ2lp KSFk+fLlZrO5p6fH7XZbLJbod7766qtut1un01111VUSNkASLMsKgqDV\nauVuSKrRNE1RVBb+4oQQmq Y1Gg3DZN3Hc5ZlaZrOzj86RVEcxwmCIHdDUo1lWRGv9EXVZ7//UJs7\nCY06x4xizYxiS0d/4PXj3d99 q7HSyt04s/DCKgudWIdrtL9WgVc7z/MxR6QMZq/Xm5ubSwjJycnx\neM72fhQWFgYCgUceeYRlWb1eHz 3Y2NjY3d1tNptZVnE3uSmKomlagQ1LtuhVm4W/OMniP3r001gW\n/uJRDMPQdNZNGU3wj76gwkYIOdjq krRRcZRadHcuqbhlQemWht7f7m97bl/rjTMLr5map1Ul9AFa\ngVf78E+HVCSS6Czvd99998MPP1y0aN Hx48enT5++YMGCl19+OT8//+KLLyaERCKR6Dv+M888M2XK\nlEsuuWToz/b09CT46JIzGAyCIHi9Xrkb kmoMw5jN5r6+PrkbIgOz2ezz+YLBoNwNSTWNRsNxnMuV\n9DdZBbLZbC6XKxzOunm0Op2OpunB2ikRKV uyQ4hEotOr/tPlvazGIm56FUVRK6ZXKDB0CCHRmnaQ\nBJ8dVq5cuXLlSkJIKBSy2+0LFixobm5esmRJ 9F83bNhw2WWXTZkyxWq1ZuGHUwCATJWy0WEx06u+\n+mr97CJDBk+vkrKoX7Ro0dNPP71+/fr8/Pyysr L6+vp33nln1apVGzZs0Gq1BoPhxhtvlPDhAABA\ndimLZ3Lu9KpHdrVaM3R6lQRd2YlQYK8CurLlbogM 0JUtd0NkgK7sZJw8letRhwTh/eb+vxzr6fIE\nPjOO6VXZ1ZUNAABAhmywmIKEHty96tgZ7ysf9nzhz7 LtXiU5BDMAAEgslf3b0/N10/PLOz3BN0/0\nffetxnKL5obzci8oN9Fp27+N0VgAAJAUKVuchMTsXnWw a82r9a8c7/HzaTlPHRUzAAAkUSqrZ925\nu1f9/tAZ0dOrZIRgBgCApEtlPA9OrzrV59/86fSq3BXTU/ DgEkAwAwBAiqQyngkhk2zc3UtK1swp\neOPj3od2NIdYzddmWVPz0IlAMAMAQEqlcvA2IcSqZW+eU/CF WQULaksEbxpMDsTgLwAAkEcqR4ep\nGMqmU6XmsRKEYAYAADmlMp7TAoIZAADkh3gehGAGAAClQDwTBD MAAChNlsczghkAAJQoa+MZ06UA\nAEC5Ujy3SglQMcP/b+9eY5q63ziAP71ZWpgpKVeBcRcKLDgKAxUY 6hx1w2wqptMYGIbMIGzZ2Mzm\nmInOsRfb2BIxke2FlyEKTDPQRNyKgFbUcceRgQKVVORSi4AghZb2/F +cjPTfomNOOaenz+cVHnvK\n8/39OOfxHI6/IoSQDbCfC2hszAghhGyGPbRnbMwIIYRsDLPbMzZmhBBC Nomp7Znih78cHR2pLcAa\nl8slCIKGhT1vbDabxWLZYXAA4HA4Dg4OPJ5tLNf3DHE4HA6HY5+TzmKxBA IBQRBUF7LYuFwuw470\nVUGOANB67+GTX8ZisYCWTcdgMFhsobgxP3r0iNoCrDk5OZlMpqmpKaoLWWwc DofH49FwRhYBl8ud\nnp7W6/VUF7LY+Hw+i8Wyz0nn8/k6nc5oNFJdyGITCoVsNpt5k75cxCG/eNzD22 RjtongeCsbIYQQ\nczDg/jY2ZoQQQkxj0+0ZGzNCCCFmstH2jCt/IYQQYjKyN98csoHfLpPwihkhhBDz 2dClMzZmhBBC\niEawMSOEEEI0go0ZIYQQohFszAghhBCNYGNGCCGEaAQbM0IIIUQj2JgRQgghGqF4gR EXFxdqC7B2\n5MgRV1fX1NRUqgtZbGq1Ojc399ixY1QXQoG8vLyUlJSVK1dSXchiu3btWlVV1cGDB6ku hALp6en5\n+fne3t5UF7LYysvLR0dHd+3aRXUhi21ycvKtt96qqKggP82CznDlL0tjY2N8Pp/qKihgMB iGhoao\nroIaWq1Wp9NRXQUFdDqdVqulugpqDA4OWn/cnj14+PDh+Pg41VVQwGQy3bt3j+oqFgQbsyWR SLR0\n6VKqq6AAj8fz8PCgugpquLi4CAQCqquggEAgoOFdq8Xh6elph5/ADQBLly61ww+7BAA2m+3l5U V1\nFQvCssPPCUcIIYRoCx/+QgghhGjEXm5lEwRRVFTU398/MzMTFxe38Ge7ampqeDxeQkLCcy3v+VEq \nlT/++OPPP//MZrMB4MiRI6Ojo59//vlC9rXp7IcPHx4eHr5z5463tzePx3vvvfd8fHwWvrtNZP/q\n q6+2bdsWGBj4+++/K5VK8hmurKysgoICoVBo/fqnDkX/0bCYbn9//+Dg4KcrmP5hn+z27dtff/31\n3E /7p59+6uTkBAAVFRUODg4ymYzcbusx4T+c1S3QcCjspTE3NTUBQH5+PgDk5eXFx8fbz+9TlyxZ\n0tnZ GR4eThCESqVydnamuqLFkJOTAwAHDx7cvXu3WCymupznIiws7Pbt24GBgR0dHaOjowaDQa/X\n83i8eb sys1lMt0Kh+MdddDodUx8siI6OJgdkjk6ne/vtt6mq5zn5x7N6e3t7T0/Pli1brPel+ezb\nS2MWiUTd 3d2dnZ2hoaHkRJ4/f97T0zM6Ovr06dMrVqzo7+9XqVQ8Hm94ePiTTz4ZGRkpLCwUCoV6\nvf6111578O BBUVERAPD5/I8++ujbb7/NzMwUi8X79u3bu3cvzc+DsbGxN27cCA8P7+3tDQoKGhkZ\nGR8fP3ToEIvF cnJy+uCDDy5dusTU7CSLuX7xxRd/+OEHg8EgFotzcnJ6enrOnj1rNBqlUunLL79s\nQ9nDwsIuXry4Yc MGrVa7cuXKrq4uk8kkkUgePXpkHlCj0ZiHUigU5tOt1+uZMRoWlErl5cuXZ2dn\nv/jii6qqKouDvaWl xcHBYcOGDcwI+wQKhYIMGxYW5uDgEBwczJiY1md1izjV1dUDAwNarVYqlVrP\nvlwup+1QcPbv37+Y34 8qYrHY19e3pqamuLhYo9GEh4f39PS88MILy5Yt6+jo8PDwePjw4dTUVEZG\nRn9/PwBcuHBBJpPJ5fLG xkYfHx8ulxsSErJp06b6+vrg4GA+n69Wq8VicVtb29q1a6kO9yRqtZrP\n53d1dSUlJVVVVUVFRXV3d2 s0mpdeeiktLe3PP/80mUwzMzOMzA4AV65ciYmJuXv3rvlcX716NSIi\nIj09/e7du1qttrOzc8WKFdu2 bRsYGKipqbGh7CKRqLy8PDIysr+/PzY29ubNm+Pj476+vm1tbeYB\nLULNzs6aT/f169eZMRrw93QLhU KVSjUzM5Obm6tWq3k83tjYmMXBrtPpsrOzq6qqbDfs44yMjJSV\nlTU3N9fW1mo0GqFQSIZVqVRcLvfS pUvMiAnzndWHhobM47i5uTk6OopEonln/+jRo7QdCnu5Yh4e\nHvbz88vOzp6ens7Pz29oaJj7K5PJRH 4REBAAAAKBwGg0Dg8PSyQSAAgJCQEAkUh0+vTp2tpatVpN\nEER0dPShQ4dMJtPq1aupSPOv+fv79/X1 qVSqjRs3AsDAwAD5oxYSEjIwMODo6Mjg7ObIuR4cHFSp\nVO3t7QDg5+eXnJxcXFx88eJFmUxmW9m5XK 5AICA7a0hISHl5uVAoTExMbG9vNw9oEQr+/0edMaNh\ngazZ4r8GzR3sy5cvBwDGhLVgfitboVCQYUlM iml9Vg8JCTGPY/F6i9mn81DYy1PZDQ0N1dXVAODg\n4BAYGGgwGNhs9uTkJAB0dXWRrzFfDsbDw+PWrV sA0N3dDQCVlZVJSUlZWVnOzs4EQTg5Oc3OztbX\n18fGxlIQ5t+Li4urrKx0d3cnM7q7u/f09ABAd3c3 +VsZBmcHAIu5XrZsmVQqzcnJiYqKIv8dnZaW\ntm/fvl9++cXmskskkvPnz0dERCxZsoTNZms0Gjc3N4 uAFqHg/6ebSaNhjsPhzH1tfbBzuVwAYEzY\nJyPDkpgU0/qsbhEHAAiCeNzs03ko7OVWtr+/f1VV1YUL F3777Tc+n5+amioWi0tKSv744w9nZ+fQ\n0NCxsTEul+vr69vb2+vu7i6VSo8fP97Y2Mjn8/39/f38/C orK5uamkQikUajiYiImJiYGB8fT0pK\nojrZP1Cr1eQji0VFRampqc7Ozg0NDTt27CgrK7t27ZrJZNq8 efOdO3cYmR3+vrfp5eVlPtdRUVFl\nZWVXr16dnJxcs2bNgwcPSktLm5ubQ0NDU1JSbCu7wWBob2+Xy+ UAoNFojEbj6tWr/fz8zAP6+vqa\nh5qenjaf7ujoaMaMhvmtbDJjV1eXs7OzRCKZ92C36bCPMzIy0tvb +8orr5B/nBsK8ouEhARmxIT5\nzup8Pt88jkQiOXPmTGJi4rlz56xn3+K4oNVQ4AIjT+nXX391c3OziR s+zxxmt8/s1uxqNOwkrJ3E\nXAgKh8JebmU/W7W1tR0dHXFxcVQXQgHMbp/ZrdnVaNhJWDuJuRDUDgVe MSOEEEI0glfMCCGEEI1g\nY0YIIYRoBBszQgghRCPYmBGyATMzMywWy9PT08PDw8vLKzMzk/yvmf9dRk bGU6/+b+HEiRN79ux5\nJm+FkD3DxoyQzRgcHBwaGurp6eHz+e++++5/f8OpqSmFQnHmzJn//lYIoWcF GzNCNkYgEHz//fdK\npfLevXsEQbz//vteXl7h4eEffvghQRCZmZmnTp0CAKPR6Ovre//+ffN99+/fHx QUFBwc/OWXXwJA\nTk7OyMjIzp07514QHR3d0tICAKtWrdq9ezcAnDhxIi0tDQAKCgoCAgJCQ0PnViWy 3kI6cOCAXC43\nXwsTIbRw9rJWNkJMwufzw8LCbt26NTo62t3d3dfXBwDh4eFZWVlyufzw4cPbt2+vrq 6WSqWurq5z\ne5FrJN28eRMA1qxZExsbW1hYWFtbe/To0bnXJCcn19XVhYWF3b9/X6lUAsCVK1dkMllN TU1paWlT\nUxOPx5PL5SUlJZ6enhZbyHcoKChoaWk5e/as+aKYCKGFwytmhGwVi8WKiIgoLi5WKBT5+f lDQ0PT\n09Nr165tbW0dHx8vLi62uN1dV1eXnp4uFAqFQuGOHTvq6uqs35NszI2NjevXr2exWFqtVqlU rl+/\nvq6ubnR0VC6Xb968ua+vr7Gx0XoLAFRUVBw4cEAmk5mvz4wQ+lfw4EHI9uj1+r/++mv58uXXr1 /P\nzMzcuXPnm2++WVtbCwAcDiclJaWkpKS+vv7YsWPmexEEMffxFSwWa95bzatWrWpra7t8+XJ8fDyH \nwyktLRWJRK6urkKhcNeuXeSzXUajkSCI7777zmJLSUmJj4/PuXPn1q1bt3XrVhcXl+c+EAgxEV4x\n I2Rj9Hr9nj174uPjvby8qqurN27c+PHHH7u7u3d2dhoMBgB45513Pvvss02bNvF4PPMdX3311ZMn\nT0 5PT+t0upMnT867Oj+Xy5VKpT/99FNCQkJSUtI333wjk8kAYN26dadOnZqYmDAYDK+//nplZaX1\nFgCQ SqUSiSQjI2Pv3r2LMRYIMRE2ZoRsho+Pj7e3d0BAwMTExPHjxwFg+/btra2tUqk0Nzc3Ozub\nfAiLvN hNT0+32D0lJSUpKSkyMjIyMlImk73xxhvzfheyE/v4+CQmJvb39ycnJwNATExMenp6TExM\nUFBQVFTU li1brLfMvUNeXp5Cobhx48ZzGQWEmA7XykaIaVpbWzMzM5ubm6kuBCH0NPCKGSFGKS8v\n37p1a2FhId WFIISeEl4xI4QQQjSCV8wIIYQQjWBjRgghhGgEGzNCCCFEI9iYEUIIIRrBxowQQgjR\nyP8AcOC7SDjB 9/gAAAAASUVORK5CYII=\n" | "image/png": "iVBORw0KGgoAAAANSUhEUgAAAogAAAGwCAIAAACl6gOwAAAACXBIWXMAAAsS AAALEgHS3X78AAAgAElEQVR4nOzdeXgb1b0//jMzmkX74iVe5SW2s5mELIXEkFD2tSyFcml/bQltaFnK 7XJp4UuB0vZbWggtEEopS7/t5Za2t9AWKHsgBLIQSEOWJiSxE0d27Hi3Nlu7Zn5/THAcW14kjzQj6f16 eHiSiT06kkbz1uecM2coSZIIAAAAaAOtdgMAAADgBAQzAACAhiCYAQAANATBDAAAoCG6NO03GAyKopim nWuHTqeTJCkej6vdkGxCURRFUflweCiIpmmapmOxmNoNyTIMw+DjmRSKoliWjUQiajcky8zkSGNZluO4 0VtSD2a/37927dpwODxnzpyvfe1rY/41FArlw+fBbDbH4/FgMKh2Q7IJy7IUReGTnxSe53mex5GWLKPR iBctKTRN6/V6r9erdkOyzEyONIqixgRz6l3Zr7zyysqVKx944IH+/v62traU9wMAAAAjUg/m7u7u2tpa Qkh9fX1LS4tyTQIAAMhfqXdl19bWbtiwwWQybdmyZeXKlfLGP/zhD++88w4h5P777y8tLVWmjRrGMAzL sjzPq92QbEJRFCHEYDCo3ZBsQlEUTdM2m03thmQZmqZZllW7FVmGoigcacmayZE2fsINlfLKX7FY7G9/ +1t3d7fBYJg9e/Y555xDCHG5XL29vYSQ2trafPg8GAyGeDweDofVbkg20el0FEVFo1G1G5JNOI5jWXZ4 eFjthmQZQRBCoZDarcgmFEVZLBaMMSdrJkcax3F6vX70ltQr5ubm5oULF/7Hf/zHI488Mm/ePHljdXV1 dXU1IcTtdufDmVcUxXg8ng/PVFkI5mTRNM0wDF60ZHEchxctKTRNS5KEFy1ZMznSxhexqQdzdXX1unXr Xnzxxfr6+nzotQYAAMiA1IPZYDDceeedCjYFAAAA0rXACKTP7q6hmfz6olKTUi0BAADFIZizwwzDeMpd Ia0BADQCwaxpCubxdB4I8QwAoDoEs+ZkLIwnemjEMwCAihDMWpFyHkfiYjguSaI0HBUJIcGoGJOkWFwK xeISIcMRkWOoGrswy8RNuavRLUE8AwCoAsGssqTyOBgVD/YHPukL7O8LNPcH3cGYOGp9GBOvowjhdRRL Uzqa1usoQoiJZ0Ix6Yg7xNDUbLswu0Coc+hnO/ROG8fSky3IingGAFAFglkd08xjSSJHfeEDvcP7+4P7 eofbvZEKCze30NBUablhSYlDr2NoiqMpXjfFmueiJHX5o4cHg4cGQxuPeP7fx92eUNxp5eoc+tkF+jqH /pRiA01TE7UT8QwAkDEI5syZZhgHIuL+/uFPeoP7+4YP9AUlQuYV6ucVG7+xrHRekcHIMSk8NE1R5Rau 3MKtqrbKW3zh+KGBwKHBUHN/4KVPBkRJ+vyCwovqHQY2QcYjngEAMgbBnAnTieRWd+iDdt/Wdt9hd6jS wi0oNn62xnbTaWWVFp5KUMrOlIVnlpSZl5SZCSGSRLYf87+wr//ZXb2XNNivnFdQbEwwID3yLJDQAADp g2BOoynzOC5Ke3qGt7b7trb7gjFxeYX5PxYWLys1GbjUb8eZAooip5WbTys3tw6GXtjX97W/NzdVWb6w oKi+QJ/w53d3DSGbAQDSJPW7S03O7XbH4/F07FlTzGZzLBYLBoOjN06Zx4GIuL3Tv+Wod3vHkJlnmirN TU5r4wSjvJk3EIi+uH/g1YODNXbhmgWFp1ea6Qlq9tTimWVZiqIikcjMmplfeJ7ned7n86ndkCxjNBpx S66k0DRtt9sHBgbUbkiWmcmRZjAYxtwGF8E8I6ODeco89oXjG494trb79nQP1RUYVlSam5yWKpuQ2kMn G4rJXo4ViolvNA/+/ZMBhqauXlB4QZ2NYxLU8SlkM4I5BQjm1CCYk4VgTg2CWUPkYN7W2jfJz4Rj4pZ2 34ZWz8fH/ItKTCurrcsrLQ79dAcR0tdpPJ2oFiVpS7vvhX39Rz3hy+cWXDGvwJ6o5Uk1EsGcAgRzahDM yUIwpwbBrBW7u4YMBkM8Hg+Hw+P/NS5KH3cNbTjs2dzuq7YJ59TaPltjTZhqY6gyfDtlSO/vC7ywr//D o76za21Xzy+sto8t9KffbARzChDMqUEwJwvBnBoEs/pGYixhMB/oC7zT6tl4xGPkmHNq7efW2sotU6y6 pZ25VJMndM9Q5G+f9L/Z4vncXMf1i4vHL1EynSeCYE4Bgjk1COZkIZhTg2BWzfjQGh3Mnb7IO62edw67 A9H4Z2ts59ba5hYZEu3mOO2E8XhTxvMD73cMx2J3rnTWJF86I5hTgGBODYI5WQjm1CCYM22SlDIYDN5g 5PVPet467G7zhM90Ws6ZbVtaappkfrWW83i8iZ67KEkv7O3/457erywqvnpB4Zhp25M/RwRzChDMqUEw JwvBnBplgxnXMU9o8qpRlKRdXcNvu45tanUvKNZ/fn7hGU7L5EtjZlcky+Q2j38paIq69pSiZRXmX7zX /sFR/x0rK0bfJAMrhQEApAwVcwJTduS+ecjzZssgRchl84svqi+wcRO+hrkUTglflqgo/eHjnteaB28+ rfSCOvuYf0349FExpwAVc2pQMScLFXNqsqMr2+fziaKYjj2nz65j/kn+NRqXNrd5Xm8e3NM9dGaV9ZI5 BYtLTXq9XhTF8Rlzapk5nS1VU8JXaU/30M/fa28o1H/vjEqrcFI3zPiXQqfTURQVjUbT2Mqcw3Ecy7LI mGQJghAKhdRuRTahadpisXg8HrUbkmVmcqTxPK/Xn7TMYrqCeWhoKE17VtbkYSxr6Q+8eqD/7UODpRb+ koaC8+sdJv549nAcJ4piLBYb+eEcjuTRxr9uw5H4uq1HP+rw3bGqarnTOuZfR78sDMNQFDX6RYMpsSyr 0+nGrDEHU+J5PuHVjDARiqJMJpPfP/WJEUabyZHGsqwgnDSLNk+7sqeztoYvHN9w2P3mIXfPcPTcWtvF DY7acTOQR8/KzqVe62ka/zJubvM9vLVjVbX1m58pFU4ecR95fdCVnQJ0ZacGXdnJQld2arKjK1uDwTzN NSlFUfpX19CbLe5tR30LZxkvqnc0VVnYCWZZGwyGhSXGPK9jxryw7mDsl1s6jnrDd6ysnF980tEmZzOC OQUI5tQgmJOFYE4Ngjk5018jutMXebNl8K3Dbo6hL6q3n19nLzKwk/z8olJTwptY5KHxL/JrzYNP/av7 qnkFX15UzJz8tWaZ045gThaCOTUI5mQhmFODy6WmltQNGwJR8X2X540Wd+tgaGW15YdnVTUWGya5BXIe dllPafxVVZc0OE4tNf1sY/vOrqG7VlUWj7qYatcx/+JyiwqtBADIBrkQzMneN0kmSeTfvcNvtLg3ubx1 DuGSBsfKKquenfBCZOTxlBaVmka/F2Vm7tFLa//fxz03/fPQ95oqzqw6Eca7jvnnF/JqtBEAQOuyL5hT i+HReocj6w953jzkjsbF8+vsT15eXzbpWtaI5Okbk806mv7GstIlZeYH3m//uMt202ml3Kfd2liEBAAg oWwaY55hJAei4uY271uH3Pv7Ak1Oy4X1jiWlRnqSPutpxAbGmCcy5s0aDMYe2HR0MBC9+7PO2YWm0dcx I5unA2PMqcEYc7IwxpwajDEnRxSlj7uH1x8a3NLmaygwnFdn+/E5VUaOmfy3kBYzNGbU2aHX/fz86r/+ u+8/X229ZXn5ZXMLR35yd9cQXm0AgBG5HMyt7tD6Q+53Wj16HX1+nf2Zq0pKTFPcfpEgkhU1umebpqjr FhYvKjXd/97Rf3X6vrO8bOTrEbq1AQBG5GBX9mAwtqHV89ahwf7h2GdrbefV2sZcTZtQaqmAruzpGPPG hUXql5vb9/UM//AsZ8ILnWE8dGWnBl3ZyUJXdmrQlZ3YcCS+uc234Yjn393Dn6kwf/XUktMrTSw92e2e ZAiDdBvTrW3kmB+dW/vyvp7/s971xVMKrz2laGSkH6UzAEDWB3NUlLYd9W047Pmo0z+n0HDubNsPz3Ja +CmGkGUIgEwaM2H74gbHgmLjTze27ewevmNlpUN/4lDEqDMA5LNsDWZRknZ3D79z2LO53Vds1J1Xa7/5 9NJi49RDyAR5rJ4x2ey08Y9fXv/bj7q++VLz7WdWnF5x4kJnZDMA5K3sC+bmgeCGw+53j3hZmjpntu2R i2urx91bYiI416tuUamJZdmReOZo6j+Xly0rM63d1LHy5FtfoFsbAPJT1kz+CselH751ZEOrxxeOnV1r O6fGNq9osoUzx0jT+R2Tv1Ig38Rie9vg6I2DwdgvN3d0+sN3rqycW4QZYWNh8ldqMPkrWZj8lZo8nfzF 0ZQvHLv59NKlpSZmgns9JYTTujaNv9D5/55X/crBwTvecn2hsfCLpxQxWCMMAPJS1gQzRZFbTy9L6ldw Kte+0aPOFEU+N9exuMz08/faP+r037myssx8YtIA4hkA8sTUVxNlo0WlJpzBs8WYd6rCwj16ae3iEuMt /zz0evPgmB+e+UrpAAAalzUV8zQhj7PRmG5tHU3fsKTk9ArLL94/uq3D/72mCqtw4vo3lM4AkNtyp2JG lZztxrx984sNv72i3sIzN7548KMO/5gf3t01hOoZAHJS6hVzIBB44oknAoFASUnJmjVrqOnPkFYa8jhn jCmdDSz9X2dUbGn3PbDp6BlVlhuXlZpPvvsILncGgNyTesW8adOmmpqae+65Z2hoqKWlRcE2TR+q5Jw0 5j09w2l5+sqGYFT82t8Pbmj1jPlhlM4AkGNSr5iLior279/vdrv7+/ttNpu8sbu72+12y/+q0yk8gM0w J6qlU8vMyu48NRRF0TSt+DPNbQzDUBQ1+Yu2tNK269iJ7usiE3PvOTXbO/yPbD26/rDnO2dUlJn50T+/ tzdINHNUpMN0XjQYDx/PZNE0jSMtBTM50sb3N6e+wIjP57v77ruNRiPHcXfffTfLsoSQ3/72t6+//joh ZN26dRUVFanteSIfd3gJIUsqrMrudiZompYkKU2LtOQq+Sic5osmv+kjQrH4//yr88+7jn3x1LLrl1Vw urFdPpo6PBREURRFUaIoqt2QLEPTNF60ZDEMo/i9AXPeTI40URTlAB2RejA/88wzp5566rJly/7+97+b zebzzz9/9L+m47aPGoSVv1Igr/wViUSm+fPje6qPuEMPf9AZjMS/01SxINE9PXNvgAMrf6UGK38lCyt/ pUbZlb9SH2OORqNyqIuiGIvFUt4PwOTGzySosQuPXFz7ubkFd7/tenhrpz8y9isgRp0BIHulXjH39vY+ +uijDMMIgvBf//VfPH/SmB8qZphIshXziPFxOxiI/uajrt3dQzefVnZOrW38r+RM6YyKOTWomJOFijk1 ylbMWXMTC21CMKcg5WCWjY/nXV1Dj3zQWaBnv9NUXmnlx/9KDsQzgjk1COZkIZhTo5WubABVjE/ZU0tN T15eP6/YcOsrh/60pzc2bgoGLqkCgCyCYIbsM37UmdfRa5aWPHrJ7G0d/ptfPrSvNzD+txDPAJAVEMyQ rcaXzjV24dGLZ3+hseiet10PvH/UF0owJxHxDAAah2CGLDa+dKYockGd/Zkr66OitObF5vWH3WKiWRSI ZwDQLAQzZL3xpbPDwN79WeftKyv/999933ipZVObL+EcR8QzAGgQ1l2DXDDm7hey08rNy8pMm9t8v9vR 9ezO7q+cOmtllXX8zVZwH0kA0BQEM+SORaWmMdlMU9SqauuZVZbNbb5ndnQ/v7f/SwuLVjgt438X8QwA GoFghpySsHSW43mF0/x6s/vRbZ3P7+u/YUnJKbMSrOWJeAYA1SGYIQeNL50JISxNXz634KIGxysHBn7y rmu2Q3/94lnziiaMZ4KEBgA1IJghNyUsnQkhHE19fn7hJQ2Of3zS/8O3XQuKDasXl8x2CAl3goQGgMxD MEMumyieBR39xYXFl88t+Nu+/u+93rqk1Lh6yawqW+J4JujiBsh7mfyajmCG3DdRPBs55quLZ105v/D5 vX23vXq4qdLy1VNnlVm4ifaDAhog36hyRSWCGfLFRPFs4ZmvLy25ekHhn/f03vRyy1k11i8vKp5lmjCe CRIaINepu8IBghnyy0TxbBN0N59W9oXGoj/t6fvaP5pPmWW8oM5+ZpWFYyZbhGf0fhDSANlOIysO4baP M4LbPqZghrd9VMokn0BfOL6x1bP+sKfNGzqr2npBnaOx2DB+ZZKJpCOhcdvH1OC2j8nKz9s+JpXHCT/g yt72ERUz5KmJSmdCiIVnLp9XcPm8gnZv+O3Dnvvfa2Np+vw6+/l1tpJJu7hlKKMBsoJG6uPxUDHPCCrm FGikYh5t8s+nKEk7u4bWH/JsbvM2FBgurLevrLYa2NTXmU8hrTNcMStywtLClxJUzMnKk4p5Jkc4KmaA TJikeiaE0BS1tMy8tMwciJa/7/K82eJ+bFvnyirr+XW2U0tMND3tPu5PTf+kkEK2aacIGN8SLUQ15DPt fDomN7ZifvTRR8f/kN1u/+pXv5rUflExw0Q0WDGPNp2Pbpc/sv6w5+3Dbk8wNqdQP7/YsKDYOLfIYOGZ NLWK4ziWZXOs+MtATqNiTlZOVszK5rEKFXMoFCKE7Nmz55133rnkkkt0Ot2rr776jW98I9lHEoQJ12rI JTqdjqZpmsbdM5NA0zRFUSzLqt2QxJrqjISQnZ2TdRrX6vXfLLZ+c0XVMV94b/fQ3p6h/97Ve3gwWGHl G2eZG2cZG0vMVXaBnv6EsanQNM0wjF6vV2qHWtDsGfvdfXF5gvuLzATLskajUdl95jaKoiiKyo0XbeRT rOwHJ+GLM5MjbXyCJB5jPv3001955ZWioiJCyODg4KWXXvrBBx8k9UiomGEiGq+Yx5j+d+1QTDzYH9zX O/xJb+CT3oBIyLxCfX2BvtDIFhnYQiNbYGAd+hQHjzJWMUdFKRQT46IUjIpxiQSicSJJhKIIITqK0rM0 IUTHUIKOJoTwOppLvid/+mZeUqNiTlYOVMzp7q9WbYy5u7vbZrPJfzabzb29vak9HkC2G/kQTvlpF3T0 ohLjopLj35qPesP7e4cPu0O7u4f7A9G+4ag7GCOEOPS6QiNbaGALDLpiI+fQ64pNXIFeZ/q0G5wixMRN t0s8EBHjRIrExEhcEiUyHI0TQobC8ZgohWJiIBqPxKVAJB6KSVFRGorEIzExHJcC0XgkJoVi8nYxHBOj IgnHxEhclHdLU5SRYyhCjNyJ7/JRUQrHJEJIOBaPxE/6Qm9gGYamGIrY9boCg85h4AoNrF3QOfS6AiNr F3QFBp2c5UnBKDVMX7aMH09H4mC+6KKLLrjggq985Ss0Tf/xj3+88MILM9wsAK2ZfILYeJVWvtLKj94i ScQdivUHogPD0b7h6EAw2uoObe+M9g9H+wLRQCRxDxPHULyOIYRQhEif/l+UyHAkNvIzLEMJOoYQYuJo QoiJY1iGFljaqGNYhuhZRq+jOB1TamIFlmEZysQyLEMJOorXMSxDsTQl6GiGJnqWYShq+hPOg1ExJkmE kOFIXJJIVJQ8wVh/IOoOxfqHowf7A4PB6EAg5g7GfOGYnmUKDWyxiS0386VmttzCl1u4MgvPJlNzj3n9 kdN5K5dieLzEXdnRaPR3v/vde++9R9P0WWeddcMNNyQ7IoiubJhIdnVlTyR954WoKIZiJz6VwWg8LhKW ZVmWDQQCoZgol55GjqEootdRumyY4hAVJXcg2h+I9QxFjvkjnf5Ipy98zBf2huKFRrbczJVZ+HIzV2rh yi18uZnjky+vZWOiGl3ZydJ4V7YW8li1rmyGYWbPnm232+W/vvzyy1dffXVqDwmQk5ItoKePpWl21Com Zo4hI2PMTGzCX9M2lqaKTVyxiZtffNIJKBAVj/nDx3yRDl+43Rve1uE/5g/3D0cLjazTJlRb+Wq7UG0T nDZ+mt37Y94ReSofZDUthHGGJQ7mL33pS8FgsLa2Vv4rTdMIZoDxxn93zsOTyEwYWLrOoa9znDRpNhwT O30Rlyfkcoc+7PD/5d993UORAr2uyiZU2fgqm1BtE6ptgoGbuqre2ekb36GFDnDty/PPUeJgjkQiL730 UoabApADxpz08/z8khpeR9c6hFrHiUsuI6LU7gm53KE2T3jbUf9f9vR1D0UKjazTytXa9U4bX20TnDZh mqPjE70pCGwV4ZMyWuJgrqur83g8IxOzASA10znXz/yUpPFEmfkT5GhqTGEdjolt3rDLHWr3hje5fH/0 9PYOR4uMbJWNr7Hrq6xctV2osglJXb46STs1/gpnL+RxQomDubOzs6ysbMWKFQ6HQ97y/PPPZ7BVAHlk Oif9T9fKTuNFw+kz/VSb/mma19ENBfqGghPJG4yKR70hlyfs8oTePeJt39XbNxwtsfBVVq7KJlTbeLkn fPL7eKbQMGT29CGGpynxrOwtW7aM2XLGGWcktV/MyoaJ5Mas7AzL89s+pnZCD0TE7pB0sNvb5gm5POE2 T2ggECsxc/KEMjmqnbbkrtdKSjZm9gxnZedD9Ko2K/uMM874/e9/v3Xr1ieeeGL79u0rVqxI7fEAAGYu 4alwygwwcPQCq77WcmI693Ak3uYJuzwhlyf05iG3yx1yh2JlZq7Gpq+0cTU2ocouVFo5VqEr0CZvYTbG dkL5EMYZljiYf/SjH23fvt3lclEUdc8996xYseKnP/1phlsGADCJFNLayDHziw2jL9nyR+JtnnCbJ+Ry h15vGXS5Q95wvNzMV9mOX6lVZeMrrFw6LhafTp6pHt4IXVUk7sqeM2fOjh07rrrqqvXr10ej0fr6epfL ldR+0ZUNE0FXdgryvCs7Zc2eeLIfT18o5vKG29xhlyfU5gkdcYeGo2K5mauyCdV2odouVNv4cjPHpHOR cBXRNG02m71er9oN0S7VurIjkUg0GpX/HAqF8uRWUQCQYxaXW4aHT3RlT6f+swi6hYJu4awTK5P4wvEj 7lCbO3TEE9p1bMjlDQWjYoWFq7IJNXbBaeNr7PpSE5urUQ2ZlziYb7311gsuuMDtdq9du/a55567+eab M9wsAADFpXaVuYVnRt+ehBDiDsaOuEPt3rDLHdre6W/zhEOxuNPGV1kF+TKtGptQYmJpRDWkJHFXNiFk w4YNGzduNBgM55133rJly5LdL7qyYSLoyk4BurJTk1QH40zGUwcCUXnut8sTcrnD7d5wJBavsgkjq5XV 2IVZJlbBW3SnCbqyp6ROV/bg4OBTTz115513nnPOOak9DABA1hl9wk02pAsMbIGBXVJmHtnSF4i2uUMu T7jdE9ra7m/zhuKiVGXlq+2CPLOsyibMMnKaT2pQQYJgtlqtf/zjH6+99tqRtbIBAPLKTEJaVmRgiwzs svITUd0zFGn3ho+4Q22e0PsuX7s3TAhxWvlq+/GS2mnlZ5m4iXcJ+SJBMDMMs2DBgrlz5y5btqy8vFze iJW/ACA/zTykZbNM3CwT95lPo1qSSO/w8Xt1uNyhja2eNm+YoakqqyBHdbWNr7ILRYbkbrkLOQArf80I xphTgDHmFGCMOTXpvh+zspf5ipLUMxR1uUPyEijtnnCbJ8wydJWNr7bz8kXV1TahIJ1RjTHmKal2udSf /vSnxx9/fOSvq1evHh/ML7zwwocffkgIGRoaOu2002644YbU2gQAkKWUKqZlNEWVmrlSM7fCaZG3iKLU PRQ94gm1eUIH+gJvHhps94QFHSMntDyzrMYu2PWJz+SQpcZWzPPmzSOEtLe3O51OeUssFrPZbNu3b59o F48//vjVV19dUlIyeiMqZpgIKuYUoGJOTbor5oTSulpWXJS6hqJH3MGj3nDrYKjNE+rwRfQsXW0Vqj6t qmvseqvATL2vRFAxT0mFinnz5s2EkFtuueU3v/nNyMZJ7v/Y3t6u1+vHpDIAQN5Stoweg6GpCgtXYTkx RywuSp3+iMsTbnOHdncP//PgQIcvYtDRtQ7BaROqbbx8xw6LgKo6a0x4HfM0/epXv7rxxhvN5uPTGd54 442PP/6YEHLDDTfY7XYFGqhtLMuKopgPfQMKommaECKKotoNySYMwzAMg26GZOl0ulgspnYrjtvZmaEO j1hcbPeEjriDRwaDRwYDR9zBo56QVdDVOgw1Dn2NQ1/jMNQ69GY+cVRzHIcjbRKLyy3jN87kSKMoiuf5 k/aW2o5kw8PDwWBwJJUJITabTZ7ITdN0PsSVTqeTJCkfnqmyKIrCi5YUiqLy5DOlLIZhtPOiLRy1dlha Q5oipMrGV9n4z9Yc7+yMitJRT8jlDh0eDGxr8/x5Z1enP+zQszV2fY1DL68BXltgMLIMRVGEEO28aBqU 8MWZyZHGMGPHHWZUMb///vter/dzn/vc+H/CGDNMBGPMKcAYc2pUGWNOlip3cIqKUrt8Wy1PWL5XR7c/ UmhgnTZ+Tom1RCDVdqHKKhg45W+rle1Um5U9Tdu3b7/22mtnsgcAgDyX1jHpibA0NdshzHacuEFRJC62 ecLt3nBXQNp61PunPb09Q9EiI+u08jV2ocomVNt5p1XQs4jqtJvpGPNEUDHDRFAxpwAVc2qyomJOSK0b IY+elR2OiW3esMsdavOEj7iDbZ5w33C0yMhW24Rqu1Bl5eSFRXldfkW11itmAABIB1XK6DF4Hd1QoG8o 0I9sCUbFdm/I5Q63eULvHvG27+rtG47OMrE1dv2nC4DzTivPMfkV1YpDMAMAaJoWQlqmZ+k5hYY5hSfK u0BElNcpa/OE1h9yt3lCA8FYiYmrsQuf3rFDcNp4FnfATAaCGQAga4yEtLoJPcLA0fOLDfOLT0T1UCTe fvz2l6E3Drld7pA3FCs1czU2vdPGybV1hZVjaVTVE0IwAwBkH60l9AgTx4yJal843u4Ny/fqePXggMsT 8oXj5Wa+2sbLV2o5rXyFldMhqj+FYAYAyGKaTegRFp5pLDY0jo7qUMwlV9We8MsHBvQm+94AACAASURB VI64Q8NRscLCVdmEaptQZReqrXy5hWPytQMcwQwAkAu0MxQ9JYugW1iiG73iijcUlyd+uzyhnV1DLk8o GBUrLVyVXaixC5VWvtauLzWxdH5ENYIZACDXaL+MHsMqMKeWmk4d9d1iMBiTr9RyeUIfdvjbPeFQLO60 yXeqPv5fiZmlqRyMagQzAEDOyqIyegyHXufQm5aUnWj/QCDq8hyP6m0d/jZ3OBoXq2x81ad3qq62C7NM uRDVCGYAgLyQvSEtKzCwBQZ2admJuzP0DkfavZEjg8F2b3hLu6/dE45LUpWVr3boq6zHZ4AXG7msS2oE MwBA3sm6vu6Eio1csZFbNqqq7hmKtHnDrsGQyxN63+Vr94YJIU4rX23nq2yCfHV1sYmbeJeagGAGAMhf uZHQI2aZuFkm7rTy41W1JJGe4UibJyRfrLWx1dPmDTM0VWUV5KiutvFVdqHIwKrb7DEQzAAAcDyhaZpu zYWAPo6iSImJKzFxp1ccv4myKEndQ9E2d8jlCR0aCL592N3uCXE6Rr5RZrVNqLbx1TbBoWpUI5gBAOCE pZW2AUM8Nwro8WiKKjNzZWZuhfPTqBalrqHoEXeo3Rs60Bd4o2XwqDei19HOT3O6yi5U2wS7PnNxiWAG AICxcqyLexI0TZVbuHILR8jxqI6L0jF/RL5T9d7ewKvNgx2+iJ6lq23CWdXWhHeXUhaCGQAAJiTnUM7H 82gMTVVa+Uorv7LqRFR3+iIub9igy8QMbwQzAABMIQ/jeTSGppw23mnjM/NwCGYAAJiW/OnfVhfu5gEA AMlZVGrKwFBr3kIwAwBAKhDPaYJgBgCA1CGeFUdJkpSO/QaDwXTsVms4jhNFMRaLqd2QbELTNEVR8Xhc 7YZkE4ZhGIaJRCJqNyTLsCwbjUbVbkU2oShKEISZnMB3dvoUbI8GLS63jN84kyONpmmeP2laWbomf4VC oXw489I0HYvF8uRbiFJYlqUoChmTFJ7neZ4fHh5WuyFZxmg04kVLihwSM3nRGmwMyenZYcPDzPiNMznS DAbDmC2YlQ0AAArD/O2ZwBgzAACkC0agU4BgBgCA9EI8JwXBDAAAmYBsniYEMwAAZAhK5+lAMAMAQEYh nieHYAYAABUgnieCYAYAANUgnsfDdcwAAKAyXPc8GipmAADQChTQBMEMAABak+fZjGAGAADNyefSGcEM AAAalZ/xjGAGAABNy7d4RjADAEAWyJ94RjADAEDWyId4xnXMAACQZXL7umdUzAAAkK1ysoBGMAMAQHbL sXhOvStbkqSnn366t7fXYrHcdtttFEUp2CwAAICkyNmcA53bqVfMO3bscDgcd9999+LFi3t6ehRsEwAA QGpyoHROPZj37dtHCFm3bl0wGCwpKVGuSQAAAKnL9p7t1Luyh4aGenp6Vq9e/eSTTxYVFS1evJgQ8otf /OKFF14ghPz1r3+tra1VrJkaxvO80WhUuxWQFwoLC9VuQvbR6/VqNyH75MaRdm5hISFkx1GPsrstLLQl 3J7ykRaNRsdsoSRJSm1ff/jDHxYuXLhkyZKNGzf29/dfc801hJBQKBSJRAghsVgs5T1nEZPJFIvFQqGQ 2g3JJizLUhQlHycwTTzPcxzn9/vVbkiWMRqNw8PDarcim9A0bbPZBgcH1W6IkpQddU5Yi8/kSNPr9QaD YfSW1Cvmurq6Q4cOLVmy5MiRI3V1dfJGQRAEQSCEuN1uURRT3nl2yYevIAqSXy68aEnBi5YaSZLwoiUl J4+0hSVGBbM54Yuj7JGW+hjz8uXLXS7XXXfd1dfX19TUpFSDAAAAlJVdo86pV8w6ne4HP/iBgk0BAABI n0Wlpqy4mAoLjAAAQL7IitIZwQwAAPlF4/GMYAYAgHyk2WxGMAMAQJ7SZumMYAYAgLymtWxGMAMAQL7T VDYjmAEAADTUrY1gBgAAOE4L2YxgBgAAOEH10hnBDAAAMJaK2YxgBgAASECt0hnBDAAAMKHMxzOCGQAA YAqZzGYEMwAAwNQyls0IZgAAgGnJTDYjmAEAADQEwQwAAKAhCGYAAAANQTADAABoiC5N++U4TpKkNO1c OxiGIYQIgqB2Q7IJwzAURdE0vhQmQafT0TSNIy1ZDMPgRUsKRVEUReFFS9ZMjrTxJ8N0BXMsFhNFMU07 1w6O4+LxeDQaVbsh2USSJIqi8KIlhaIohmHwoiVLp9PhRUuKHBJ40ZI1kyNNLvBGQ9UyIwMDA0NDQ2q3 IstIkpQPvSnKCgQC/f39arci++BIS1Y8Hj969Kjarcg+yh5pFA7cmbj33nvnzZv3xS9+Ue2GQI579dVX 33777YcffljthkCO6+/vv/zyy7du3ap2Q/IaKmYAAAANSdcYc55YtmxZaWmp2q2A3Od0OlesWKF2KyD3 CYJwxRVXqN2KfIeubAAAAA1BVzYAAICGIJiT5vf7f/jDH6rdCsh99957769+9Su1WwH5IuGZ7Y033sBE sMzDGDOAFvn9fvkSqVgsptMl/pwGg0G9Xp/hhgFAuiGYUxQKhR5++GFJkqxW66233rp+/frW1laWZXt6 em6//XaWZdVuIGS3Dz/8cPny5d3d3Xv27FmyZMmzzz4bCoUoivJ4PLfddtumTZs+/vhjQRC+/e1vq91S yCn//Oc/S0tLly1b9uc///nUU09Vuzl5Cl3ZKert7b3qqqvuuuuuQCDQ29tLCOF5/mtf+1p1dfUnn3yi dusg623ZsmX58uWf+cxnRjoSi4qKbrzxxrlz57799tuEEJvNhlQGyEkI5iTs2bOHfLrCi8FgeO211x59 9FGXyyUvPlpbW0sI0ev18Xhc3XZCthseHt67d+9zzz335ptvfvjhh6MPsNra2u7ubkJIQ0ODyq2EXDH6 zDYiH9ZU1iwEcxKef/55t9vtdrtLSkpeeuml888//9vf/nZBQYF8QFMUpXYDIUd8+OGHV1555R133HHv vfc2NjbKfTAHDhyQ/y9fOj/RwDNAskaf2WialpcZlo83UAU+20m46qqrHnvsMZqmv/SlLwUCgRdffHH9 +vUlJSXr168fWWaEZVmDwaBuOyHbbd269ctf/rL85zPOOGPr1q2CIBw8ePDHP/4xwzC33377pk2b1G0h 5JLRZzaLxfLwww9v3bq1qKgIc2XUggVGALLAs88+29TUVFdXp3ZDACDt0JUNAACgIaiYAQAANAQVMwAA gIYgmAEAADQEwQwAAKAhCGaAvPDAAw88+uijarcCAKaGYAYAANAQBDNAzopGozfffHN1dfXpp58uL7vo 8/lWr149b968VatWvfvuu2o3EAASwMpfADnrd7/73YEDB1paWtxu98KFC0877bTnnntOFMX9+/e//fbb L7300tlnn612GwFgLFTMADnrvffe+8pXvsKybHFx8SWXXEIIaWpq2rBhwz333GMymR555BG1GwgACSCY AXIWTdM0ffwzLt/0YtGiRdu2bSsrK7vvvvs+//nPq9o6AEgMK38B5Kynnnrqr3/96xtvvOH3+xsbG3/w gx/4fL5YLPbjH/+4q6uroaHB5/PhrmgAWoNgBshZ0Wj0P//zP996662ioqKLL764pqZm5cqV1113XV9f X2Vl5Y033jhyDysA0A4EMwAAgIZgjBkAAEBDEMwAAAAagmAGAADQEAQzAACAhiCYAQAANATBDAAAoCEI ZgAAAA1BMAMAAGgIghkAAEBDFLjtYywWW7du3dDQkNPpXL16tbxRkqSnn366t7fXYrHcdtttWI8XAABg OhSomLdt2+Z0Ou+9996+vr6Ojg55444dOxwOx91337148eKenp6ZPwoAAEA+UCCYW1paGhsbCSGNjY0t LS3yxn379hFC1q1bFwwGS0pKZv4oAAAA+UCBruxAIGAwGAgher3e7/fLG4eGhnp6elavXv3kk08WFRUt XryYEPLGG298/PHHhJCvf/3rDodj5g+tLIZh4vG42q1QAUVRFEWJoqh2Q1SQz8+dpmlJkvLzNjY0Tefn m05wotPe+05RlHy79BEKBLPBYAgGg4SQYDBoMpnkjUajccWKFcXFxStXrjx8+LAczDabrby8XP6BSCQy 84dWEEVRLMvKTyTfMAzDsqzW3pHM4DhOkqT8fO6CIMTj8VgspnZDVGAwGCKRiAbP0emGE50GP+wMwygf zPX19fv3758zZ86BAweuueYaeWNdXd2hQ4eWLFly5MiRuro6eePy5cuXL19OCHG73Vo7Mmia1uv1WmtV ZnAcxzBMfj53+Ut0fj53+SQVDofVbogK9Hp9KBTKw8IRJzoNPne5y3k0BcaYly9f7nK51q5d63A4Kisr m5ubf/3rX8sb77rrrr6+vqamppk/CgAAQD6gVBlhcrvdWvuuStO03W4fGBhQuyEq4DhOr9d7vV61G6IC g8FAUdTw8LDaDVGBxWIJh8P5WTE7HA6v16u1s1AG4ESnwROdwWAYUzRjgREAAAANQTADAABoCIIZAABA QxDMAAAAGqLA5VKQ7XYd8/N8ZGhoaFGpSe22AADkO1TMeW1319DurqHRf1WxMQAAQBDM+SxhDI+JagAA yDAEc56aPH2RzQAAasEYc96ZZujKP4ZRZwCADEPFnF+SLYVROgMAZBiCOY+klrIYdQYAyCQEc16Yebgi mwEAMgPBnPuUylSUzgAAGYBgzmXpiFJkMwBAWiGYc1b6EhSlMwBA+iCYc1MGghPZDACQDriOOddkMi9x rTMAgOJQMecUVapYlM4AAApSp2LW6XQ0ra3vBHJ7WJZVuyEp2nXMTwjR6VJ5QxmGoWk6td+V7esLEUJO LTOnvAe1MAxDUVT2vu8zQVGUTqcTRVHthqiDZVmtnYUygKKovD3g5ROdBp87RVFjtuTdcZmT5FRWnUaa AQCQ1dSpmGOxWDweV+WhJyJ/d45Go2o3JGkz70mmKEoUxVgsNvPG/KvdTbJq1JllWYqisvF9nzlJkmKx WH4+d0JINBrV2lkoA2ialiQpP990+USnwec+vohHxZzFlLpsqcMbfv1gnyhJM9+VDKPOAAApw6zsbKVU +L3RMvjb7d1WQfc3gfn+mZXlFk6R3WLCNgBAahDMWUmRVB6OxB/9oHNfb+DnF85eXGn/wzbXLf889MVT Cq9tLKLpsZMRUoN4BgBIFrqys4xS3de7uobWvNgcE8mTV9QvLDHpaPq6hcWPXFL7vsv7nddb2z3hmT/E CPRsAwBMH4I5myiScHFRenZnz4/fbf/60pJ7z3aaOGbkn2rswmOX1TVVmm979fBf9vSKopKjzohnAIDp QFd2dlAq1bqHIve/d5QQ8vjn6srMCYaTGZq6bmHx6ZWWhzZ3vOvy/OBM52yHoMhDE0J2dw2hWxsAYHKo mLOAUqn81iH3TS8fWlZmeuTi2oSpPKLGLqy7dPbZ1bbvvHb4mR3dUeXWoEDpDAAwOVTMWqfsPK//e151 Y7FhOr8il84rnJa1mzs+Our7/srK+gL9zFsiQ+kMADARVMzalY55XtNM5RFVNmHdpbOvmF94+xtHUDoD AGQAglmj0j3Pa/poirq0wfHE5XWf9AZueflQc39g5g0bgWwGABgDXdmao+Q8r/ePEmnCeV5JKTNzv7yo 9rWWwR+85bpsjuP6xbNYXOsMAJAGqJi1ReF5XqVTz/OaPooilzY4nvhc3YG+wM0vtxxE6QwAkAaomDVE kXAaisQf/aDzk97Az86rXpDkiPJ0lJq5tRfWvtYyeAdKZwCANEDFrAkKzvO68cXmuEievKI+Haksk0vn 315e19wfuOmllv19KJ0BABSDill9Ss3zem537z/2D3xredm5tbaZ73BKJSbugQtqX2sZvPMt12drrDef VirolPmeh9IZAPIZKmaVKZLKR73hb71y6F/Hhn7zubrMpLJMLp2fuqKuayjyjRdb9nQPK7hzlM4AkJ9Q MatGwXlej3/YdfX8gi8vKlbqrlBJmWXiHji/Zv1h933vtq2sQukMADAjqJjVodQ8r5+91/7fO3vuP7/6 q4tnqZLKMooiF9TZn7mi3h2M3fhi8y5Fi12UzgCQVxSomGOx2Lp164aGhpxO5+rVq+WNbrf7wQcf5Hm+ vLx8zZo1FKVaZmiNUjGzs2vogU1HF5eYnr6ywcBq4guWw8D+5Nyq913en7zbvrLaetNnSvUKNQylMwDk DwXOm9u2bXM6nffee29fX19HR4e8cf369eeee+599903ODjY2to680fJDQqu5/WTd9tvXFZ6x6pKjaTy iFXV1meuavCEYje+2PzxMZTOAADJUaBibmlpWbFiBSGksbGxpaWloqKCELJq1Sqr1RoIBHw+n812fDrS rl275JA+44wzjEbjzB9aQRRFURQlCIrd4nC8nZ0+jpvpWh/tntBPNhxhaeqZq+eXKrRyiE6no2l65m0b UcJxP7+ofmOr+2fvtZ1VY7+1qVKv0Kjz/oEIIWRxuUWRvRFCdDpdut93zaJpmmXZ/OzNoiiK53lRubXf s0UGTnSaJZ/oNPjcaXrs6VGBYA4EAgaDgRCi1+v9fr+8saSkJBwO33PPPTqdbiSDXS7XRx99RAg5/fTT WZad+UMrSD49palVH3d4CSE63Uxf7TcO9v9qk+s/FpXcsKxCqQHlJRVWmqYZholGo3I7lXJeQ9HSSvva 945c/9d9d51Tu6zCqtSe/90TWKLQ3hiGIWl73zWOpmn5e4naDVGHTqeTJEntVmRaWk90GkfTNEVRWfHc qZkfmr///e+bmprmzJnz+uuvC4Jw9tlnE0IkSZKPgMcff3zu3Lnnnnvu6F9xu93xeHyGj6ssmqbtdvvA wIDie1ZqntcjWzv39wXuOsup4Moh8qgtx3F6vd7rPZ7KivcYv+/yPvpB52nl5luWl5lTupHGRGY+6mww GCiKGh5W8kKvbGGxWMLhcDgcVrshKnA4HF6vV2tnoQxI34lO+8ac6LTDYDDIxe0IBToY6+vr9+/fTwg5 cOBAXV2dvPGxxx47cOAAIcRut4+v0/OHIiG3s2tozYvNLE09c2WD4qk8/e0pW1Vt/d1VDeGY+PV/NG9t 9ym4Z4w6A0DuUaBijsViv/71r6PRaHFx8fXXX9/c3PzWW29deeWVzz33XCgU0uv13/3ud8f0HuRDxaxI ZsRE8U+7+/6xf+C25WXnKLdyyJjoneiLZJpK50Ulpu80lVt4TZTOqJhRMecVVMxZUTErEMwpyPlgViTS 2r3hn7/Xzurou1ZVlpgUm5k1PsMmOV4Vz2Z/JP7Mv7o/aPd+u6niDKdic7hIqtmMYEYw5xUEc1YEM1b+ UpiW1/NKIbrkX1Ewns0c892m8hWV5oe3dr5z2POdFWUWQZmDENc6A0BuyN/R33RQJMB84fi9G9qe3dnz c0XX85pJYi0qNSkbeMsrLb+7qsHMM2tebN7UpuQXWIw6A0C2QzArRpFI+PjY0Ddeajbq6KevbJif/nle md/JCBPHfLep/PYzK3/z4bGfvNvuCyvWqajUPTQBAFSBYFaAIkkQE8Vnd/b8dGP7N5aV3rGqUqnFLJUt dhUvnU+rMD99ZYOZZ77+j4Pvt2HCNgAAxphnTKl5Xve/127imKeurC8yKHb9e5oGXBeVmhSMPbl0PrPK 8vCWzo2tnm+vKLcKykzYxqgzAGQjVMypU6rL9K1D7tteOdxUaXnwghqlUlnx0jbd+/9MufnpK+vNPHPD 3w++2jyo4J5ROgNAdkHFnCKl5nk9tLmjdTD48/OrtTaiPM0HUjD2jBzz3abyldXWX23p+KDd952m8kKF vqagdAaALIKKORVKzvNitTjPK6mHU/YRl5WZnrmiodTMfePFFpTOAJCHUDEnJ4vW88okZUtnA0ffenrZ qmrb2s1Ht7R5v3tGhVI9/CidAUD7UDEnQal5Xt965fCenuGnrqzPjVQeaYCybThlluHpK+prHfpvonQG gHyCinm6lJrnpYX1vNJH2dKZ19FrlpYsr7Q8tPnoZpf3u2eUFxuVWZoUpTMAaBaCeWqKJI03FP/lliye 5zV9iq/i2VhseOqK+md39X7zpUNrlpVcUu9Q6g7Cu7uGBCGm1K2dAQAUgWCegkLzvPwPbOpYUmp6+soG BVcOUWQ/aaJs6cwx9JqlJU2VlrWbOza5PN9rqihW7q4eOzt9wWBw5K8af2EBIOchmCekSK5ERem/d/a8 enAwZ+Z5TZ/ipfP8YsOTV9Q9u6v3my8f+sqpxVfOK6CVqp1HGd/grHi1ASBnIJgTU2aelyd8//tZs55X mqSpdH5oS8cml/f7Z1aWWRQrnSeSsP3Z9S4AQBZBMCeg8DyvU4uVKuyyNAzSUTr/9or6Z3f23PRyy5cW Fl17SlE6SufJIa0BIE0QzCdRap7XQ1uOdngjay+qaSjQz3yHsmw/6SsbzxxNrVlacnaN7cHN7R90+L9/ ZmVF+kvnKSGtAWDmEMwn7DjqmflORuZ5/eZzdXkyzyspyvZsz3YIj19W98Le/lv/eeiLpxRe21ik1EVo CsKgNQAkhZIkKfOPOnoSrEZQFLWvLxQOh1PeQyQu/m5758v7ev9rVfV59QVKNWxxuUWpXU2EYRidTjeT 556CnZ1K3uTx0EDgZ++08jr6/5xdU2VPopdCp9MRQmKxmIKNSU0G3ugxOI6Lx+PxuGJ3ws4igiBEIhFR FNVuSKZRFCUIggbPwBmgyoluOmia5nl+9BZ1gtntdmvtdEDTdOsQ5fV6U/v1dk/4Z++3WTjdHasqlbr1 AslUacVxnF6vT/m5p0zZFbhiovjC3v4//7s/qdJZEASKojR7nkrrAWCxWMLhsAbPUxngcDi8Xq/WzkIZ QNO03W4fGBhQuyEqUOtENyWDwWAwnLS4ReKu7L6+vqKioow0KRdgnldqlB111tH0dQuLT6+0rN10dOtR /+1nVDht/NS/pm0YtAbIQ4mDedmyZUuXLl29evXFF1/MsorVf7lHnufV6Y08dFFNPeZ5pUTZUecau/DY ZXXP7+277dXDmh11niGkNUBuSxzMra2tb7/99v/8z/98+9vfvuqqq66//vpFixZluGXad2Ke1+V1gg7z vFKnbOnM0JRcOj+0ueNdl+cHZzpnOwRF9qxlmGIGkDMmG2P2er3PPffcnXfeyTBMbW3tY4891tTUpMij ZvsYc0SUnt3Z89rBwduWl52d/et5aWfoRdlR57goPb+377k9fVfMK7h+cTFLJ/jypPExZsWNPsYwxqy1 s1AGYIxZCye6MaY7xvynP/3pf//3f3fu3HnZZZe98sorZ5555u7du7/whS8cOnQoI+3UtDZP6P732y2c 7qkr67NunpfGpaN0Xl5peWhLx0dHfd9fWangcEOWGv3aGn1SNBqNRCIT/TCOSQBVJA7mDRs2fOtb3zrn nHMYhpG3LF68+P77789gw7RIkshrLYNPbe/GPK+0UnbUudourLt09ust7tvfOPK5uY6JSmcYLzM3rsbx DzDG2K7sL37xiwl/7s9//rOCj5qNXdkj87z+z1lKFl5aOCtptodH2WA45o88tLnDH459f2XlyIps+daV PZrRaJy8Ys4lYz5o6MpWuyEq0OyJbuqu7DVr1mSwPVljxzH/A5s6lmKeV2YpWzqXmbmHLqp5vcX9/eOl 8yw25yZsw0TGHEiWYXpoaEheYASfRNCascF87rnnEkLi8fhIJzYhZNu2bRltlJbI87zeaB783hkVTU7F 1mbCuWCalB11pinq0gbHklLTL7d03PJyy+1nViyqyP0J2zC5MUcXPpugusTF35e+9CV5kcL+/v4bb7zx uuuuy2yrtOKIO3Tryy3NA8Enr6hHKqtoUalJwRet1Mw9eGHNxQ2OH7zpeurDjkg879ZlhEns7hoa+U/t tkCeSjz5a8GCBVdfffVFF13005/+9IYbbvjkk08y3CzVSRJ56cDA7z/u+fKiomsWFCl1U0FE8kwo2LNN U9Tn5xcur7Q8vLXz/Gd2lJjYCgtfYeHKLUKFlSu3cMVG9e9VBaobfbzhwwsZM+F1zA899NBPfvKTDz/8 cN68eYo/qsYnf3lCsYc2dxzzRe76bGWdI6fmeSWk2TkRE1GwlBEEYSgitvZ5u/2RY75wmyfc5gkd9UVi olRo0FXZhGq7UGrmSk1sqZkvNedUWufV5K8xLBbLyBhzajT7cZ4cJn9p8EQ39eSv73//+yN/Li4uvvXW W5cuXUoIWbt2bQbapwWY56V9yk4KM/NMQ4F+zJ2z/ZG4HNJd/siOzqFuf9jlCfE6ptTElpj5MgvntPLV dqHCwhsUurknZBcU05A+Y4O5sbEx4Z/zQSQuPbOjG/O8soKyk8LGM3NMY7GhsfjE19i4KPUOR7v84a6h aJc/8r7L+z+7enqGokaOKTWxVTahysaXWfgSM1dl5XmFvtJBVkBIg7LGBvP1118v/+H3v//91q1bn3ji ie3bt69YsSLjDVPBz95u6fEFn7qi3oH1vLKEsqXz5BiaKjVzY3qzwzGx0xfp8Ec6vKF2b3hrh7/DEx6O xmcZuQoLV2HlKyx8uZWrsPBFRlapFWlAyzDHG2Yu8eSvH/3oR9u3b3e5XBRF3XPPPStWrPjpT3+a4ZZl 3vdW1UjhAOZ5ZZd0l86T43V0rUOodQiEnOhi8UfiHd5why/c4Q3v6Rl+rWWw0xeJi2K5ha+wCOVWTp5l VmnlbELiDyDkDBTTkILEk7/mzJmzY8eOq666av369dFotL6+3uVyKfioGp/8NXPZ9QnU7JyIpKSWzRlb +csfiXf5Iy53qN0bPuaLdPvDbd6wJEmlZr7KJpRZuFIzV2UTamy8kWOm3p0SMPlrJpO/ZkitUwQmf2nw RDfdm1hEIpFoNCr/ORQKCQIWYZiu7IrkXKJu6TwlM8eYx00xGwhE2zwhedD6g3bfX/b09gxHjezxKWbV Nr7aLpSYOaeVV2oeImgEerxhEomD+dZbb73gggvcbvfanKR9QgAAHzxJREFUtWufe+65m2++eZJdxGKx devWDQ0NOZ3O1atXT7Ix5+HTpbpMjjrPXIGBLTh5QkNUFPuHY13+sMsTbvOE9/YNdvnC3UMRu56ttgul Jq7UxJZZeKeVd1p5GkuK5gr0eMNoiYP59ttvX7JkycaNG+Px+DPPPLNs2bJJdrFt2zan03nNNdesXbu2 o6OjoqJioo25DR8njdB46Tw5lqblKWZLyswjGyOidMwbbveGj/nCXUPRDzr8Lnc4HBeLDLpSC19q4qps fLWNLzXzs0yYYpb1ENIw4dyTtra2rq4ueVb25LtoaWmRp203Nja2tLTIGZxwY3d3t9vtJoQUFRXpdNqa 9kLTNCEnrRA+faeOOodmI4ZhKIrS2jsyQ0srbbuO+af8MZqmCSGpve8Zo2fI7ELd7ELj6I3+SLzLFznm D7ncoU/6gm8f9rR7QqJESs1cjUNfZuZLzGyZma916O36xO8sRVE0TWv8uaePTqfT2kyX8fb2njT7Yean Gpqmc+/DPk2aPdFR475MKzArOxAIyAPXer3e7/dPsvHFF198/fXXCSHr1q3TYA1Nef1Go3HqnzvZkgpr OhqTSRRFURRlNmf314vxVs4xE0I+7phsrof8kdDgZ3VKRiMpsZPFJ2/0hWKtg4Ejg4FOb2h3T/DF/YNt 7oCRZcqsQrlVKLcKNQ7D7AKD0yYYOJ0czByXU8uZTRNN09k4dabFe2K22kzOPLn3YZ8OzZ7oxk9CTHw+ +stf/iLPymYY5vXXX6+vr58kmA0GgzypNRgMmkymSTbedNNNN910EyHE7XbLpbN20DQtSZTP55v+r8i9 TFp7IinQ7GRFRdQYCZm4Zzv37sdcayK1JgMhxyd5RkWxyx89fvmWL7C7w9PhCw8Go0VGzmnTm3lGFEUT xxBCGJqSVzFjaYpnKEKIwDIsQxFC9DpaR1OEECNHU4RQFCVPHWdpSp6VxjMUq6MJIXodpaOzYJ6a6rOy Z27jJydOVtPv8ZZnZefAWSsFmj3RGQwGlj1prokCs7Lr6+v3798/Z86cAwcOXHPNNZNszCUY+8ku2TUp TEEsTcszxUZvDEbFTn+4L0R5g+FIJBaIxgkhUZGE4yIhxB+OD4oSISQYDcVEQggZjsYlQiRRGo7ECSEx UQrGREJIOC5F4xIhJBgTYyffpMvI6WiKUIQYOZrIqa+jCSE6hhZYmhAiMCfCXh4XN/MMIYQm5Pj3Ax0t pz7HUDxDE0IEltZR8s4ZiqJoihhZ+SsF0bMMIYRnKI7Jgq8FisOwdI5RYFb28uXLf/3rX69du7a4uLiy srK5ufmtt9666aabRm9MT+NVg0M/G2X1pDBl6Vm6zqFflIbrmIcjcZEQSSJyhMclIqd+LC6FYnFCSCgm xUSJEBKIxuMSIYT4QzFCiEhIICqHvegNxwkhkZgYjkuEkFA0HpN3Ho5LkiQRMiTvXCTHvx/ExDH37hR0 NMvQhBADe3zqupljCCE0TRk4hhCiZ9kaGze3UJhfbLTwOTXKjguxcsCEd5fasGHDxo0bDQbDeeedN/ms 7BRk7wIjOXmUa7aHJ01Gn7lyryt7+nJvgZFQTIzKqR+Ji3LqR+KEEFGUjn8/EMnxTgAdv/eYe1/P8GF3 qMTEzi8yzC00LJhlrLbxTO5ehLao1IQFRjR4opvuAiNf+cpXLr744ttuu62oqCgjDcsOOZnKeQilc64S dLQ86mb+dPW00gl+0mKxfNZpEEUxJoqt7vDenuH9fYG/7u3zhGKzC/QNBfpTZhlPmWWcaEJ7ltrdNUTT tHmI8nqHcDbTssSH3XnnnffOO+/cd999Npvtoosuuuiii5qamjLcMk3BQZx78nbUGUbT0fTom34OBKLN /cF9fYG/fdL/i/fbTbyusdjYOMvQUGiYU6hnc6iYlg9+nNm0acKubEJIf3//X/7ylwcffLCjo0PZ6YvZ 1ZWd88euZnt4MsBgMOw65kdXdr6ZzqzsuCgddof29gy39AebB4Kd/kitjV8wy1hfoF9UYpxlysrLzGia NpvN4z/sOX+WIxo+0U23K/uWW27ZtGkTRVFnnXXWww8/vGrVqow0T4vy4XjNc4vLLcPDJ03/QSUNhBCG psYX0y0DwbdbPY9s7TTxTEOBvrHY0FhiaijUc1leTI8c8zjjaUHiYN69e3coFDr//PNXrFhx2mmn5edI Mw7QvDX+rUdUQ4GBXeFkVzgthJC4KB31hvf1BfZ2D68/7BldTC8sMZZkZzEtQxe3FkzYlR0KhbZv3/7e e+899dRTFEW1tbUp+Kja78rOq+NSsz08GWAwGCiKGh4eTuF3sz2t0ZWt1AjdYDB2sC/QMhDc2xfY1zNs 5LRbTE/UlT2RXDoTavZEN92u7B07drz33nsbN27ctWvX0qVLL7zwwow0TxNy6UCEtEp4qGR7WkMKHHrd CqdlymK6oUBfbc+ydUBRQKsiccW8bNmyCy+88MILL2xqakrHMsKarZirDdpqVWZo9otkBsykYp4+baY1 KuYMLMnpDsYO9AVaBoLNA8F/9wR43fFx68ZZhsZZxsyvU5ZsxTxGVie0Zk904yvmyWZlp482gxnX3avd EBVkJpgTUj2tEcwZXitbFKV2b7h5ILivN7C3Z7jTHyk3c42zjAuKDRkrpmcYzCOyMaE1e6Kbblc2AKQb ppjlG5qmqu1CtV24oM5OCBmOxA/2B/b2BN53eZ/4qIulSUOhQS6mFxQbeZ2mF/1GF3daIZgBtAKD1nnF yDFLysxLyszk5GL68Q+7xhTTVTZh3B17NQEXWaUJghlA05DW+WBMMR2IiAf6h+Vi+rcfdcUlMqdI31hk qC/Qn1JiNHGau+sGCmhlIZgBsg/SOrcZOHp8Md0yEPyfXT2tnnC5mWso0DeWGBcUGTRVTKOAVgqCGSBH IK1z0thiOiq2ukN7u4c+aPf9bkd3XDxRTDeWGM3aKKaR0DOEYAbIZZhilmMMLN1YbGgsPj6Jt8sf+XfP cMJi2mnjabWraXRxpwbBDJBfRs6SFoslHA6Hw+Fp/iISXYNKzVypmUtQTP+rOyZJc4sMcjG9YJbRwqtW TKOAThaCGQCmJX1nVUS+IkYX05JEjnrD+/sC+/qGN33sPeqLVFq4ecWGxmLT8tk6i0qFNBJ6mhDMAKAy RL7iKIo4bbzTxl9Yf2Ka9yd9wfdd3t98dKzaxl8+t2BltVWtO0yji3ty6qz8pcHb31IUJQiCBhuWAQzD 6HS66Xdp5hKWZQkh0WhU7YaogOO4eDyutTX4MkMQhEgkIq/8tbPTp3ZzMoeiKMLo3jnY/fyeniODwYvm FF67sKTMwqvbqsXllgw8imZPdDRN8/xJbwGW5DwOS3JqcKW6DFBxSU7VJTvGnEscDofX6014FsrtInv0 kpzNA8FXDw5uaPXMKzZc1uA402mhVb0RVroLaM2e6LAkJwDAZMbEQw7ndEOBvqGp/BvLSja6vP+9s+c3 Hx27pN5xxbxCq6DONDGMQI9AMAMATCjnc9rIMZc2OC6pd+zs8r9y0P3/Pb//tArLZXPs8vImqkBCI5gB AKYrV3Oaooi81thAILr+kHvt5g49y1w2x3FJg0NQ73YaeTtHDMEMAJCi0ZmRGyFdYGCvW1h8dWPhB+3+ V5oH/3tn72drrFfOK6jJyF0pE8rDAhrBDACggFwqplmaXlVtXVVtPeoNv3nI/b3XW0tN7JXzC8+ptepo lQtokgcJjWAGAFBebuR0pZVfs7TkSwuL3z3ieWFf3zP/6rqg3nH5HEexiVOxVTnfxY1gBgBIu6zOaQNL X9rguLTBIV9h9bV/NM+fZbxqbsHySouKq3HncAGNYAYAyLQszWn5Cqsblsx6o3nw1x8e++32rovr7Zc0 OCyCmlGSewU0ghkAQGXZldM2QXfdwuJrTyna1TX0ykH3H58/cFqF5ZoFhfOLDVP/ctrkUgGNYAYA0Jas yGmaouQrrI75I681D979tqvExF46t+C8Whuv3hVWJCcSGsEMAKBpGr8oq8zMrVlacv3iWR+0+15pHnz6 X91nVVuvnl/otKm8BHf2dnEjmAEAsoZmi2mWpuQrrFoGgq8cHPzWK4fmFhsua3Cc4bQwqi7BPfISfabK oWIzkoKbWByHm1hocG33DMBNLHATi1wyZU6PvolFWgUi4rsuz4uf9PvC8fPr7FfOKyg0sOl+0MmxLLti drEGT3S4iQUAQM7STj1t4I5fYbW3N/D3ff2r/3ZQXoJ7calZxSussgWCGQAgN2khpxuLDY3FzsFA9K1D 7oe2dAoMfUGd7bK5BSZOnXtYZQUEMwBAXlhUaqJp2m63DRjiGQ5ph4G9bmHxtY1FH3b4/3Fg4E//7ju7 xnbFvIJa9Zbg1jIEMwBA3pGL6QzHM01TK5yWFU5Lhy/yRsvg7a+3yldYnV9n51SdIKY1CGYAgDylSjwT Qios3JqlJV9dPGtjq+fvn/T/4ePuC+sdn5vjmKXqEtzaoUAwx2KxdevWDQ0NOZ3O1atXyxvdbveDDz7I 83x5efmaNWsoDPcDAGjSyFB0hhOao6kL6uwX1NnlJbjXvNgyr9hwWYPjTKeFzu8CWoH1WbZt2+Z0Ou+9 996+vr6Ojg554/r1688999z77rtvcHCwtbV15o8CAABptajUpMpyHA0F+u82lf/52rnLK8xP/6tr9T+a /7Kn1xfOtYvZpk+BirmlpWXFihWEkMbGxpaWloqKCkLIqlWrrFZrIBDw+Xw2m23mjwIAABmgVv+2iWM+ P7/wynkFx5fg/ut++QqrJWXmDLdEdf9/e/ce1MT19gH85EYuCCQGuagQBYRwaWkNFFRABanoi60U/FEd R8XSOhVm2loda60zWrXT1lpnKh2r71svZbBK8RV1Rq2ggJFqFRT8WYlR0aEogvDjDrmQ5P1j3zJpsJUi spvN9/MXrrvJec7unodz2DwZhsTc09NDfThaLBZ3dnZSG728vPR6/YYNG/h8vrOzM7Xx888/LygoIITk 5+f7+fk9+1sPO3d3d7qbQBtHjl0sFtPdBHo4OTm5uDjcqEeRyWR0N4E2g7nZE/7Yp/L3tufcHFvxMll8 iE9Tl6Hw3w2fqx94ujilvOA9R+kpFjzrEq9AIGDgQGc0Gm22DL3yV3Fx8W+//RYdHX3z5s2pU6cGBQWd OnVKJBLNnDmTEGKxWKi/K3/77bdKpTIhIYEQ0tbWRpVYEolEXC6dVc4H4nK5rq6ubW0jfQkygUAgEIlE /b9UORSxWMzhcHp6euhuCA1GjRplMBgMBgPdDaGBm5tbV1cX+yp/PRWXy3Vzc2ttbf2nB1Y9pGd86DNb yuvaT2habj3unTlR+kaY+wTpED9hxefzp/h7MHCgE4lENnODoc+YZ82aNWvWLEKI0WisqakJCgrSaDRp aWnU/+7cufPVV19VKpUymaw/B0ulUmpZm4ElOalfUJjWqpHB4/EsFotjxm42mzkcjmPGbrFYzGazY8ZO CDGZTA4Yu8ViGdrN/oKnhNCxvs0lJNbXNdbXta5df0LTknX8tt9oUWqI+xBKcA859udt4PR4GGpl9/X1 5eTkGI1GDw+PpUuXarXaM2fOzJ8/Py8vT6fTicXiDz74QCD4U5VUBiZm1MpmYAnZEYBa2aiV7VCGa6Cj q9hnfwnudr3p1QDZa8rRHs6D/YSVHdXKxpdY/D8kZgZeryMAiRmJ2aEM70BHYy1ubUvv0d+ay+63TR7r 8kaIfDAluO0oMaPACAAADAVdz28TQgLl4rVxPm9Hep+5/Z/t5Q8EPE5SgGxukNxVyIYS3EjMAAAwdHTV JyGEjBbz33zR418vjKlq6Prfmy0/VDVNn+CWFjbGf7R9l+BGYgYAgGFA1wSay+FMHusyeazLww7Dydv/ WfNzrZez4L+U8kR/qROPWR//GSQkZgAAGDY0rm+PdXXKVHktfdnzYl3HkZvN/13xKNFfmhrq7mVvJbiR mAEAYJjRuL4t4HLiJrjFTXCjSnC//UcJ7hn+8hFuyZDZ5TQfAADsAl31t8kfJbjzFigjx476n8pHi/N/ q6hn3CPZT4QZMwAAPF80rm+7CnkLwsakhrpXN+n85RJisIMyf0jMAAAwEmhc3+ZyOK+Md5WJBe32UIIW S9kAADCiaFzftgtIzAAAQAOk57+CpWwAAKANjevbjIUZMwAA0A8T6H5IzAAAwBRIzwRL2QAAwDQOvr6N GTMAADCUY06gkZgBAIDRHC09YykbAADsgOOsb2PGDAAA9oT1E2h6ZswiEeO+xZrD4XA4HGdnZ7obQgMe j8fj8RwzdoFAQAhxzNh5PJ5QKOTzHXHZjMPhSCQSs9lMd0NGGpsGuqkBzoSQaw86Brk/l8tl5kDH5drO kOm5J3U6nclkouWt/wqXyxUKhd3d3XQ3hAZOTk5isdgxY5dIJBwOxzFj5/F4er1er9fT3RAaCIXCnp4e po1CI4B9A12glEf98NT1bYFAYDKZGBi7RCKx2YKlbAAAsHtsWt9GYgYAAJZgR3p2xD8vAQAAi9n789uY MQMAADvZ6QQaM2YAAGAzKjffbLab5xwxYwYAAPZ7aawL3U0YLCRmAAAABkFiBgAAYBAkZgAAAAZBYgYA AGAQJGYAAAAGQWIGAABgEI7FYhn5d21vb2fa97pYLJbu7u5Ro+zvo+jPzmQyGQwGsVhMd0NoYDAYCCFO Tk50N4QGOp2Oz+c75rdLdXV1SSSSgd/qw3oY6Bg40IlEIptW0ZOYGaipqSklJaW8vJzuhtDg/PnzBw4c +P777+luCA327NnT0dGxevVquhtCg1WrVsXHxycnJ9PdEBrMmTMnJyfH39+f7oaMtObm5tdee+2XX36h uyE0UKvV+/bt27t3L90NeTqH+4URAACAyRxxFeuJxGLx66+/Tncr6OHt7T19+nS6W0EPpVKp0+nobgU9 oqOjfX196W4FPebMmePq6kp3K2ggEokceaCbMWMG3a0YFCxlAwAAMAiWsgEAABiE5UvZFotl165dDx48 0Ov10dHRaWlpgzzw3LlzAoEgNjb2uTbvuVKr1bt37/7hhx+oR0937drV2tr68ccfD+ZYuw4/JyensbHx 3r1748ePFwgE77zzjo+Pzz96BbsIf8uWLQsXLvT39z9z5oxard68eTMh5N13392+fbtEIhm4/5CDYn5v 2JzxiRMnTpo0aWgNZn6wf0+r1X722Wf9F/zatWupB7ALCwtFIlFSUhK13d7DpAx5eLfBwN5geWKuqKjg cDhbt24lhKxfvz4mJsbLy4vuRo0cJyenmpqa0NBQi8VSW1srk8nobtFIyM7OJoRs3rx55cqVcrmc7uY8 LyEhIVqt1t/f/8aNG62trUaj0WAwCASCJ2ZldrM540VFRU89pLe3l4EfmxkWERERVIf06+3tnT9/Pl3t eX6eOrxXV1ffuXMnNTV14LEMvwBYnpilUunt27dramqUSiV1/k6cOOHt7R0REfHjjz++9NJL9fX1tbW1 AoGgsbFx9erVLS0t27Ztk0qlfX19s2bN0ul0O3bssFgsbm5uWVlZX3zxRWZmplwu37Bhw7p165g/AkZF RV26dCk0NPTu3bsBAQEtLS3t7e3btm0zGo2enp7vv//+2bNnWRw+xeaM+/r67tixw2AwuLu7Z2dnP3z4 MDc312QyxcTEKJVKOwo/JCTk9OnTc+bMaW5unjJlikajMZvNwcHB3d3d1gE2NTVZB1VUVGR9xg0GAzt6 w4ZarS4rK+vr6/vkk09OnTplc8tfvXpVJBKlpqayI9i/UVRURAUbEhIiEokmTZrEpjAHDu82ERUXFz98 +LC5uVmlUg28ANLT0xnbG7yNGzeO5PuNMLlcrlAozp07l5ub29TUFBoaeufOHRcXl7Fjx964ccPLy6uj o6OnpycjI6O+vp4QcvLkyblz5y5cuPDKlSs+Pj4CgSAgICAlJaWsrGzSpElCobCurk4ul1dVVcXHx9Md 3FPU1dUJhUKNRjNjxoxTp05Nnjz59u3bjY2N4eHhb7/99vXr181ms16vZ2v458+fj4yMlEgkWq3W+oxf uHAhLCxs2bJlv//+e0NDg0ajefHFFxcuXNjQ0FBcXGxH4Uul0vz8/PDw8Pr6+qioqOvXr7e3tysUiqqq KusAS0tLrYPq6+uzPuMXL15kR28QqzNeW1ur1+tXrVpVV1cnEAja2tpsbvne3t6srKyTJ0/ab7B/paWl 5fDhw5WVlSUlJU1NTRKJhAq2traWz+efPXuWHWFSBg7vjY2N1hF5eHg4OztLpdInXgB79+5lbG+wfMbc 2Njo6+ublZWl0+m2bt16+fLl/v/qLz3m5+dHCBGLxSaTqbGxMTQ0lBASFBRECJFIJAUFBT///PP9+/fN ZnNERMQ333xjNpunTZtGRzRDMXHixPv379fW1s6bN48Q0tDQkJCQQAgJDg5uaGhwdnZmd/jWqDPe0NBQ W1tbXV1NCPH19Q0PD8/NzT19+nRSUpJ9hc/n88ViMZVZg4KC8vPzJRJJXFxcdXW1dYA2QZE/X/Cs6Q0b VJtdXV1NJlP/xv5bPjAwkBCSkJDAjmBtWC9lFxUVUcFS2BQmedLwHhQUZB2Rzf42FwCTe4PlT2Vfvnz5 6NGjhBCRSOTv7280GrlcbldXFyFEo9FQ+3A4nP79vby8ampqCCFarZYQcuzYscTExPfee08ul1ssllGj RvX19ZWXl0dFRdEQzJBER0cfO3bM09OTCtPT05MK7datW9TfY9gdPiHE5oyPGzdOpVJlZ2dPnjx5/Pjx Wq12yZIlGzZs+Omnn+wu/ODg4BMnToSFhTk5OXG53KamJg8PD5sAbYIifz7jbOoNazwer//ngbc8VYWU NcH+PeuSqywLc+DwbhMRIcRisfzVBcDk3mD5UvbEiRNLSkoOHz5cWloqFArT0tLkcnleXt6vv/4qk8mU SmVbWxufz1coFHfv3vX09FSpVLt37y4rK3NxcfHz85swYcKxY8cqKiqkUml9fX14eHhnZ2d7e7tdfEq9 rq6Oeljxu+++S0tLk8lkly9fXrx4cW5u7tmzZ/l8fmpq6r1799gafv/C5ujRo63P+Msvv3z48OELFy50 dXXNnDmzu7s7Nze3srJSqVQmJyfbV/hGo7G6ujo9PZ0Q0tTUZDKZpk2bplAorANUKBTWQVH1sa3POGt6 w3opm4pRo9HIZLLg4OAn3vJ2HexfaWlpuXv37iuvvEL9s78rqB9iY2PZESZl4PAuFAqtIwoLCysoKIiL izt+/PjAC8Dm1mBUb6DAyD9z9OhRDw8Pe1nqGXYI35HDt+FQveEgwTpImINEY2+wfCl7eJWUlNy4cSM6 OpruhtAD4Tty+DYcqjccJFgHCXOQ6O0NzJgBAAAYBDNmAAAABkFiBgAAYBAkZgAAAAZBYgZgNL1ez+Fw vL29vby8xo0b99Zbb3V2dg7LK2dkZAy57r+NAwcOrFmzZlheCgCQmAHsQENDw6NHj+7cuSMSiTIyMp79 BXt6eoqKigoKCp79pQBgeCExA9gNsVj89ddfq9XqBw8eWCyWtWvXhoeHe3t7r1ixwmKxZGZmHjx4kBBi MpkUCsXjx4+tj924cWNAQEBgYOCnn35KCMnOzm5paVm+fHn/DhEREVevXiWETJ06deXKlYSQAwcOLFmy hBCyfft2Pz8/pVLZX49o4BbKpk2b0tPTrQthAsA/xfJa2QAsIxQKQ0JCbt261dbWVl1dXVFRQQgJDQ3V arXp6ek5OTmLFi0qLi5WqVRjxozpP+rkyZOFhYXXr18nhMycOTMqKmrnzp0lJSV79+7t32f27NmlpaUh ISGPHz9Wq9WEkPPnzyclJZ07d+7QoUMVFRUCgSA9PX3fvn0KhcJmC/Wd39u3b7969eqRI0esK2ICwD+F GTOA/eFwOKGhofv37y8sLNyyZcujR490Ol18fPy1a9fa29tzc3OXLVtmvX9paWlaWppEIpFIJIsXLy4t LR34mlRivnLlSmJiIofDaW5uVqvViYmJpaWlra2t6enpb7zxxv3798vLywduIYQUFhZu2rQpKSnJujgz AAwBbiEAe2IwGG7evBkYGHjx4sXMzMzly5cnJCSUlJQQQng8XnJycl5eXnl5+b59+6yPokr5Uz+3tbU9 cal56tSpVVVVZWVlMTExPB7v0KFDUql0zJgxEolkxYoV1LNdJpPJYrF89dVXNlvy8vJ8fHyOHz+ekJCw YMECd3f3594RAOyFGTOA3dDr9WvWrImJiRk3blxxcfG8efM+/PDDCRMmaDQa6lHtN99886OPPkpJSREI BNYHTp8+/ciRIzqdrre3t6Cg4Il1+fl8vkql2rNnT2xs7IwZM7788sukpCRCSEJCwsGDBzs7O41G4+zZ s69cuTJwCyFEpVIFBwdnZGSsW7duJPoCgL2QmAHsgI+Pz/jx4/39/Ts6Ovbv308IWbRo0bVr11Qq1apV q7KysjZv3kwIoSa7S5cutTk8OTl57ty54eHh4eHhKSkpc+fOfeK7UJnYx8cnLi6uvr5+9uzZhJDIyMil S5dGRkYGBARER0dPmTJl4Jb+V1i/fn1RUdGlS5eeTzcAOATUygZgj2vXrmVmZlZWVtLdEAAYOsyYAVgi Pz9/wYIFO3fupLshAPBMMGMGAABgEMyYAQAAGASJGQAAgEGQmAEAABgEiRkAAIBBkJgBAAAY5P8A/lqd I4TOCLIAAAAASUVORK5CYII=\n" | |||
}, | }, | |||
"metadata": {}, | "metadata": {}, | |||
"output_type": "display_data" | "output_type": "display_data" | |||
} | } | |||
], | ], | |||
"source": [ | "source": [ | |||
"%%R -w 9 -h 6 -u in\n", | "%%R -w 9 -h 6 -u in\n", | |||
"prophet_plot_components(m, forecast)" | "prophet_plot_components(m, forecast)" | |||
] | ] | |||
}, | }, | |||
{ | { | |||
"cell_type": "code", | "cell_type": "code", | |||
"execution_count": 8, | "execution_count": 5, | |||
"metadata": {}, | "metadata": {}, | |||
"outputs": [ | "outputs": [ | |||
{ | { | |||
"data": { | "data": { | |||
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAoAAAAGoCAYAAADW2lTlAAAABHNCSVQICAgI fAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW 9uIDIuMi4yLCBo\ndHRwOi8vbWF0cGxvdGxpYi5vcmcvhp/UCwAAIABJREFUeJzs3XmUXFd96PvvGWse elYPanVrsCTL\ntmRZWIBtDMQx4BCDwWBsHEguiSMSr2vyQsIliVm5ZIC8ywsXwmAExMYB2+/hsCJjZF 9AtjEYT/I8\nSLJktaZu9TzVfOoM749TVd0ltQbLLbW66/fx6lXqc06dOmd3u+tXe+/fbyue53kIIYQQ Qoiaoc71\nBQghhBBCiDNLAkAhhBBCiBojAaAQQgghRI2RAFAIIYQQosZIACiEEEIIUWMkABRCCCGEqD ESAAoh\nhBBC1BgJAIUQQgghaowEgEIIIYQQNUaf6wuYbY2NjXR1dR1zf7FYxDCMM3dBZyFpA1+ttkOt 3veR\nar0dav3+y2q5HWr53qdbaO2wb98+hoeHT3jcnAaAX/va1/jud7+L53n8yZ/8CZ/5zGeq9nuexy 23\n3MLWrVsJh8PccccdrF+//rjn7OrqYvv27cfc39fXR1tb26xc/3wlbeCr1Xao1fs+Uq23Q63ff1kt \nt0Mt3/t0C60dNmzYcFLHzdkQ8Msvv8x3v/tdnnrqKV544QXuv/9+9uzZU3XMAw88wO7du9m9ezeb\n N2/m05/+9BxdrRBCCCHEwjFnAeCOHTvYuHEj4XAYXde5/PLL+clPflJ1zJYtW/jEJz6Boii89a1v\nZX x8nMOHD8/RFQshhBBCLAxzFgCed955/PrXv2ZkZIRsNsvWrVs5ePBg1TG9vb0sXry48n1HRwe9\nvb1n +lKFEEIIIRaUOZsDuHr1aj73uc9x5ZVXEolEWLduHZqmndK5Nm/ezObNmwHo7++nr6/vmMcO\nDQ2d0m ssJNIGvlpth1q97yPVejvU+v2X1XI71PK9T1er7TCnSSCf+tSn+NSnPgXA3/zN39DR0VG1\nv729vapX 8NChQ7S3tx91nptuuombbroJ8Cc/nmgy50Ka7HmqpA18tdoOtXrfR6r1dqj1+y+r5Xao\n5XufrhbbYU 7rAA4ODgJw4MABfvKTn3DDDTdU7b/66qu588478TyPJ554gkQiQWtr61xcqjiLOK6H\nZbtM5ov0TeQY SBWwbHeuL0sIIYSYN+a0B/DDH/4wIyMjGIbBN7/5TZLJJLfddhsAmzZt4qqrrmLr\n1q0sX76ccDjM7b ffPpeXK04jz/OYyNtM5oooCmiqiqr4+9KWTargkCnYZIsOruv5OxQFBfC/86gL\nmTREDGIBA11V0FUF U1cxNRWtfDIhhBBCzG0A+Otf//qobZs2bar8W1EUvvnNb57JSxJnkO24pAo2\no1mLg+N5cpaDWgrUPM /Dj+4UdBUMzQ/k6kIGqnJ0MOd5HnnbZd9IFtvzYFpoiAeKqhDUVJY2hGmN\nB9E1WQRHCCFE7VpwK4GI s5freqQtm/FskYF0gdFsEQ8PFYVYQCcWO/VfR0VRCBkaIWPmRCLP8yg6\nHi8PpNg9nOWcxgh43im/nh BCCDGfSQAoTgvP80gXHDKWzVi2yGjOIl2wcT0FVYGwodEQNlBm6M07\nHRRFwdQVmvUAlu3yUn+K4uQE arSellhQhoiFEELUFAkAxayyHZehdIHXR7KkCjYKfuAV1DUawuab\nCvhs1yNj2WQKDhnLIW3ZFGyXtn iQ9sTJB3GmrtIcNRnKqDzfN0lIz7CqOUJLLFgZghZCCCEWMgkA\nxZvmuh6pgs3hyQIHxnM4rkc8oNEc DZzU84fSBV7qT/Fqf4qRbJG0ZZOxHDIFp/LvdMEmf5xMX0NT\nWFIXorsuTFd9mO76MEsbwnQmQ5j6zP P9DE0hGQ1QsF2e75skHsiyelGM+rB5Su0ghBBCzBcSAIpT\n4nkek3mb/lSBQ+M5LMfDUCEZNI7bE5e3 HXYNZnipf5KXD6d4qT/FQKoAgK4qNERMIqZG1NRIBHXa\n4gEiAZ2oqRExNSKmTjTgP0ZMDUNTODSRZ9 9olp7RHK8Opvnl7uFy+geqAu2JIF31Yda2xvngeYtI\nhoyqawroKs3RABnL5sn9YzRETM5pih51nBBC CLFQSAAoTlq5VMtAqkDfRJ687aCrCvGAPmNWred5\n9E7keak/xUuHJ3m5P8WuoQxOqYxLWzzA2tY456 +Pcf6iGOc0RY/ZW3c8F1XXDydvOxwYy9Ezmi19\n5egZyfLrvaN878kDfPC8RXx8fTuhI87jB5U66YLN b/eN0hYPsKIxSiQg/5sIIYRYWOSdTZzQkfP6\nDNXP2o0Hj/71SRdsHts3ysN7Rth+aJzxnA1AyFA5ty XGH6xv57zWOOctitEYOT1DrUFd45ymKOc0\nRau27xnO8B/PHOLHLx7mxy/08c4lMf74kigrmiJVx0UD fu/iSKZI3+QI7XG/BzEhPYJCCCEWCAkA\nxTGl8ja9E3kOjGdxXI45r28iX+TR10d5aM8wTxwYo+h4NI QNLu2q5/zWOOe3xljaEEGf4wSL5Y0R\n/ud7VvLpt3dx17O9/OSlPrb96FnevqSOT2zo4KKORCVJRVEU kiEDz/MYyVr0TuRZ2hBhRVNEMoaF\nEELMexIAiipFx2U4XWDvaJbJvI2uKjPO68tYNg/vGeGBnYNsPz iO48GiWIBrL2jld5Y3cn5r/KwN\nlBbFAvxfly/lI8uD/KLX5p7n+9j0ny9xbkuUT25YzDuXNVSuXVEU EkGDWMBj31iG0ZzF2ta4DAsL\nIYSY1+RdTFTm9vWO5+idzON6EDWP7u2zXY+nD4zzsx0DPPL6CHnbpT 0R5A8u6uDdKxpZ3Rw9pTIv\nRcelYPtfLl5pAQ8FRfHwjljRAwUUFDw88BR/wY8STQFDVTF1lcBJzCWM BTT+28Vt3LC+nZ+9Osh/\nPHOIz/1sB4uTQW5c38H7z22pnEdVFJoiAVJ5m9/0jHJBa4zWxJGzCIUQQo j5QQLAGlUu3TKYLnBw\nLEfBcWdcas3zPF4byrB15yAP7hxkJFskHtC5anUzV61uZm1r/KSDPs/zKNgu 2aKD401tCxoayZBB\nXcggbGhoqoKm+uv8qoqCrvnr+noeOKXVOxRAKQWDRcc/Z8ZySOWLTJbuSynFh6 amEjb1Yw5BB3WN\nD1/QygfPW8TDrw9z5/ZDfOmhPWx+Yj/XrWvj2gtaiQf9+X+xoE7QcXm2d5LFGYtV zbFTSlwRQggh\n5pIEgDXE8/ygb/9Yjh3pYSzHQ1MgEdRJaNUJDoPpAg/uHOJnOwZ4fSSLripc2l3PVa ububSr/oRB\nj+d55Iou2aJd6sUDBY9YwKC7IUwiaBDUNYKGivEm1+U1dZVIQKdp2rai45ZqCfprDQ+m LSzXRVf8\nBJaZXlNTFa5Y0cTvLG/kmUMT/GD7Ib712/3c8fQhbljfxqcu7sTQ/OttiZr0pwoMZ4qsbY vTcJoS\nWoQQQojTQQLAGpC1bIbSFvvHcmSKNoXJPK1t9Uf1iGUth4f2DLN15yBPHxjHA85fFON/vGsZ V5zT\ndMK6eLbrkS7YWI6LgkJDxKCrPkYiZBDQVQxVPWMrbRiaSjKkkgwZtCdDlaXpBtN5DozlGcsVsQ o2\nMdc7aq6ioihsWJxkw+Ikrw2luf2pg3zvyYM81jPGP7x3JV31YRRFoSFskrcdntg/xoqmCMsaJEFE \nCCHE/CAB4AJUDnaG0gV6J/OkCzaaohAN6DRHAoznpoZDHdfj6YP+vL6H95Tm9cWD/PHGTt63qpnO\n uuPPcyvYLmnLxvE8TFWlLR6kORYgHpy5l22uKIpCLKgTC0ZZ2hBhIm/zyuspJgo2tuMRNlSiMyR2\nnN MU5Uu/t5or9wzzj7/czcfveo6/eMdSPnz+IhTFX+KuOary+kiG0azFBa1xwqb8byWEEOLsNqfv\nVF/9 6lf53ve+h6IonH/++dx+++0Eg8HK/jvuuIO/+qu/or29HYCbb76ZP/7jP56ryz3rWbbLQCrP\n6yNZck UHTVWImvqMpVteG0qzdccgD+4aYjhjEQvovG9VM7+3upm1bcef12fZLinLxnE9wobGisYo\nDRGDWEB/ U2v9ninlEi/d9WFaFjUylrXYO5plIFUgZKgz3se7ljdy3qIYf//z1/jyQ3t4bN8ot16x\ngvqwiaooNE cCTOSLPNYzytq2OM2x4DFeXQghhJh7cxYA9vb28vWvf51XX32VUCjERz/6Ue655x7+\n8A//sOq46667 jm984xtzc5HzQDmD99B4jt6JPB4eiYAfjB1pKF3ggZ1D/PTlXnrGLXRV4ZKu0ry+\n7vrjZs7ajstE3u /pCxsayxsiNEbNeRP0HYumKjRGAzRGA4znivSMZOhPFVAVhWSweoWTpmiAf7vm\nPO55ro9vPNbDx374 LF/43XO4tLsegETQoGC7PH1wnO76MCuaomdVL6gQQghRNqc9gLZtk8vlMAyD\nbDZLW1vbXF7OvFFO5h hOW+wfz5G3HExdpT5cncEL/ry+h18fZuuOQZ4+OI7rwarGIH/9rmVceYJ5\nfbbjkirYFF0PU1Ppbgiz KBYkGtDmddB3LMmQwYUdSXJFh76JHD2jOYpOkWTQqCS9qIrCDevbubgz\nyd8+sJPPbHmFj6xt5ZbLug nqGgFdpSUa4NB4nqG0xYUdiUoGsRBCCHG2mLMAsL29nc9+9rN0dnYS\nCoW48sorufLKK4867j//8z95 9NFHOeecc/jqV7/K4sWL5+Bq557rekzki/SX1uG1XBdN8dfhjR/R\n2zc1r2+QR14fJlf05/X9t4sX87 5VzSScFMnGlhlfp5LIYbuYusriujAtsQDxgH7GEjjmWsjQWNYY\npas+wmAqz47BDBOFInUhszJ3cnlj hDuvv5BvPNbD3c/1sf3gOP/43lWsLNVCbIiYZKxSzcBFcdqT\nwQUZNAshhJif5iwAHBsbY8uWLfT09J BMJvnIRz7CD3/4Q2688cbKMb//+7/P9ddfTyAQ4Dvf+Q6f\n/OQneeihh4461+bNm9m8eTMA/f399PX1 HfN1h4aGZv9mThPH9chYNiPZIkPpArbjYWgKIUPHLI0s\nZrJTx+8dK/CLvZM8tG+SkZxDxFB515IYv7 s0znlNpQDESZEeHz3qtQq2XzZF1xSaowE6IiZRU0Ox\ni2THIHvUM+a/k/1dWBHyGEwX2N87DAokAnql APWn1kRZW9fO/3q8n0/e8xx/tLaRj5xbV+mJ1V2P\nx18dojlq0n0WLIcH8+v/gdOp1tuh1u+/rJbboZ bvfbpabQfF80qVdc+wH//4xzz44IN8//vfB+DO\nO+/kiSee4Fvf+taMxzuOQ319PRMTE8c974YNG9i+ ffsx9/f19Z3VQ82Zgs1EvsjhyQLDGQvPA0Pz\nM3hnCh6G0gUe3DXE1h2D7B7OoKkKl3TVcdXqZi7rbp hxXt/48ADJxhaKpXl9LhA3NZY1RmiMmFXz\n3hayN/q7kC867B3J0DOaIx7QCZtaZd94rsg//XI3D78+ wkUdCf7ne1ayKDaVfDOSsQjoKus7ksSC\nc5slfLb/P3Cm1Ho71Pr9l9VyO9TyvU+30NrhRHFQ2Zy9E3 V2dvLEE0+QzWYJhUJs27aNDRs2VB1z\n+PBhWltbAbjvvvtYvXr1XFzqaWU7LpMFv05f32SefNFBVRRC hkpD2Jhx2DBXdHh4zwhbdwzwVGle\n35qWGH/1zmVceU4jdeFjFyWuDPGmCwQNjRWNEZpjgRlLoIhqQU Pj3EVxWuNBXjqcYihToKGUBZwM\nGfzf71/Nfa8O8JVHXuf6Hz7L59+9nCtX+uWpy0PCj/WMsK49waK4 ZAkLIYSYO3P2rr9x40auvfZa\n1q9fj67rXHjhhdx000184QtfYMOGDVx99dV8/etf57777kPXderr67 njjjvm6nJnTXkJtolckYF0\ngbFcEdcFXYXoDPP5ysrz+rbuHOThPf68vrZ4gD96iz+vr6s+fOzXLCWN FGwXQ1NpjAY4d0kdydDM\nAaY4vrqwySXd9ewdybB7KEM0oBEx/WzoD6xZxPr2BLc+uIu/eWAnv9k3yl +/cxnRgE7E1DE1lWcO\njbOsIcqKJikcLYQQYm7M2RDw6XI2DQHbjkvedskVHVJ5m7FckZGsheN6qIpC 2NAIGepxg7DdQxm2\n7hzgwZ1DDGUsoqbGFec0Ver1HZn1e+Tr+0O8Hu2JEO2JIMmgQX//4QXV3X2qZu N3YSJX5KXDk6Qt\nu9IbCH7bf/+pg3z/qQO0xoP88/tWsWZRDPAD8pGsRSJosLbtzBeOXmjDHaeq1tuh 1u+/rJbboZbv\nfbqF1g5n/RDwQuO6HnnbIWs5TOZtBtIFJvM2Hh6goCkQ1DXqQkeXajnSTPP63t5Vx1 +uauaypTPP\n65suazmkLRtdU1neGKE9GSSga8d9jjg1iZDB27qmegMjpubP19RU/vRtS9i4JMnfPbCL //b/vcDN\nl3Tx8fXtqIpCUyTAZL7Ib/aOckFbXIaEhRBCnFESAJ4ix/UYzlgMZwoMpy3ytoNb6kvVVb 9371hz\n+GaSLtg88vpI1Tq85y2KnVS9PvDn9k3mi9iu59eza0/UVELHXNJUhRVNUVpiAV46nGIwbdEQ NtBU\nhXVtCe76+IX8wy9287Vf9/D0gXH+/j3nUB82iQcNio7LM4cmWFJnsbJZCkcLIYQ4MyQAPEXpgs 1T\nB8aImhohQzulJIp80eHXPaP8fNcQj+0bxXI82uNBPrXRn9e3pO7Y8/rKpvf2ddWHaY0HJaFjjsSD \nBm9bUseB8Rw7BlKEdI1YUCce9BNE/vPFw/zro3u5/ofP8g/vXcnFnXUYmkpL1KRvIs9IxmJde4LE\n CYJ9IYQQ4s2SSOFNMDTlDa/yUHRcHt8/xs93DfGrvSPkii4NYYMPn9/KlSubOG9R7IS9hk6pKLTt\nQT KoS2/fWURVFbrqwzRGTF46PFnVG3jt2jbWtiX4/NYd/PlPXuYP37KYP33bEnTVLxydtRwe6xll\nZXOE 7vpIzRTeFkIIceZJAHgG2K7HM4fG+fmuIR7aM0KqYJMI6rx3ZTPvWdnEhe2Jk8oGzdsOkwUb\nTVHoTI ZpTwTnvKacmFk0oLOxs459o1l2DaWJmn7dwBVNEf7jhgv5yiOvc/vTB3nm0AT/9L6VtMaD\nhE1/KbnX hrIMZSwuaD3zCSJCCCFqg7y7nCau5/Hi4Ul+vmuIX+4eZjRbJGJqXL6sgfec08TGzuRJ\n9di5nsdk3s ZyPGIBjbWtcZqiAZkrNg+oqsLSxggNEZNneycYyVo0hE1Chsatv3sOF3cm+edte7jh\nR8/xd1es4HdW NKKpCs1Rk4lSgsjatjgtkiAihBBilkkAOIs8z2PXUIb/s2uQn782zECqQEBTuXRp\nPe9Z2cTbu+oInm Q2ru16TOSKuHh0JEJ0JEMkgrrU7ZuHEiGDS7rqeaV/ksOpAo1hE01VeM/KZta0\nxPibB3byuZ/t4NoL WvnMO7oJ6hqJoIFluzxzaJwl9WHOaZIEESGEELNHAsBZsHckw89fG+Lnu4Y5\nMJ7zy7YsqePmS7p4x9 J6Im9gGK+8PJuiwNLGMB2JEEFDSrjMd6au+gkeI1l2DKZIhgyCukZHMsT3\nP7qWb/12H//xTC/P903w patW010fxtRVmqMBesfzDKUt1rbFj7vKixBCCHGyJAA8RftGs/y/z/fx\nWM8Yu4czqAps6EjyiQ0dvG t5A4k3mBySKzqkCjaGprKqOUprPIh5gnp/Yn5RFH9IOBEyeK53gnzR\nJRkyMDSVWy5byoaOJH//89e4 8a7n+MvLl3LNeYtQFD9BJFd0eHzfGEsbIixrDEtvoBBCiDdFAsBT\n0DeRZ92/PgrABa1xPvvOpVyxoo nGyBvrnanM73Nd4qafzdsUDcjyYAtcQ8RfSu7FvgkGM/6QsKoo\nXNJdz903rucL/2cX/7xtD7/pGeXW K1ZQV5o3GNBVDoxl6ZvMs6YlSnMsIFMChBBCnBIJAE9BWyLI\ntz50PmFT5bxF8Tf8fM/zmMjbWI5LRz JEZzJEXOb31ZSQobFhcV1lBZFESCeoazRGTL5xzXnc81wf\n33ish4/98Flu/d1zuLS7HrXUG1iw/eLR zbEAq5ujRKTuoxBCiDdIxpFO0Q3r22mJBd7w81J5268N\nFzG4bGkD57fGSYROfsUQsXCUVxB5a1cdua LLeK4IgKoo3LC+nTuvv5C6sMFntrzCvzy0h3zRASCg\nq7TE/KXkHt07wr7RLK67oJb0FkIIcZpJAHgG OK7HaNZiMF0gEtC4pLuede1JWbFDAFAfNrm0u55Y\nQGcgXcD1/GBueWOEH3zsQj6+vp0fv3iYG+96jp 2D6crzEkGD+rDJjoEUzxwaJ2vZc3ULQggh5hkJ\nAE+jouMylCkwni/SWRfm0u4G3tJZJ0t9iaMEDY0N i5Msb4wwmLYo2C7g9/b9xTuW8q0PnUe26PDJ\ne57njqcP4pR6/HRVoTkaYDJv8+jeEfZLb6AQQoiTMK cB4Fe/+lXWrFnDeeedx/XXX08+n6/aXygU\nuO6661i+fDkbN25k3759c3Ohb1DBdhlMW2Qsh9XNMd61 vJGVzVFZtUMcl6oqnNMU5S2LE2Qsm4l8\nsbLv4s467r5xPe9a1sA3HtvHn977IvtGs5X9yZBBXcjklY EUj+8fYyJXnOklhBBCCGAOA8De3l6+\n/vWvs337dl5++WUcx+Gee+6pOub73/8+dXV17Nmzh7/4i7/g c5/73Bxd7cnJWg6D6QJFx2VdW4x3\nLm9kSb2U7BBvTHMsyKVLG4iYGoNpqzIknAgafOmqVfz9leewdy TL9T96ls1P7Mcq9RbqqkJLNIDt\nuPx23yg7B9IUHXcub0UIIcRZak4jE9u2yeVy2LZNNpulra2tav+W LVv45Cc/CcC1117Ltm3b8Lyz\na3jLz+gtMpguoGkKGxYnuWxpA62JkJRzEacsZGi8ZXEdyxvDDKYt8r afAKIoCu8/t4Uff+Ii3r28\nkc1PHOCGHz3Lc70TledGAzqNEZMDY1kefX2E/sn8Wff/jRBCiLk1ZwFg e3s7n/3sZ+ns7KS1tZVE\nIsGVV15ZdUxvby+LFy8GQNd1EokEIyMjc3G5MyoUXQYz/vqub++q5+1d9T RFA6gS+IlZoJazhJdU\nZwmDX0vwn963iq9/cA2W4/InP36Rf/rlbibzU5nEDRGTsKHxXO8ETx0YI5WX JBEhhBC+OZuUNjY2\nxpYtW+jp6SGZTPKRj3yEH/7wh9x4441v+FybN29m8+bNAPT399PX13fMY4eGhk 75mqcrOi5teoGG\nsElQcciMZciMzcqpT7vZaoP5bj61w/Kgy+6hDHuHiiSDBmrpo9u5UfjOVYv5jxdH uPeVfh7ZM8Sf\nbWjmnUuildJCJjA46XDwUB+t8QDBYmbubuQsMp9+/qdDrd9/WS23Qy3f+3S12g5zFg D+8pe/pLu7\nm6amJgA+9KEP8dvf/rYqAGxvb+fgwYN0dHRg2zYTExM0NDQcda6bbrqJm266CYANGzYc NZR8pBPt\nP1lLZuUsc2O22mC+m0/t0NnhsXckw2vTCkcDJIG/XtTKB9al+adtu/mn3xzmkUN1/I93L6 c1Hqwc\n43keY7ki/SmLOjNBZ10Ivcbnp86nn//pUOv3X1bL7VDL9z5dLbbDnP317+zs5IknniCbzeJ5 Htu2\nbWP16tVVx1x99dX84Ac/AODee+/l3e9+txRMFjVLVRWWlwpH54suI5mpBBGAlc1Rbr9uHX95+V Ke\n7Z3gI3c+ww+fPYRdKgujKAr1YZNYQOe14TSP7h2ldzxXKSkjhBCidsxZALhx40auvfZa1q9fz/nn \nn4/rutx000184Qtf4L777gPgU5/6FCMjIyxfvpx//dd/5ctf/vJcXa4QZ436sMllSxvoqAsylLFI\n F6bm9mmqwvUXtvPjP7iItyxO8r8f7eEP73meHQOpacdAUyRASFd58XCKR/f6iSJSP1AIIWqH4i2w\n9M ANGzawffv2Y+7v6+urya7e6aQNfAuhHSZyRV7uTzGRL9IQNtGnJSB5nse2PcP8r4dfZyxX5GPr\n2tn0 tiVYk8MkG1sqxxVsl4l8kYips7IpQnMsUBM97Qvh5/9m1Pr9l9VyO9TyvU+30NrhRHFQWW1P\nABJink uEDN62pI41LTHGc0XGc1al5IuiKFyxool7P7GBa85bxF3P9fLR/3iGJw6lq84R0FWaowE0\nBZ7tneCx nlGG0wUpHSOEEAuYBIBCzHOqqrCkPsw7ljXQEDEZSBfIFZ3K/lhQ5/O/s4LvffQCwobG\n3z3Sx+d/to PhjFV1nqCh0RwNAPD0wXEe6xllKF2QoWEhhFiAJAAUYoEIGRrr2pO8dUk9rgeDmUJV\nksi6tgQ/+viF /OHaBn61d4QP3bGdb/9231H1AUPTAsHtB8f5Tc+ozBEUQogFRgJAIRaYhojJJd31\nLG+IMJSxqnoDDU 3lxvMbuPvG9by9q47vP3WQq29/mu89eYCMNXMgqKnwXO8Ev5EeQSGEWDAkABRi\nAdJKq4i8bUkdRddj JGNVzelbUhfmy7+3mh/dcCEXtse57fH9XP3vT3Pn9kPkpwWMAEFdq8wRlB5B\nIYRYGCQAFGIBqwubXN pdT1siyGC6UFlTuGxlc5R/vXoNd3xsHee2xPj6b3r4wO1Pc/dzvRRst+rY\n8hxBTfF7BH+1d4TDE1JH UAgh5iMJAIVY4AxN5bzWOBsWJynYHhM5+6gM3/MWxfi3a87jex+5gK76\nMP/Pr/ZyzR1Pc++Lhyk6Mw eCAU3l+b4UD+8ZZu9whqwlaw0LIcR8IQGgEDWiORbk0u56WuImA+nq\nuYFl69oTfOfaC/j2h89nUSzA lx/aw4d/sJ37XumvrChS5pePMYmZGruHM/zq9RGe3D8m8wSFEGIe\nkABQiBpi6ird9RHe3lXnZwqnC0 cN9QK8ZXGS7390LV/7wBoSQYMv/mI3H73zGR7cOXjUkK+uqTRG\nTJqjASzbrcwT7JvIYc1wbiGEqDWT +SLD6cJcX0YVfa4vQAhx5pXnBg6k8uwcyjCRt0kGdUx96jOh\noihc0l3P27vq+NXrI9z2xH7+7sFd/P tTB/nTty3hXcsbUI9YMSRsaoRNjXzR4cXDkwA0RwO0J0Ik\nQzoBXTuj9ymEEHPBcT1SBZsbOcrFAAAg AElEQVRUvkjvRJ7hjEV92KSxVGLrbCABoBA1SlUVWhMh\nmmNB+ifzvDaUYfwYgeA7lzfyjmUN/PK1Yb 7zxH4+97MdnNMU4U82dnJZdz26Vj2YEDQ0goaG53mk\n8jbPpsdRPH/lko5EkIaISdiUPz9CiIXD8zwy lsNAKk/PaI6i46IqCmFDoz5szvXlHUX+AgtR4zRV\noT0ZYlE8yOGJPK8NZ5goFKkLGlWBnaooXLmyiX evaOTBnYN898kD/NX9O2gIG7xvVTO/v6aFZQ2R\nqnMrikI0oBMN+H9qckWHVwfSuJ5HMmTQVReiKRo4 KoAUQoiznev6Ad9kvshAusBIxsJ2PVRFIRnU\n0TWjcuxMU23mmgSAQgjADwQ76kIsigfom8yzayiD4x ZJBIyqHkFdVXj/uS28d2UTj+0b46evDnD3\n83388Nlezm2J8vvntvCelU3Eg8ZRrxEyNEKGPwycKzo8 35dCU1M0hk0aIyaxoE7ErO6BFEKIs4Xn\neUzkbQ6O5+ifzGN7HioKQV0lETTQVOXEJzlLSAAohKiiay qddWFa4/7Q8J7hLOP5IlFTJ2xqVcdd\nvqyBy5c1MJa1eGDnED99dYB/efh1vvroXi5f1sDV5y7i4s7k jH8Uy8Gg63mkLZuhjIXreShMrUJS\nHzEJGSohQ8OQXkIhxBwpOi5D6QJ7R7Kk8jYBY/4FfEeaswBw16 5dXHfddZXv9+7dyxe/+EU+85nP\nVLY98sgjfOADH6C7uxuAD33oQ3zhC18449cqRC0yNJXFdWHaEyGG MxZ7RjIMpPJEzKkh3bK6sMkN\n69u5/sI2dg1l+OmrAzy4c5BfvDZMc9Tk91a38P5zm1lSFz7qdVRFIW LqRKZNkbFsl77JPPvHs3ie\nAngEDY1EQPcDR1MjqKvoqoKhqRiaQkDX5tUfY8f1cD0PzwNFAQVwPA/H 9VAUBU1RUBUqiTbl3GtV\n8YfWhRCnX6Zgc3A8z4HxLI7nETd1mmNnTyLHmzFnAeDKlSt5/vnnAXAch/ b2dq655pqjjrvsssu4\n//77z/TlCSFKVFWhORagKWoyniuyazDNQKpAIqQTPCKrV1EUVjVHWdUc5ZZL u3m0Z4SfvjLAD7Yf\n5PanD3JBa5x3r2hgXWuclc3RY/bqmbp61DCw7bikLZvxfBHb8XDx8MOm0qPnEQ noaIqC43loij8s\nY2h+kGhqKgFdRddUXM9jKFVAncyjqQqqoqAo/pwe1/PPOL1Ytgc4rovtgu26FG2P nO1SsJ1KAOd5\n4OFhO34QZ3serltuF3+IXStFepbj4rmA4jF1G6UocNpdgTcV+ZV2Kor/ZWh+AFxpM0 0lqPv3aGoq\nIVPDKAXIZilY1hQFdR4FyULMBdf1GMsV2TeaZTBdwNAUkvO8t28mZ8UQ8LZt21i2bBlL liyZ60sR\nQhyDoijUhU02LqljJGPx4uEUmYJFImRUBSJlpq5yxYomrljRxHDG4mc7BvjZq4P870d7/P 2awrkt\nMS5ojXNBW5wLWmPHzZTTNfWEySKW7YeFuqLgARnL8Xva8HBdD6cSTHmkR7McdiePEXT5AaFX jr48\n//4V/EBOUfy5kOU3BM8DpfRfQPcDyuk9dZ7nn6lcQjFmam+qF8/1/EDVdT3Kp7Edl/GiU+lFdD 0P\nrxQYl+8Rz2/HaEDHmcxCJEfY1AkZqpToETUtV3TIFGwGMwX6JgoUHZewodEUMRdsj/ubCgBjsdhx \nG2ZycvKkznPPPfdw/fXXz7jv8ccfZ+3atbS1tfGVr3yFNWvWnNK1CiFmh6IoNEYDXLbUYO9IloPj\n frkDU1OJBfQZPyU3Rkw+uWExn9ywmOGMxYuHJ3mhb5IX+ya567le7nzmEACLk0E/ICx9tSUCRN5A\nuZ g3kjyi53SS0TNTmqEcPM5WB0I5wJx+QuMk4zfH9Sg6LsPZAunDqVKQq2CoCsmQQV3IIGxqlV5T\nf3hd XbBvgqI2ZQo2g+kCI1mLQ71jBCd0PLzK37GZPtQuNG8qAEylUgDceuuttLa28gd/8Ad4nseP\nfvQjDh 8+fFLnsCyL++67jy996UtH7Vu/fj379+8nGo2ydetWPvjBD7J79+6jjtu8eTObN28GoL+/\nn76+vmO+ 3tDQ0Eld10ImbeCr1XaYzfuOAasjHumCzXDG4tCIhedB2PSDh5nowPokrE9G4NwIluPy\n2kiBV4ZyvD KU47G9I/xsx2Dl+JCuUB/SaQjpNIRLjyGNhpBOfUinMew/ho03liSSHh99E3c+M9fz\nKDoeRdd/tNyp 7y2nep/r+T2SXrk3D79HzwO/p9Lz0FUFXfODM12devTnPiroKhiqQsTQiAXUowpz\nH1d2En1acO240D /ucMApD12Xx7ZBUSFm6qUsbQ1TVwnqGoY2/98ka/XvANTWvduu/3cqVbAZzxVJ\n5W2U0jQRLzOJMW1e czoz+69fLA0/9AXys3/yU6R4R64KfwrWrl3LCy+8cMJtM9myZQvf/OY3+fnP\nf37CY7u6uti+fTuNjY 3HPGbDhg1s3779mPv7+vpoa2s74WstZNIGvlpth9N53+VMuT3DWTIFm6Dh\nf5p+I71HnudxaCLPK/0p BtIFhjMWw2mLoYzFcMZ/nKmmVtjQqAsbfpCkKeiqWgmWKl/a1Da3WCAc\nClW2KQrYjt87ZjkeRdf1Az Zn2qPrYTnutONc7NI2qzT3b65oqkJD2KAhbNIQMWkIG9SHTRoiBo2V\nbf73YUNjYmSQZGPLSZ3b9Tzy Rf9+i45HaXCZgKGRDBk0hAziIYOIOf+ytWv17wAs7Hsv2A6pvM1k\n3v9wOpK1AH/qRrhUqL5sfHjgpP 9fOPXr8f9mvb27/rS+Dpw4DiqblTmAkUiEH/3oR3zsYx9DURTu\nvvtuIpHIiZ8I3H333ccc/u3v76el pQVFUXjqqadwXZeGhobZuGQhxGlgaCptiRCt8SDjuSIHxnL0\nTeZRFIgY1WVkjkVRFBYnQyxOhmbc73 ke6YLDcNZiKF1gOFNkKFNgOG0xni9SdDxst/RVCtBs1yNv\nu9iuje36AZxVtHEVq7TfxfP86y8nTpST R8rfh00NU1NLPXIqZmm/rimY04ZL/cep/eYR/y4fo2tT\ncwWrH0vDu5WAtDoYtd2pYLQcnKYLNiPZYu WNbihdYOdgmrGsNW3e45SgrtIc0emsH6YjEaQ9Eaw8\ntiWCRyX3qIriL/NH9XbbcZnMFRlMFfDwM5r9 VQ8M6sIGkVLpIJlfKE63ouOSsRxS+SKHUwVGMxYo\nCpoCQX1hz+U7VbMSAN51113ccsst3HLLLf76oZ dcwl133XXC52UyGX7xi1/wne98p7LttttuA2DT\npk3ce++9fPvb30bXdUKhEPfcc4/8AIWYB8oJI3Vh k1UtUUYzFgfG8wymC6ilP8hBQzuleTaKohAL\n+sOR3fVHl5U5WWfiU/9ccz2PiVyxKjgcyfj/PjA8wW CqwLOHJsgWnarnNUXMqqCwIxmiPR6kqz5U\nVeBb11Simsr05U2LjstIpkjfZB63lDxjlucXhk1iAf9n H9RPnNQjxPGk8jZ9k3n6J/Pkii7gl1AK\nGxqNEvCd0KwEgF1dXWzZsuUNPy8SiTAyMlK1bdOmTZV/33 zzzdx8881v+vqEEHMnoGu0JkK0JkJk\nLZvhtMVw1mI065dzQfGTEBT83qOQIQkHs0WdFogvb6welSkH wJ7nMZ4rcmgiT+9EvvLYO5HjqYPj\nDO6wqp7XEDborg/T3RCmuz7M0vowXfVhGsIGilLuPVWJTXt7sV 2/2PdwxsIfCPMzrU3NXyowETKI\nB/VKCZuArs67oWRx+uWLDtmiw3i2yOFUnsm8ja4qxAJH1yYVJzYr LTY0NMR3v/td9u3bh23ble3/\n/u//PhunF0IsEGFTp7Nep7PUc+eU5s9lLYdUwWaolJXnlYqy6MrUMK tWGh4FPzfhDSU8nGXKZWHA\nr9AyPeAt7/O8I46blkk8mwHy9N7a81vjR+0v2C6HJ/McGM+xbzRHz2iW ntEsW3cMkrGmeg5jAb9H\ntrs+5AeHdX6AuCge8OddHlHsG6jMnzw0nsN2vUoZHs/z52rFggaJgE601G sYmFbnUD4kLHxZyyZV\ncBhKFxhMFbDc8u+G/2GxObowCjLPlVkJAD/wgQ9w2WWXccUVV6BpMtdDCHFy NFUhpPpLwjVETLrq\nwziuR9ZyyBWdStZetuhQsF2cUpDgwVTvoQeUgiN/WFFBpTyPTikFWKcWME6v32 e7Lq5brsHnZ+46\npcLRUzUDS69RKe7sTRV5LodypQBOU5Sp81eKQiuVotEqoJQewc8SdlwPx/Pw3Gmv WTp3peZgVWgJ\nCv7i9OVVU8pJMCcroKt0lXr53rG0um2GMpYfEI5kS4Fhjkf3jrLllYHKccHS87vrQ6 UA0f/qSIZK\n1zK1PvR0rudh2S6HU3mK4+WguLxKCtSFDeIBwy9+bfgZyYaqYuqKBIjzUL7ofwicyBdJ FRzGc0Xy\nRQdFgYCmEgnoJGqgNMuZNCsBYDab5V/+5V9m41RCiBqnqVNz/I635FK597DouFi2S9pyGC u9afgJ\nIB6e6/nlVUpLrpUDJkWBdM6mmLYqQ9CVVTcqAVs5cPTnugU0lbDpZxebmoqhK5iqv8pGObDy VxWZ\nSuYoL/FWDkbKb18zrcZRDm5ORrl4g+dNFYUuJ2Hg30mlXYquR85yyNlOqditw4Tjks4VKWYK/l VN\nC1jL91JOWDnWNSmKQnM0QHM0wMbOuqp947lipaewHCA+2zvJAzunyo7oqkJnstRbOC047KwLEdQ1 \nVEXx5wrOEBw6rkfOcpnIlXsOpz4IlNvZUBUChlpJ0Cn3HJq6/zMsJ/pYpQ8WC22Vh7OV53lkLP8D\n neW4jGYtBtMW+aI/OcBQ/WSskK4Sl2Hd02pWWvf9738/W7du5aqrrpqN0wkhxAlN7z0EaAS6jnO8\n5/ nZwE5p9Yz+w0UWtTbgeVSt3FHuMTzTPUhv5PUqAaUCKjM/b6ZetTLP8zjYW6SppRHb8bOgbdfv\nccvZ DqmC3/s6mbVxy4Gp50eJqkJVtvNMgVMyZHBhe4IL2xNV2zOWXTWM3DOaZfdQhof3DFdWSVGA\n9kSQ7l Kv49JS72FXfbgyz0tTZ85Knn5/TqmHtmD7Uwwcb2o1mMryfUBmdJydGcMPOgyNsKkRNFTC\nulbVs1jO CpdA8eQVHZd80SVvO+Qsh5RlMzBZoOC4pd9hj0Cp3SXYO/NmpcW/9rWv8c///M+Ypolp\nmpVPsie7Eo gQQpxufoKCUlkxw1/hojanrCilIeGQoYFx7OPcSo3DqTI0edslU5qbNVnwy+qUzuov\nlVdap3imRI6I qbNmUYw1i2JV2wu2y8FxPzDcO5Jl32iWvaNZnjgwVimgC9AcNStBYXlYeWl9mLoj\nlhBUFAW9tFzfiR g5g2Q04K+Q4rp+1nTGm+pZnD6sj+f3Bld6fUFVVAK64pe8MbRSDcryl9+buhDX\nX/aDa4e87fc0lx8d 1yNXdJgo2BRsh6mpCP7yjxFTI6Ed55dOnDGzEgCWVwQRQgixcKiqQlCdeRi2\nrOi4leG8wrTgcCJXZD xnl0ZmPQxVJWj4Q+lH9nYGdJXljZGjMpVt16NvIs/e0amgcN9oli2v9JfK\nfvgSQZ2lDWG6SoknSxv8 ALElevKlQDRVQVO1E74ruqW1lh3HpWiDh8NkDnqdPG55KBoqw9F4Hqo6\nVSsyqPs9XgHdH442NK0yfa D86JWmLKilKQUKU9MJ/FMrbzgZqDxlokwvvU6ZPS3QL/eWut7UXMys\nXZ6T62A5Ll5pPm6l17zUhmpp DmtYhnDPerPy0ykv/9bT08Ott97KwYMHOXz4MBdffPFsnF4IIcRZ\nqlz2ZSZFxyVXdMgVXcZyFqMZvy bh9LmYuqocMzDUVYXOuhCddSFYNrUIgOt5DKYK9IzmKkFhz2iW\nh/YMM5GfqkQRMTWW1FUnn3TXh2lP BE95KFdVFNRpPcknwy0FVLbnl8OZyBdLCT3Tk4eqk3d8pX2e\nVxmyriQUleaq+tMVjrg+SsGhQmUebN FxS8dNzXfNjI0RTRmVuaNTiUtK6Sj/5+TPg/WHwsO6SszU\nJMlmAZiVAPDP/uzPUFWVhx56iFtvvZVo NMqf//mf8/TTT8/G6YUQQsxD5eAwHoSWUkKP63oUHJd8\nKbN7PF9kNFNkNFss9aApKIpHQPPn4s0UXK qKwqJ4kEXxIG/rmkpA8TyPsXICykiWnrEcPSNZnjow\nXrW+tKn5gWV3fZjWoMfqDtVPQEmGMPXZrz9Y DhpPR3/Y9F68Svmgo15/5ix4I2+QPLI2j6gZs/L7\n+OSTT/Lss89y4YUXAlBXV4dlWSd4lhBCiFqjHp G8sygeBKoDw6zlMFoqFj6eK/qlc4CAVh46nTlI\nUxSF+rBJfdjkoo5k1b50wa7OTB7N8epAml9O5PFe 9Bck0BRoT4ZKNQxDlWLXXXXhk1rGcC5M74mr\ndPAJcRJmJQA0DAPHcSq/iENDQ6iqVHEXQghxcqYHhn VhPxAD/PlnRYdMwWY0azGWs5lIW5WgsDyn\n7kRDutGAzvmt8aOKXff3H2ZCjR0RHGb5zb5RHHeqL21R LDBtGDlUWQ0lEZSEBjE/zUoA+N//+3/n\nmmuuYXBwkL/927/l3nvv5R//8R9n49RCCCFqmFnq8UuGjE pQaDt+UJgu2AymLYYzFrbrlwg31Kkk\ni5MR1FUWNUZZ2Ryt2m47LodKCSjTi10/2ztBwZ5KpqgvL41X H6arlJXcXR+WtWjFWW9WAsCPf/zj\nXHTRRWzbtg3P8/iv//ovVq9ePRunFkIIIaromkpcU4kHDdoSIT zPXz0mYzmM5iyG0hZD6YJ/rKoQ\nMrUZk0xO9BrlFVCmcz2Pw5MFeo7ITH5w5yDpaUvjRU1tqpZhw1QC Sms8MK+XMRQLx5sOAB3HYc2a\nNezcuZNVq1bNxjUJIYQQJ01RFCIBnUjAXz1mVTMUbIdU3mYsV2QwXW A4Y5XSZT1MTSWka6eU8KEq\nCu2JIO2JIJd211e2e57HSLZ4VC3D3+4b5aevTi2NF9BVltSFptUy9APE xYkg+jGyqYU4Hd50AKhp\nGitXruTAgQN0dnbOxjUJIYQQb0pA1whENRqjAVY0RStrTGeLDqMZi+GsxU S6QCZn42YtwqVh41Md\ntlUUhcaISWPE5C2LqxNQJvLFUo9hrjKc/ELfJA/umloaT1MVOpPBqaCwFCB2 1YWOW4dRiFM1K0PA\nY2NjrFmzhosvvphIZKqQ53333XfM5+zatYvrrruu8v3evXv54he/yGc+85nKNs /zuOWWW9i6dSvh\ncJg77riD9evXz8YlCyGEqCHT15gul6SxbJe9B/KY8QiDGcuvUVhaySpsaISMUw8I p0sEDda1JVjX\nVr00XtZy2D/mZySXk09eH8ny6OsjlBdAUYC2eNCfX1gqcN1dKngdC0qhZXHqZuW3J5 /Pc//991e+\n9zyPz33uc8d9zsqVK3n++ecBfxi5vb2da665puqYBx54gN27d7N7926efPJJPv3pT/Pk k0/OxiUL\nIYSocaZemkfYGGFpYwTbcclY/iomA+kCI1mrVBdZIWSoBPUTZxu/EWFTY3VLjNUt1UvjWb bLwYlc\nJfFkb6n38OmD41jTlsZrjJilnsLqYtf1YUMSUMQJzUoAaNs2l19+edW2XC530s/ftm0by5Yt Y8mS\nJVXbt2zZwic+8QkUReGtb30r4+PjHD58mNbW1tm4bCGEEKJC11QSIZVEyKCzPozjeqQKNpO5Io OZ\nAmPZYqVnTsUP4IJvYtj4WExdZVlDhGUN1UvjOa5H32R+qlzNiN97eP+rg2SLUwkoiaBeGUqeXram \nJSYJKGLKmwoAv/3tb/Otb32LvXv3csEFF1S2p1IpLrnkkpM+zz333MP1119/1Pbe3l4WL15c+b6j\n o4Pe3t6jAsDNmzezefNmAPr7++nr6zvmaw0NDR1zX62QNvDVajvU6n0fqdbbodbvv+xk2kEH2jRo\njX oUHY+87ZAuOIyNFRkoFPE8P9s4bM5uD+FMYsAFcbggbkKXCSTxPI/hrM2BSYv9ExYHSl8P7x7i\nvwpT gWFQV+iMm3QmTDoTAZr1AqvaLFqjxmm/7rNZenz0tL9GsfTJoS+QP+2vdbLeVAB4ww038L73\nvY/Pf/ 7zfPnLX65sj8Vi1NfXH+eZUyzL4r777uNLX/rSKV/HTTfdxE033QTAhg0baGtrO+7xJ9pf\nC6QNfLXa DrV630eq9Xao9fsvezPtUO4lHEgV6J3IUbBdFEXBUP15hKdjabmZ1AErZtg+lrUqcwzL\nmckvDWX5ZU +qdEQKQ1NYnJyqYVj+6qwLnXQ9xfku2dhyWs9frh3Z1nZysdGZ8KYCwEQiQSKR4O67\n7z7lczzwwAOs X7+elpajG7+9vZ2DBw9Wvj906BDt7e2n/FpCCCHEbNJUhWTIIBkyWNkcJVf0y8+M\nZCwG0wXG80UUBY KaRsjU0M9wT1td2KQubLK+ozoBJV2webnnEMNuiL0jWXrGsuwaSvPQnmHKC6Co\nCrQn/MzkcnDYVRpS jpiSgDLfzflP8O67755x+Bfg6quv5hvf+AYf+9jHePLJJ0kkEjL/TwghxFkr\nZPjL2TXHAqwmRtaymc gVGUxbDGUsio7fQ6grEDI1gvrclHiJBnRWNYaO6vkq2C4HxnLsHc1Uytbs\nHc3y+L6x0morvpaoOW0F lKli18mQLI03X8xpAJjJZPjFL37Bd77zncq22267DYBNmzZx1VVXsXXr\nVpYvX044HOb222+fq0sVQg gh3rCwqRM2dVpLK5bkig5Zy6kUqB5MFwCFkK6ekTmEJxLQVVY0RVjR\nVJ2AYrseh8Zz7Bv1E0/KK6D8 1yv95IpTS+MlQ3qlhuH0YtfNUVka72wzpwFgJBJhZGSkatumTZsq\n/1YUhW9+85tn+rKEEEKIWacoSi UgLBeoLtgOEzmb/lSe/skCjuehlsrOhAztrMna1VWlsjTeO6dt\ndz2PgVShqlxNz2iWX742zGTBrhwX MTW66sKlWoahSrHr1nhwzoPeWjXnQ8BCCCFErQroGs0xf8h4\nzSKPdMEfMh7KWIxkLFz8YtDBUg/h2R IQlqmKQms8SGs8yNu7qpfGGy0tjTf96/H9Y9VL42n+0njl\nuYXdpaHkzmQIQ5bGO60kABRCCCHOApqq kAgZlTqEruuRtmxSeZuB0nrGjguaCjFTP2MZxqdCURQa\nIiYNEZMNRyyNl8rbfkA4lq0Uu36lP8UvXh uiPMtQU6AjWV3gurveDxRDsjTerJAAUAghhDgLqapC\nPGgQDxq0J0OVgHA4bXFoIs94poCpqsQC+rwa Ro0FdS5oi3NBW7xqe77osG8sV91rOJLl1z2jONMS\nUFpjgUpP4fTgMB6UBJQ3QgJAIYQQYh6YHhB2N4 SZzNv0TuQ4NJHHcUFXIRbQ5+3QadDQWNUcZVVz\ntGp70XE5OJ6rWjO5ZzTLMwcnKDhTCSgNYWMqIJwW IDbI0ngzkgBQCCGEmGcUZWq4eFVzjFTBZjhT\n4MBYnrGcjab6iRdzVWZmNhmaytKGCEtnWBrvcCrPvt GcX8uwlJm8decgGWtqBZRYQK8sh9c9LUN5\nUby2l8aTAFAIIYSYx9Rpcwe76yOkCjZjuSKHxnMMpguo ikI0sDCCwek0VaEjEaIjEeLS7uoElOGM\nxd7RclDoB4i/7hllyytTCShB3U9A6YionNNWqBS77kgE0e dpL+obIQGgEEIIsUBMDwa76sNkCjZD\nGasqGEwG9QUd4CiKQlM0QFM0wMbOuqp947liqZbhVNmal4ZS bNu3v3KMrip0JkN01Yf8sjV1fmC4\npD60oIJoCQCFEEKIBSoS0IkE9Eow2J/K0zOao+gUcSyHhOfV1P y4ZMhgXXuCde1TS+ONDw9gxhvZ\nN5Zl70i2Uux6z3CWR14fqSyNpwBtiWBV4km52HU0MP/Cqfl3xUII IYR4wyIBnWWBKF31EcayFi/s\nHmcoU0RTIRE0zvg6xWeTsKlxbkuMc1tiVdst2+XAeK4qK7lnLMuTB8 YoOlOZyU0R84jMZH/OYV3o\n7E1AkQBQCCGEqCGaqtAYDbC6JUaysZ7eCb9X0PFc4qZOUOrsVZi6yvLG CMsbj14ar28if1Sh65++\nMkC2OJWAkgjqlcLWb+uq4+3T5irONQkAhRBCiBoVNnVWNEXprg8zmC6wby zHULoACsQDBoGzuNj0\nXNJVhc66EJ11IS5f1lDZ7nkeA2mLfaPZSmZyz2iWX+0dIWicXW0pAaAQQghR 43RNpS0Roi0RomA7\nDKctXhvOMJEvEjE1IqaECydDURQWxQIsigV465KpBJSC7WJPq1l4NpCfqBBCCC EqArpGezJEazzI\nSNbi9eEMg+kCpqYSD+o1XTvvzTjbMq8lABRCCCHEUVR1qpzKZL7IwbEcBydyKCjE AroMD89zc/rT\nGx8f59prr2XVqlWsXr2axx9/vGr/I488QiKRYN26daxbt44vfvGLc3SlQgghRO2KBw 3WtMZ51/JG\nzm2JYrseA+kC+WkJD2J+mdMewFtuuYX3vve93HvvvViWRTabPeqYyy67jPvvv38Ork4I IYQQ0wV0\njcV1YTqSIYbSBXYO+sPD8YBkD883cxYATkxM8Oijj3LHHXcAYJompmnO1eUIIYQQ4iQpik JzLEhj\nJMBQusBrpXmCsYBOSALBeWHOAsCenh6ampr4oz/6I1544QUuuugivva1rxGJVNfaefzxx1m7 di1t\nbW185StfYc2aNUeda/PmzWzevBmA/v5++vr6jvm6Q0NDs3sj85C0ga9W26FW7/tItd4OtX7/Zb Xc\nDrN570sDHuOezf6RLIcth2hAwzzLkh6OJT0+etpfo1w0ui+QP+2vdbIUz/O8Ex82+7Zv385b3/pW \nHnvsMTZu3Mgtt9xCPB7nH/7hHyrHTE5Ooqoq0WiUrVu3csstt7B79+7jnnfDhg1s3779mPv7+vpo\n a2ubtfuYj6QNfLXaDuMcO2UAACAASURBVLV630eq9Xao9fsvq+V2OB337roeg+kCOwbTFGyXZFDH\nOM sDwfHhAZKNLaf1NQq2XwLmTBSCPlEcVDZnP5WOjg46OjrYuHEjANdeey3PPvts1THxeJxoNArA\nVVdd RbFYZHh4+IxfqxBCCCFOTFUVFsWDvGNpA2taoqQth+GMhe3OSV+TOI45CwAXLVrE4sWL2bVr\nFwDbtm 3j3HPPrTqmv7+fcgflU089heu6NDQ0HHUuIYQQQpw9NFVhcV2Yy5c1sKIxwkS+yHDGwpFA\n8Kwxp1nA //Zv/8bHP/5xLMti6dKl3H777dx2220AbNq0iXvvvZdvf/vb6LpOKBTinnvuOWsXVRZC\nCCFENUNTWd oYoSMZ4uB4lt1DGQxNJRHU5f18js1pALhu3bqjxqk3bdpU+ffNN9/MzTfffKYvSwgh\nhPj/2bvz+Kiq u3/gnztzZ18yM9mTSQghEJKwEzYFKlILYh+qFhFFbUVfaLU/sW7ts9m6Fas+KNW2\nPlCrtj6K1taCWm ldQKkiu8qiISQBsu+T2Zd77/n9McmQEAKBzJ2ZZL7v18sXmTt35p5zEjPfnPs9\n30OiSM0rMCbNiCyT FhUtbjS7A9DwCpg1FAjGC+0EQgghhJCYMGh4TMuzwOkPobrdgwZnAFoKBOOC\nAkBCCCGExJRZq8KUXA vGpAo41uZGkysAXsHBolPRXsMxQgEgIYQQQuLCpOUx1W6BOyDgpMOLk50+\nKMAhRacCr6BAUE4UABJC CCEkrowaHqWZZhTaDKjv8qGq3QeJSbBoVQlfR3C4ogCQEEIIIQlBq1Ji\nTJoR+VY9Gp1+VLZ6EJJCFA jKgAJAQgghhCQUlVKBfKseOWYtGp1+HG31ICiFYNGooOYpEIwGCgAJ\nIYQQkpB4pQJ5Vj2yzVo0OQM4 2uZBVyAEm04NJeUIDgkFgIQQQghJaLxSAbtVhyyzBic6vTja6oGO\nV8KkpTDmQtE8KiGEEEKGBV4ZLi g9vzAVGpUCLW7aXu5CUQBICCGEkGHFoOExK9+K4nQDOrxBOHwh\nMEaB4PmguVNCCCGEDDsKBYfCNAOy zBocbXWjoSsAk4aHXq2Md9OGBZoBJIQQQsiwpVfzmJJrwewC\nKzgOaHEH4AuJ8W5WwqMAkBBCCCHDnk 2vxkUFNkzLTQHHAc0uCgTPhm4BE0IIIWREUCg4ZJq1yDBp\n0OEN4XCTCy3uACxaqh94uriOhsPhwLJl yzB+/HiUlJRg586dfZ5njOGuu+5CUVERJk2ahP3798ep\npYQQQggZLjiOQ6pBjbmjbZiUbYY3JKLNE4 RAK4Yj4joDuGbNGixevBhvvvkmgsEgvF5vn+ffe+89\nVFZWorKyErt27cKPfvQj7Nq1K06tJYQQQshw olBwyLXokGHSoLbTh2NtHjAANr0KCi65C0nHLQDs\n6urCJ598gpdeegkAoFaroVar+5yzefNm3HTTTe A4DrNnz4bD4UBjYyOys7Pj0GJCCCGEDEcqpQKF\naQbkWrQ43uFDTbsHvJKDRauKd9PiJm4BYE1NDdLT 03HzzTfjyy+/xPTp07F+/XoYDIbIOfX19cjL\ny4s8ttvtqK+v7xcAbtiwARs2bAAANDU1oaGhYcDrtr a2Rrknww+NQViyjkOy9vt0yT4Oyd7/Hsk8\nDsnadxOAcXoR9V1+VLcGoPB1yX7NkBi+9dyg8ct+rcGK WwAoCAL279+PZ599FrNmzcKaNWvw+OOP\n45FHHjnv91q9ejVWr14NACgvL0dOTs5Zzz/X88mAxiAsWc chWft9umQfh2Tvf49kHodk7nshgHZP\nEJ8eOgZBZ4VVp5Jtf+GAIAEAcnJssrz/hYjbIhC73Q673Y5Z s2YBAJYtW9ZvkUdubi5qa2sjj+vq\n6pCbmxvTdhJCCCFkZEo1qDE1NwVj0vRo9wbR5Q/Fu0kxE7cAMC srC3l5eaioqAAAfPjhhygtLe1z\nztKlS/HHP/4RjDF8/vnnSElJofw/QgghhESNUsGhqHt/YZOGR7Mr gJAoxbtZsovrKuBnn30WK1eu\nRDAYRGFhIV588UU8//zzAIDbb78dS5Yswd///ncUFRVBr9fjxRdfjG dzCSGEEDJCGTQ8yvMsaOjy\n40iLG6IUgkWrgko5MusHxjUAnDJlCvbu3dvn2O233x75muM4/OY3v4l1 swghhBCShDguXDYm06RB\no9OPY21edPoEGNQKGNQja++MkdUbQgghhJAh4pUK5Fn1yE3RocMbRGWbB8 3uAFK0PLS8Mt7NiwoK\nAAkhhBBCzkCh4JBm1CDVoEaLK4AjzW64AgHYdGrZVgzHCgWAhBBCCCFnwXHh PYZTDWqc6PSistUD\nlVIBi274FpIemZmNhBBCCCFRxisVGJNmxPwxqbDqVGh2+eEXxHg364JQAEgIIY QQch70ah7T8iyY\nmW9FQGBo9wTBGIt3s84LBYCEEEIIIRcgzajBvEIb7BYtmt3Dq34gBYCEEEIIIRdI pVSgNMuM6XYL\nHP4QHL7QsJgNpACQEEIIIWSIssxazBudCptehRZ3EM4E31aOVgETQgghhESBQcNjqt 2CMf4QKlvD\ntQP1vBJqPvHm2xKvRYQQQgghw5hZq8L0PAsuLrDBqOXR7g3Gu0n90AwgIYQQQogMUnQq lOdZ4PCF\n4A0I8W5OHxQAEkIIIYTIyKJTJVzRaLoFTAghhBCSZCgAJIQQQghJMnENAAsKCjBx4kRMmT IF5eXl\n/Z7fvn07UlJSMGXKFEyZMgUPP/xwHFpJCCGEEDKyxD0HcNu2bUhLSxvw+Xnz5uGdd96JYYsI IYQQ\nQkY2ugVMCCGEEJJk4joDyHEcvvOd74DjONx2221YvXp1v3N27tyJyZMnIycnB0899RTKysr6nb Nh\nwwZs2LABAPDNN9+c8XZyj9bWVqSnp0evE8MQjUFYso5Dsvb7dMk+Dsne/x7JPA7J3PfeRto4HD9+ \nfFDncSyOG9bV19cjNzcXLS0tuOyyy/Dss89i/vz5keedTicUCgWMRiP+/ve/Y82aNaisrBzSNcvL\n y7F3796hNn1YozEIS9ZxSNZ+ny7ZxyHZ+98jmcchmfveW7KOQ1xvAefm5gIAMjIycNVVV2H37t19\nnj ebzTAajQCAJUuWIBQKoa2tLebtJIQQQggZSeIWAHo8HrhcrsjX//znPzFhwoQ+5zQ1NaFngnL3\n7t2Q JAmpqakxbyshhBBCyEgStxzA5uZmXHXVVQAAQRBw/fXXY/HixXj++ecBALfffjvefPNN/O53\nvwPP89 DpdNi0aRM4jhvSdc+UZ5hsaAzCknUckrXfp0v2cUj2/vdI5nFI5r73lqzjENccQEIIIYQQ\nEntUBoYQ QgghJMlQAEgIIYQQkmQSPgCsra3FggULUFpairKyMqxfvx4A0NHRgcsuuwxjx47FZZdd\nhs7OTgAAYw x33XUXioqKMGnSJOzfvx9AeMeRni3lpkyZAq1Wi7/97W9nvObixYthsVjw3e9+t8/x\nlStXori4GBMm TMCqVasQCoVk7Hlf0RoHAHjggQdQVlaGkpIS3HXXXRgoC2Dt2rUoKipCcXEx/vGP\nf0SOr1q1ChkZGf 0W7cgtUcZgoHaM9H77/X7MnDkTkydPRllZGX7+85/L2u/TJco49BBFEVOnTu33\ne0IuidT/c23jKadE GgeHw4Fly5Zh/PjxKCkpwc6dO2XseeL0vaKios/nqdlsxjPPPCNr33tLlHEA\ngKeffhplZWWYMGECrr vuOvj9fhl7HmUswTU0NLB9+/YxxhhzOp1s7Nix7PDhw+z+++9na9euZYwx\ntnbtWvbAAw8wxhh79913 2eLFi5kkSWznzp1s5syZ/d6zvb2dWa1W5vF4znjNDz74gG3ZsoVdccUV\nfY6/++67TJIkJkkSW7FiBf vtb38bza6eVbTG4dNPP2UXXXQREwSBCYLAZs+ezbZt29bveocPH2aT\nJk1ifr+fVVdXs8LCQiYIAmOM sY8//pjt27ePlZWVxaDnpyTKGAzUjpHeb0mSmMvlYowxFgwG2cyZ\nM9nOnTtl6/fpEmUcevzP//wPu+ 666/r9npBLIvV/1KhRrLW1NQa97i+RxuGmm25iGzduZIwxFggE\nWGdnZ9L0vYcgCCwzM5MdP35cxp73 lSjjUFdXxwoKCpjX62WMMXbNNdewF198Uf4BiJKEnwHMzs7G\ntGnTAAAmkwklJSWor6/H5s2b8YMf/A AA8IMf/CAym7d582bcdNNN4DgOs2fPhsPhQGNjY5/3fPPN\nN3H55ZdDr9ef8ZoLFy6EyWTqd3zJkiXg OA4cx2HmzJmoq6uLZlfPKlrjwHEc/H4/gsEgAoEAQqEQ\nMjMz+11v8+bNWLFiBTQaDUaPHo2ioqJInc b58+fDZrPFqOenJMoYDNSOkd5vjuMidTlDoRBCodCQ\nV+Wfj0QZBwCoq6vDu+++i1tvvTVGvU+s/sdT ooxDV1cXPvnkE9xyyy0AALVaDYvFkhR97+3DDz/E\nmDFjMGrUKFn73lsijYMgCPD5fBAEAV6vFzk5OT EahaFL+ACwt+PHj+PAgQOYNWsWmpubkZ2dDQDI\nyspCc3MzgPDuInl5eZHX2O32fh/OmzZtwnXXXXfB 7QiFQvjTn/6ExYsXX/B7DMVQxmHOnDlYsGAB\nsrOzkZ2djUWLFqGkpKTfNQYzjvGUKGPQux2xEO9+i6 KIKVOmICMjA5dddlnM+n26eI/D3XffjSee\neAIKRXx+hca7/z3beE6fPj2yDWc8xHMcampqkJ6ejptv vhlTp07FrbfeCo/HI3OPT4n3z0CPoX6e\nDlU8xyE3Nxf33Xcf8vPzkZ2djZSUFHznO9+RucfRM2wCQL fbje9///t45plnYDab+zzXMys3GI2N\njTh48CAWLVp0wW254447MH/+fMybN++C3+NCDXUcjh07hq+/ /hp1dXWor6/HRx99hB07dsjZ5KhL\nlDE4WzvkkAj9ViqV+OKLL1BXV4fdu3fj0KFD592PoYr3OLzzzj vIyMjA9OnTL6j9QxXv/gPAv/71\nL+zfvx/vvfcefvOb3+CTTz45734MVbzHQRAE7N+/Hz/60Y9w4MAB GAwGPP744xfUl/MV7773CAaD\n2LJlC6655przfm00xHscOjs7sXnzZtTU1KChoQEejwevvPLKBfUlHo ZFABgKhfD9738fK1euxNVX\nXw0AyMzMjNzabWxsREZGBoDw9nK1tbWR19bV1UW2nAOAN954A1dddRVU KhUAYNeuXZFE1i1btpyz\nLQ899BBaW1uxbt26qPVvsKIxDm+99RZmz54No9EIo9GIyy+/HDt37sRbb7 0VGYe9e/eecxzjJVHG\n4EztSIZ+97BYLFiwYAG2bt0qd9f7SIRx+PTTT7FlyxYUFBRgxYoV+Oijj3DD DTckTf973hsYeBtP\nuSXCONjtdtjt9sgs+LJly/osLhjJfe/x3nvvYdq0aWe8bSq3RBiHDz74AKNHj0 Z6ejpUKhWuvvpq\nfPbZZzEchSGKdxLiuUiSxG688Ua2Zs2aPsfvu+++Psme999/P2OMsXfeeadPsueM GTP6vG7WrFns\no48+Oud1t23b1i+5e+PGjWzOnDmRhM9YitY4bNq0iS1cuJCFQiEWDAbZpZdeyrZs2d LveocOHeqT\n9Dp69Og+yb81NTUxXwSSKGMwUDvkkij9bmlpiSS5e71eNnfuXPb222/L2fU+EmUcejvT 7wm5JEr/\n3W43czqdjDHG3G43mzNnDnvvvffk7HofiTIOjDE2d+5c9s033zDGGPv5z3/O7rvvPtn6zV hi9Z0x\nxq699lr2hz/8Qa7uDihRxuHzzz9npaWlzOPxMEmS2E033cR+/etfy9z76En4AHDHjh0MAJs4 cSKb\nPHkymzx5Mnv33XdZW1sbu/TSS1lRURFbuHAha29vZ4yFfzDuuOMOVlhYyCZMmMD27NkTea+amh qW\nk5PDRFE86zXnzp3L0tLSmFarZbm5uWzr1q2MMcaUSiUrLCyMtOOhhx6Sr+OnidY4CILAVq9ezcaP \nH89KSkrYT37ykwGv+eijj7LCwkI2btw49ve//z1yfMWKFSwrK4vxPM9yc3PZ73//e3k73y1RxmCg\n doz0fn/55ZdsypQpbOLEiaysrCymP/+MJc449BbLADBR+l9VVcUmTZrEJk2axEpLS9mjjz4qf+d7\nSZ RxYIyxAwcOsOnTp7OJEyey733ve6yjoyNp+u52u5nNZmMOh0PWPp9JIo3Dgw8+yIqLi1lZWRm7\n4YYb mN/vl7fzUURbwRFCCCGEJJlhkQNICCGEEEKihwJAQgghhJAkQwEgIYQQQkiSoQCQEEIIISTJ\nUABICC GEEJJkKAAkhJAo+cUvfoGnnnoq3s0ghJBzogCQEEIIISTJUABICCFD8Nhjj2HcuHGYO3cu\nKioqAAC/ /vWvUVpaikmTJmHFihVxbiEhhPTHx7sBhBAyXO3btw+bNm3CF198AUEQMG3aNEyfPh2P\nP/44ampqoN Fo4HA44t1MQgjph2YACSHkAu3YsQNXXXUV9Ho9zGYzli5dCgCYNGkSVq5ciVdeeQU8\nT39nE0ISDwWA hBASZe+++y7uvPNO7N+/HzNmzIAgCPFuEiGE9EEBICGEXKD58+fjb3/7G3w+H1wu\nF95++21IkoTa2l osWLAAv/rVr9DV1QW32x3vphJCSB90b4IQQi7QtGnTcO2112Ly5MnIyMjAjBkz\nwHEcbrjhBnR1dYEx hrvuugsWiyXeTSWEkD44xhiLdyMIIYQQQkjs0C1gQgghhJAkQwEgIYQQQkiS\noQCQEEIIISTJUABICC GEEJJkKAAkhBBCCEkyFAASQgghhCQZCgAJIYQQQpIMBYCEEEIIIUmGAkBC\nCCGEkCRDASAhhBBCSJKh AJAQQgghJMlQAEgIIYQQkmQoACSEEEIISTJxDQC3bt2K4uJiFBUV4fHH\nHz/jOW+88QZKS0tRVlaG66 +/PsYtJIQQQggZeTjGGIvHhUVRxLhx4/D+++/DbrdjxowZeO2111Ba\nWho5p7KyEsuXL8dHH30Eq9WK lpYWZGRkxKO5hBBCCCEjBh+vC+/evRtFRUUoLCwEAKxYsQKbN2/u\nEwBu3LgRd955J6xWKwAMKvhLS0 tDQUGBLG0+XSgUgkqlism1kg2NrbxofOVDYysvGl/50NjKK1bj\ne/z4cbS1tZ3zvLgFgPX19cjLy4s8 ttvt2LVrV59zjh49CgC4+OKLIYoifvGLX2Dx4sX93mvDhg3Y\nsGEDAECr1WLLli0ytvyU1tZWpKenx+ RayYbGVl40vvKhsZUXja98aGzlFavxXbp06aDOi1sAOBiC\nIKCyshLbt29HXV0d5s+fj4MHD8JisfQ5 b/Xq1Vi9ejUAoLy8HDk5OTFrYyyvlWxobOVF4ysfGlt5\n0fjKh8ZWXok0vnFbBJKbm4va2trI47q6Ou Tm5vY5x263Y+nSpVCpVBg9ejTGjRuHysrKWDeVEEII\nIWREiVsAOGPGDFRWVqKmpgbBYBCbNm3qN215 5ZVXYvv27QCAtrY2HD16NJIzSAghhBBCLkzcAkCe\n5/Hcc89h0aJFKCkpwfLly1FWVoYHH3wwksO3aN EipKamorS0FAsWLMCTTz6J1NTUeDWZEEIIIWRE\niGsO4JIlS7BkyZI+xx5++OHI1xzHYd26dVi3bl2s m0YIIYQQMmLRTiAk4Tj9IRxsdKKqzQ1BlOLd\nHEIIIWTESehVwCS5iBJDdbsHla0eiIKEyjYP6hx+TM g2I9WgjnfzCCGEkBGDAkCSELp8IXzV6IQn\nKCDNoIYroITFoIE/JOLzEx2wW3QoTjdCq1LGu6mEEELI sEcBIIkrQZRQ3eHFsTYPjGol0g2aPs9r\nVUpk8gq0uQNodgZQkmlEbooOCgUXpxYTQgghwx8FgCRuHL 4QvmpwwhsSkG5QQ8GdOajjOA4WnRqC\nKOFQkwsnO32YkG1Gio62LCKEEEIuBC0CITEniBK+aXbjs5oO cADSDZoBg7/eeKUCGUYNBInh0+Md\nONLsRFCgRSKEEELI+aIZQBJTnd4gvmpwwi9ISDcOPOt3NkYND7 1aibpOPxq6ApiQZUKmSQPuAt6L\nEEIISUYUAJKYCIkSjrV5UN3uRYqWR9oQV/UqOA6pBjWCgoT99V1I N6hRkmmCUUM/0oQQQsi50Kcl\nkV27JzzrFxQlZBrVUZ2pU/MKZBo1cPpD+KS6HcXpBoyy6sErKbuBEE IIGQgFgEQ2IVFCZasbNR0+\nWLQ8zFr5avmZtSoYJIbKNg9qHX5MpNqBhBBCyIAoACSyaHMH8FWjC4IM s34DUSo4pPeqHZibokVx\nhgk6qh1ICCGE9EH3yUhUBQUJhxqd2H3SAQ0fztOL9eIMrUqJTKMG7Z4gPq lqx8lOLySJxbQNhBBC\nSCKjGUASNS0uPw42uiAxICNGs34DOb12YG2nD2XZZliodiAhhBBCASAZuoAg oqLFjTqHDyk6FbR8\n4txy5ZXhRSKeoICdxzswyqZDUaoRap4mvwkhhCQvCgDJkDQ7/TjY5AJjDBnGxK 3FZ1Dz0KuodiAh\nhBACUABILlBAEPFNixv1Dj8sOhU0w2BGjaPagYQQQggACgDJeWKModkVwMFGFziO yZLrxxiDIOOi\nDaodSAghJNlRAEgGzR8S8XWzC43OAKw6lSx5dLUOH375YSUON7mweraAa6fkQCVTYN a7duBJhx8T\ns0xIM2pkuRYhhBCSSCgAJOfEGEOT049DTS4oOCDTFP0gSZAYXjtQj+d3ngCv4DDWpsEz O2rw1qEm\n3PetMZhTYI36NYG+tQN3n+xEDtUOJIQQkgTies9r69atKC4uRlFRER5//PEBz/vLX/4Cju Owd+/e\nGLaOAIAvJOJAXRcONDhh0vCw6KK/u0ZlqwerXv8C63fUYFa+BX++aTr+57I8PPO9MkiM4f/9 7RDu\n2XIYdV2+qF+7h1alREav2oEnOqh2ICGEkJErbjOAoijizjvvxPvvvw+73Y4ZM2Zg6dKlKC0t7X Oe\ny+XC+vXrMWvWrDi1NDkxxtDQ5cfhJheUSg6ZMtwaDQoSXth9Ei/trYNZw2PtkvH49tg0cBwHhx+Y \nO9qGmXkWvPZFPV7YVYvlf9yHG6bbcfOMPFlm6HrXDjzc7EKdg2oHEkIIGZniNgO4e/duFBUVobCw\n EGq1GitWrMDmzZv7nfff//3f+OlPfwqtVhuHViYnb1DAvroufNnohFnLw6KNfgD0ZYMTK1/djxd2\n12 JxcTr+fNN0XDYuvd+CEjWvwA/K8/CXH0zHt8el4w+7a/H9l/fiHxUtYEyeGbqe2oEiY/ispgNH\nmp0I CpIs1yKEEELiIW4zgPX19cjLy4s8ttvt2LVrV59z9u/fj9raWlxxxRV48sknB3yvDRs2YMOG\nDQCApq YmNDQ0yNPo07S2tsbkOrHCGEOrO4iqdi94BWDU8PD4o3sNX0jCC1+0YXOFA+kGHr+8NBcz\ncwyApwMO z6nz3I6OPq9TAbhnugWL8jV4bk8L/vO9CmzadxJ3lqejyCbfHwcaBnxT1YajNUChTR+X\nre3kMNJ+dh MJja28aHzlQ2Mrr0Qb34RdBCJJEu655x689NJL5zx39erVWL16NQCgvLwcOTk5Mrfu\nlFheS07eoIDD TS60ijzsOSmylETZebwTv/ywEk2uAK6ZnI07Ly6AQT3wj6AlLbPfsYvTgNnFo/D2\nkWY892kN7njvJK 6emI3b54yS7VatBeHb1XX+EALiyKkdOFJ+dhMRja28aHzlQ2Mrr0Qa37h9iuXm\n5qK2tjbyuK6uDrm5 uZHHLpcLhw4dwiWXXAIgPLO3dOlSbNmyBeXl5bFu7oglSQz1XT4cbnZBrVTI\nssK3yx/C0x9X452vW1 Bg1WHj8kmYkpNywe+nVHC4ckIWLi1KxcbPT+KNLxvwz4pW3H7RKFw9MRu8\nIvozdKfXDhybZsBoG9UO JIQQMjzFLQCcMWMGKisrUVNTg9zcXGzatAmvvvpq5PmUlBS0tbVFHl9y\nySV46qmnKPiLIk9AwKEmJz q8Idh0qqgHM4wxfFjZhie2V6HLL2DVzDzcMjM/aruGmLUq3HvJGFw5\nMQtPba/CE9uq8NeDjbjvW2NQ nmeJyjXOdE2DxFDV7kFdF9UOJIQQMjzFLQDkeR7PPfccFi1aBFEU\nsWrVKpSVleHBBx9EeXk5li5dGq +mjXiSxFDr8OHrZhc0vAIZMgQwre4AfrWtCtur2lGSYcRzV03A\nuHRj1K8DAGNSDfjt1RPx0bF2PP1J NW7/y0FcNjYNa+aNRpY5+vmBVDuQEELIcBfXRKYlS5ZgyZIl\nfY49/PDDZzx3+/btMWjRyOcOCDjY6I TDF4JNr4767VLGGDYfbsYzn1QjJDKsmTca103NleW2bG8c\nx2Hh2DRcXGDFH/fV4eU9dfikpgM3z8jD jdPtsuxVrFUpoVUpI7UDx2cYkWfRQSFzXwkhhJChGv6Z\n7GRQJInhZPesn45XyjLrV+fw4dEPKrG3rg vT7Sn4r2+PRZ5FF/XrnI1WpcTq2aPwb6WZeGZHDZ7f\neQJvH27GT+aPxrfGpMqygrenduCRZjfVDiSE EDIsUACYBFx+AQebnOjyCbLM+gkSw6YD9fhd9zZu\n/7mwCN+bkAVFHMulZJu1+NUVJdhT68CT26tw3z tfY1a+BfddMgajbfqoX49XKpBhVMMTFPBZTQcK\nbDoUpRll2S+ZEEIIGSoKAEcwUWI40eFFRasHelU4 QIm2Y20ePPz+URxpdmN+oQ0/u7RIltnFCzUj\nz4JXV07DX75qxPM7T2DFK/tx7eQcrJ6dL0spF4Oah1 6lRJ3DjwZnAGWZRmSZtSOidiAhhJCRgwLA\nEcrpD+FggxOuoIhUvQrKKM/6BQUJf9hzEi/u6b+NW6Lh FRyunZKD74xLw+92nsBrB+qxtaIFd15c\ngH8rzYz6TCXHcUg1qBEUJHzR4ITN4UNZlnlE1A4khBAyMt D9qRFGlBiq2tz4tKYDgsSQblBHPfj7\nqnsbt9/vqsWiIhJJTwAAIABJREFUs2zjlmisejX+Y+FY/On6 qbCn6PDI+5X44aYvcLDRKcv11N0r\nrL1BETuqO1DZ6oYg0pZyhBBC4o+mJEaQLl8IBxudcAcFpOqjH/ h5gyJ++9lxvP5FAzJNGvz6yjJc\nVGCL6jViYXyGES8sn4StFa1Yv6MGN7/+Jb5bkoEfzx2NNEP0b5P3 1A6sbvdS7UBCCCEJgQLAEUAQ\nJdR0eHGszQODWol0Q/SDi89PdOKxDwa/jdtQSIyhyy9AHRShV8tTW4 /jOFw+PgPzC214cXct/u9A\nPbZVtePWWflYMSUHqigXxVYqOKQZ1PCHROw62YkcsxbjM6l2ICGEkPig AHCYc/hC+KrBCW9IQJpB\nHfV8tmhv43Yu7oAAT1BEllkDxgEt7gAsWpVsq2kNah4/njsaS8uy8PQn1V i/owZvHWrCfd8qlGV2\nU6tSIkulRIc3RLUDCSGExA0FgMOUIEqo7p71M6n5qM/6yb2N2+kEiaHDG4JZ y2NuYQrcHSKysmxo\ndPrxdYsbzoAAqy76i1l65Ft1ePp7ZfhXTQfWfVyNu/52GPMKbbhnfqEstQwtOh UEieFIsxu1Dh8m\nUO1AQgghMUQB4DDU6Q3iqwYn/IKEdBlm/WK5jRsQnmUMChJKM02R2TA3AIWCQ65F hwyTBse7g121\nUiFroDR3tA2z8i147UADfr/rJJb/aR9umGbHzTPyon47mldw/WoHjkkzQMPTbWFCCC HyogBwGAmJ\nEqravKhu98Cs5aO+YOH0bdzumjsa10+Tbxu3kCihwxdChkGNknwTDAOUSVEpFRibbkSO WYvKNjca\nugIwaXjZ8gNVSgVuKrdjSUkGnv1XDV7cU4t3jjRjzbzRWFQc/dXOkdqBXX7UdwUwIYtqBx JCCJEX\nBYDDRIc3iC8bnAgJEtKN0Z/1q3P48NiHldhT24VpueFt3PKt8mzjxhhDpy8EgMPUHPOggx2D hseU\nXAvyrUF83eSSPT8wzaDGQ4uK8f2J2XhyexX+a2sF/vxVI+6/ZAzGZ0R3RpTjOKTqw7UDD9Q7ke rw\noTTTDJOW/hclhBASffTpkuBCooTKNjeOd/iQouFhjvKsnygxvNZrG7f/WFiEK2Xcxs0viOjyhWC3 \n6DAu3QjtBayCtenVmFMQzg/8Jgb5gZNyzHj5uinYcrgZv/n0OG589QCumpiFOy4qiPrtaDWvQKZJ\n A5dfwL9q2lGUZsBomx58lFclE0IISW4UACawdk841y8kSsgwqKN+S7D3Nm7zCm342YIiZJrkqU8n\nsf AiD7VSgZn51iHXwRsoPzBFy8ty61TBcbhyQhYWFqVhw64TeOOLBrx/tA23zxmF70/KjvptcpOW\nh15S hmsHOvyYmE21AwkhhEQPBYAJKChIONYz66flYdZGd9YvKEh4cU8t/rCnFmYNj19ePh6XjZNv\nGzdPUI A7KKLQZsCYNH1Ua+ydKT/QqFHKVqPQpOVx77fG4KoJWXhqezWe3F6Fvx4M3xYuz7NE9VqR\n2oEC1Q4k hBASXRQAJpg2dwBfNbogiBIyjNGf9fuqwYlHPjiKmg4fLh+fgXu/VSjbqlpRYmj3BWFS\n87iowCbr6t 2e/MBR1iCOxCA/sDDVgN9cPQHbq9rx9CfVuP0vB/HtsWm4e95oZJm1Ub2WllciyxSu\nHfhxVRtKMkyw W3Sy3fImhBAy8lEAmCCCgoSjrW6c6PTColMhJcqzft6giN99dhybvmhAhkmD9d8r\nw8Wj5dvGzekPwS 9IKE43YpRNH7NgxdqdH9jk8uPrZnnzAzmOw4KiNMwpsOKVffV4cU8tdtR04Ifl\ndtxYboc2yuVcTq8d WJZlglUf/a3rCCGEjHwUACaAFpcfBxtdEBlDplET9Vm/nm3cGl0BLJd5Gzeh\nu7SLTa/CjHwrjAOUdp GTQsEhJ0WHdGNs8gO1vBK3zsrHd0sysH5HDf7385PYcrgZP/lWIRaMSY3q\nNXtqB3qDInYe76TagYQQ Qi4IBYBxFBBEVLSEZ3OsOnXUd9no8ofwzCc1ePtIM0ZZdfj9NZMwJVe+\nbdwcviBECZiYZUauJf517H ryA3NTtDjaKn9+YJZZi7VXlOD7tQ489XEVHnjna8zMs+DeSwoxJtUQ\n1Wvp1UroVAqqHUgIIeSCUAAY J81OPw42ucBkmPVjjOHDY214clsVHL6Q7Nu4BQQJDl8I2WZNQi5S\n0Ktjmx9YnmfBK9dPw18PNuL5z0 7g+lf2Y/nkHKyePSqqdf16ageGRKodSAgh5PzEtbjY1q1bUVxc\njKKiIjz++OP9nl+3bh1KS0sxadIk LFy4ECdOnIhDK6PLHxLxRb0D++q6YFApYdNHd6FHmyeIB975\nGj979xukGzX443VTccdFBbIEf4wxtH uC8IVETLenYEpuSsIFf7315AdOzjHDGxLR7glClJgs1+IV\nHJZPzsFff1iOKydkYdMXDbjq5T3426Gm qF9TpQzXDvQFJfyrph2VrW4IohTVaxBCCBlZ4hYAiqKI\nO++8E++99x6OHDmC1157DUeOHOlzztSpU7 F371589dVXWLZsGR544IE4tXboGGNocvqxo7oDbZ4g\nMk2aqM5AMcbwt0NNWPbyXnx2vBN3zR2Nl1ZM QXGUd6zo4QuJaPEEYbdoMa8wFZnD5PZjT37g/DGp\nGJ2qR4c3CIcvBMbkCQQtOhX+feFY/On6qSiw6v HoB5X44aYv8FWDM+rXMnVvD1jd7sWO6g60uPxR\nvwYhhJCRIW4B4O7du1FUVITCwkKo1WqsWLECmzdv 7nPOggULoNfrAQCzZ89GXV1dPJo6ZOFZvy7s\nr+uCUa2EVRfdlZt1XT7c8deDePSDSoxLN+K1G6bhpn K7LHv4ihJDqycAUWKYM8qK0iyzbLdS5dST\nHzh/TCpSDSq0uIPwBAXZrjc+w4iN10zCo4uL0e4NYtUb X+LBf1SgzROM6nUUXLh2oJrnsLe2C/tr\nHfDK2C9CCCHDU9ySherr65GXlxd5bLfbsWvXrgHPf+GFF3 D55Zef8bkNGzZgw4YNAICmpiY0NDRE\nt7EDaG1tPevzPbdIq9q9UHCAUcPDGwC8Ubq+KDG89Y0DL37Z BqWCw90zM7BkbAoUohOOtujPMPmC\nIvyChDyLDjlGLXyONvgcUb8MgHOPbTRlcIBOG0J1uxctQREmDQ 9eKc9s5uw0YPIV+XjtcAf+fKQV\n2ypbccPEVFw13gJ1lLd70wCodQqoqWUosOmRadJEtviL5fgmGxpb edH4yofGVl6JNr7DIlv8lVde\nwd69e/Hxxx+f8fnVq1dj9erVAIDy8nLk5OTErG0DXcsXEnGkyYVmkU d2dkpUd78Awtu4PfJhJQ43\nuzBvtA0/u1S+bdx6SrukWlWYkBW7RQax/D4CwNgChmaXH0ea3RAlBotM 9QMtAO7Jzsbych/WfVKN\njQfa8I8aD+75ViHmRrk2owWAIDG0eEPwBZR9agfGenyTCY2tvGh85UNjK6 9EGt+4BYC5ubmora2N\nPK6rq0Nubm6/8z744AM89thj+Pjjj6HRJP5eqIwxNHT5cbjJBaWCQ2aU9289 fRu3xy4vxnfGpcuW\nf+fwhRCSJJRlmWBP0UExgnefUCg4ZKfokNZdP7CqzQOVjPUD7RYd1i0tw2fHO/ A/H1fj7s2HMXe0\nDffML0S+VRe16/SpHXiiE6MsOugFCYyxYZG3SQghJPriFgDOmDEDlZWVqKmpQW5u LjZt2oRXX321\nzzkHDhzAbbfdhq1btyIjIyNOLR08b1DoLjMSRKpeBT7Ks34HG5145P1KVHd4Zd/GLS iEZ/2yTBqU\nZBqhl6l2XiLqVz/QGYBRLV/9wIsKbJiRZ8HrXzRg466TWP6nfVg5LRerZuZF9Zo9tQPr nX4427pw\n1KeGUa2EUc3DpOFh0PDQ8gpoeAXUSsWIDvYJISTZxe1Tned5PPfcc1i0aBFEUcSqVatQVl aGBx98\nEOXl5Vi6dCnuv/9+uN1uXHPNNQCA/Px8bNmyJV5NHhBjDPUOPw43u8AruKjfio3lNm6MMXT4 QlBw\nHKbbU5Bpiv7OJMNFLOsHqpQK3DDdjsXjM/CbT4/j5b11ePfrFtw1dzQuHx+9Gd6e2oFKPQ+zTo WQ\nyODwhdDiDkDsXgnNWHgxiV6thFHDw6QJB4ma7uBQwytpH2JCCBnmOCZX/Ys4KS8vx969e2NyrYaG \nBqSkZuBIswttniBsuujP+n1+ohO//LASDc4ArpmcjR/LuI2bPySiyy8g36rD2PT4bi/W0NCQULkS\n knQqP1CQmGz7C/c41OjEE9urcKTZjUnZZjywYAzGR7Gkj6OtGZa0zAGfZ4xBkBgCgoSQKEHoKSvI\nAW AMGpUyHBhqeJjUPHRqJTTKcIAY7f8HhptE+9kdaWh85UNjK69Yje9g46Dkua8XZYwxNLn8OOhs\nh0qp QEaUc/1iuY2bxBg6vCGoeQVmjbIi1RDdMjUjQe/8wBOdXhxrlTc/cEK2GS+tmIJ3jjTjuU+P\n48ZXD+ DKCVm446JRkUUccuI4DiolN+DiJUGU4AtK6PL5IUgSGEN3cMhBreS6Zw55mLRKaHklNLwy\nfGt5GJYM IoSQkYgCwAvkCgg41ubFKLs16vX2PqxswxPbjsHhC+HmGXm4dZZ827i5AwK8IRFj0gwo\ntOmTfvbmXF RKBYrSjMgxy58fqOA4LC3LwqVFadi46yQ2fdGADyrbcNucfCyblCNLncfB4pUK8EpA\nj/6zxILEEBQl NLr8OOlgiNxiYAxKBQeDOnxb2aRVwaBWRm4tq5WKpE03IISQWKMA8AIxBig5RPVD\nuM0TxK8+OoZtVe 0Yn2HEr6+cINtOHoIUnvUza5S4qMCGFJkWk4xUffIDm92y5gcaNTx+Mr8QV07I\nwlPbq/DU9mr89WAT 7r9kDGbkWaJ+vaHiFRx4hfKM2wJKLBwctntCaHQGIIGBsfCMI8eh36KUSN4h\nLUohhJCoGlQA+Oyzz+ KGG26A1WqVuz1JiTGGLUea8cwnNQgKEv7f3AKsnCbPTh5A+PZyUJBQkmlC\nvmVkl3aRm1WvxpxR1kh+ oDMgyJYfONqmx3NXTcDH1R14+uNq/OgvB3FpUSrunleInBRt1K8nBwXH\nQcsrcaZSkowxBM+wKKWHjl fCpOFh1PAwa2lRCiGEDMWgAsDm5mbMmDED06ZNw6pVq7Bo0SK6VRMl\ndV0+/PKDY9hd68C0XDP+69vj oloDrreQKKHDG0K6UY3SfBMMGpoAjoZY5gdyHIdLxqRizigrXtlf\nhxd31+LTmn24qdyOH5TboT3DrN twwXEcNDx3xnSHnkUp7qCATl8IgsQgMYAbYFGKVnXq1nK0i7AT\nQshIMKgI4NFHH8UjjzyCf/7zn3jx xRfx4x//GMuXL8ctt9yCMWPGyN3GEUmUGDZ90YDffnYcvILD\nv19ahKsmZkW26oomxhgc/hAYAybnmJ GToqUAXga98wMr2zyo7/LLlh+o4RW4ZWY+rijJxPod1di4\n6yTePtKMu+ePxsKitBH3/b3gRSkAeIUi Us7GrOGhU51alKJSciNurAghZDAG/cnEcRyysrKQlZUF\nnufR2dmJZcuW4bLLLsMTTzwhZxtHnGNtHj zyfmy2cfMLIhy+EOwWHYrTjcN6hmi40Kt5TM5JQb5F\nh69b5M0PzDJpsHZJCZZNcuCp7dX42bvfoNye gvsuGYOiNEPUr5eozrYoRZQYQqKEFpeAOoe/z6IU\nhYLrzjkML0rR95o51PC0KIUQMnINKgBcv349/v jHPyItLQ233nornnzySahUKkiShLFjx1IAOEg9\n27i9uKcWRo1S1m3cJMbQ6Q2BVyowM9+K9CiXqSHn ZtWrMTs/NvmB0+0W/On6qXjrYCN+99kJrPy/\n/Vg2OQe3zc6HWZvcC3yUCg5KhfKMf/ycaVFKOEIML0 rpKYadQotSCCEjzKACwI6ODvz1r3/FqFGj\n+hxXKBR45513ZGnYSNN3G7d03PutMbJt4+YNinAFBIxO 1aMozUA5UHHUOz/wZKcXla0e8AoOFp0q\n6oE/r+BwzeQcXDYuHf+78wT+/GUD/lHRgjsvKsDSsixaKH EG51qUEhIZnL4Q2t0BiAzoKWrDAdD2\nWpRi6lmUolRAlBgGqq9PM4qEkERx1gCwo6MDALBmzZo+j3vY bDaUlJTI1LSRwRcS8dvPjmPTgfA2\nbs98rwxzZdrGTZQYOnxBGNQ8Lhptky3AJOdPpVRgTJoR2THID7 ToVPhpd07pU9ur8NiHx/CXg024\n75JCTMmRp5j4SMRxHNQ8N+Ct+5AoRRalhCQJPUmHnnYHDrvD31cO HAbaa+mMsSAXSV08/XCkTQM+\nN0AfBnqSG/A1g7jWGd9v4OCW4y6k7We+lqfDDUHrhVHLR27ZU2BNyP k766fP9OnTwXHcGf+a5TgO\n1dXVsjVsJNh1shOPfdC9jdukbNx5cQGMMq28dfkFeAUR49ONGGXT02xP goplfuC4dCP+d9kkvH+0\nDet3VOPWN77C5eMzcNfcAtCfBkOnUp55hbHKx8NiGHzKxdl24zzbPp1n28 RzwKeifK2zvqbXs4yd\n9iYX0Pael7v8Ar5ucYfPYwCv5GDTqWAzqGHS8NCrldBSUEjIOZ01GqmpqRnw uRG2hXBUOf0hPN29\njVu+VYeN10zCVJm2cRNECe2+EFL1KpTnW2QLMEl09c4P/LrFI1t+IMdx+E5xOu YV2vDSnlr8aV8d\ntle1YVqWDmMyvMi36jDKqkO+RQebPvq3pcm5nW3Mz/rduKBv1fD//gbVSlh6bVcp dpcHavMEITEG\ncICS42DVq2DTqWHW9gSFSsrbJKSXQUULDz74IB5++OHIY0mScOONN+L//u//ZGvYcB XLbdwc/hBE\nkWFSVri0C/1yG15imR+oUynxo4sK8G9lmdj4+UkcbHBgV309BOnUH3IGtTISDOZ3/zvK qkOeRUd/\nWJCE1bO9YO8tzCXG4AtKqPJ6IHb/iCs4IEWrgk2vQopWBb1aCb2KgkKSvAb1W722thZr16 7Fv//7\nvyMQCGD58uWYOnWq3G0bVto8Qfxq2zFsO9aO4nSDrNu4BQQJnb4Qsk0alGSZzrjlFhk+eucH Hmvz\noE7G/EB7ig4PLSqGo60ZRlsGmlx+nOz04WSnDycc4X+/bHDiHxWtfW7FpepVkaAw36rDqO5/7S k6\nWW5fEzIUCo4LB3jqU78bJcYQECSc6PBCYOG7WAoOMGlUsBlUsOrU0KvCr6EUGpIMBvUJ84c//AEr \nV67E2rVrsW3bNixZsgR333233G0bFk7fxu3HFxfghunybOPGWHj/XqWCQ7k9BRkmDd2yG0H0ah6T\n clKQb9XjSLNL1vxAILxq2J4SDuIuKuj7nF8QUefwo9bhw4lOH052B4c7ajrQcTgUOU/BAdkmbTg4\nPG 3WMMukoQ9SkjAUHAedqu8e1YwxBEQJ9Q4/jnd4AXAAYzBpedh0alj1p2YKeaqmQEaYswaA+/fv\nj3y9 Zs0a3Hbbbbj44osxf/587N+/H9OmTZO9gYms2R3CE28dwu6T4W3c/vPbYzHKqpflWr6QCGdA\nQIFVh6 I0I826jGAWnSom+YFno+WVKEoznLGYtMsvhAPC7qCwJ0D8ssEJb0iMnKdScshL0fWdOaR8\nQ5JAuEgZ oL5BYVBkaHT5caLTF06bZIBBo4RNr4JVp4JBHc4rpBJbZDg7awB477339nlstVpx5MgR\n3HvvveA4Dh 999JGsjUtUosTwm0+P4+EP6sErFfjZpUW4WqZt3CTG0O4NQscrMXuUFTa9+twvIsPe\nmfIDVUoOKdr4 B04mLY+yLBPKskx9jjPG0O4NhW8p98wcdvpwotOLf9V0UL4hGRYG2pM6KEhocQXC\nu8l0LzbR8uGg0K Y/FRRqeErJIcPDWX/Tbtu2LVbtGFYauvz45YeVKEvX4pErJsq2jZs7IMAbElGU\nZsBom55uQSShM+UH GlTKhAySOI5DmkGNNIMa0+x9V70LEqN8QzKsqXlFv5+/kCihwxNCo9OPnr9v\nNEoFrAY1UnWqSK1C2o KTJKJBfYo0NzfjP/7jP9DQ0ID33nsPR44cwc6dO3HLLbfI3b6ElGfV4ZM7\nLkL1yVpZgj9BCs/6WXQq XGxPSfqtvEj//MBmVwBWnXz5gdF2tnzDgCChrqvv7WTKNyTDQU8tSFOv\nj1JBlOD0hdDiCkSCQhXVKi QJaFAB4A9/+EPcfPPNeOyxxwAA48aNw7XXXjvkAHDr1q1Ys2YNRFHE\nrbfeip/97Gd9ng8EArjpppuw b98+pKam4vXXX0dBQcGQrhktY9IMqKmN/v+8ju5dBcoyTciz6KhE\nAenDolNhzigrml0B2fcXjhUNr8 CYVAPGpA4u37CW8g1JAuOVChiVCvTefl0YZK1CnUpJP6skZgYV\nALa1tWH58uVYu3Zt+EU8D6VyaFPa oijizjvvxPvvvw+73Y4ZM2Zg6dKlKC0tjZzzwgsvwGq14tix\nY9i0aRN++tOf4vXXXx/SdRNVUJDQ6Q 8hw6hBaaYRehlKgJCRgeM4ZJm1SDWow/mBbR6oFImRHxht\nlG9IRgJewYE/rVahKJ25VqFFGy5Lk6JV Qd+9apkmAogcBvXbz2AwoL29PfLh8vnnnyMlZWg7W+ze\nvRtFRUUoLCwEAKxYsQKbN2/uEwBu3rwZv/ jFLwAAy5Ytw49//GMwxkbUhxxjDJ2+EAAOU3PMyDJr\nR1T/iHyGU35gtJ1vvmFtpw9fNVK+IUkcSsXA tQqPt4drFQKAAuE/hGx6NSw6FdUqJFEzqE+KdevW\nYenSpaiqqsLFF1+M1tZWvPnmm0O6cH19PfLy8i KP7XY7du3aNeA5PM8jJSUF7e3tSEtL63Pehg0b\nsGHDBgBAU1MTGhoahtS2wXAHBPicnXC0XXh+XlCQ 4AoKyDRqUGDTg3lCaPREsZHDWGtra7ybMKyk\nAdBoBdR0eNHiF2DS8FApB/6AcDs6Yte4ODACKDUCpU YeyDMBCM8gBkUJDa4Q6pxB1PX86wzh4yoP\nHP5Tt5QVHJBhUMFuUsFuVsNuVsFuUsNuViNdz5/1w3ek j228JcP4csCp/boZ4HBJaBElCFJ4h2WO\nAXqNEmaNCmYtD61KAS0/9KCQfu/KK9HGd1AB4LRp0/Dxxx +joqICjDEUFxdDpUqchQmrV6/G6tWr\nAQDl5eXIycmR/ZpdvhB0jU5Y0jLP+7USY+j0hqBVKjAzx4xU A5V2OZNYfB9HmnEFLJIfGBKls+YH\nXsjP7kiQkQlMOcPxgfIN/1nt6pNvqFaGF7QMlG8IJO/Yxkqyj2 9PrUK/IKJBZGAiolarkH7vyiuR\nxndQAaDX68W6detw4sQJbNy4EZWVlaioqMB3v/vdC75wbm4uamtr I4/r6uqQm5t7xnPsdjsEQUBX\nVxdSU1Mv+JqJwBMU4A6KKLQZMCZNT4VESVQlU35gtEUr3zBdp4RaVQ 9w4d0nOAAcB3DgwHHh2UWA\ng4LrOR7+vnEIn4/uY31ee9r7KDic4Tyu7/tx4duHPd93xWnv0/O6QbXz tPfvqXna8z6R9+9+bf92\nnvl9TvX7tOO93ifSzu7rmpgPU1PEpC6tcj61CnWRWoVqGDThsjSU3kCAQQ aAN998M6ZPn46dO3cC\nCAdm11xzzZACwBkzZqCyshI1NTXIzc3Fpk2b8Oqrr/Y5Z+nSpXj55ZcxZ84c vPnmm7j00kuH7YdY\nT2mXFA2PiwtsSNElzgwqGXl68gNzUnSobHUnVX5gtJ0t31CUwjtGnOxVvqa+ww mlShPONWThGX8G\ngHXvPxv5GgwSO3Vc7D7GGOt+PvxaAN3n9X9tn/cHTr028l6AhPCLJNbrnO736Xl/ dno70fd9el7b\n+33iScHVYpRVh+J0I8alG1GcYUBxuhGWJP+9OlCtwnZPCA1Of+RnUqNShsvS6FUwaq iAdbIa1KdB\nVVUVXn/9dbz22msAAL1eH/7rYigX5nk899xzWLRoEURRxKpVq1BWVoYHH3wQ5eXlWLp0 KW655Rbc\neOONKCoqgs1mw6ZNm4Z0zXhx+kPwCxJKMozIt+opeZfEjE6l7Fc/MNk/JKNJ2bu+YfcxR1 tzUtyi\n7Akkpe6osefr04PHnq+l7q+B7mDztIC0530igWrv13a/UJAYKmqbUOfnUdHqxoEGJ7ZWnMqr yjSq\nMS7DiPHpRoxLDweF2ebk3jN9oFqFDl8ITa5A+HvCAWoFB3hd4Aw+2AxqCgiTwKACQLVaDZ/PF/ mf\nqKqqChrN0AsgL1myBEuWLOlz7OGHH458rdVq8ec//3nI14mXkCihwxtCmkGNmfkmGGj2hcTJ6fUD \nO70CJG8QaqUCGl5BqQjkvPW+fQvELsBKg7FPgO3whXC01Y2KVk/43xYPPq3piBRhNmt4jEs39Jkp\n LLDpwSfxH+ID1Sps7RTxZaMTAJBu0CDPooNVr6LfDyPUoCKShx56CIsXL0ZtbS1WrlyJTz/9FC+9\n9J LMTRveHL4gJAZMzjEjJ4VKu5D468kPTDOoUaHwQG8xoMsvwOkPweELgXEcwBgUXHjWQKMM306S\nY49r QqLFolNhZr4VM/OtkWP+kIhj7V5UtLhR0erG0VYP/nKwEQFBAhBeyFOUZui+hRz+d2y6Abok\nzivkFR x0aiUsBg0YY3AHBOyr64KCA7JMGuSmaGHVq+kO1ggyqADw5ZdfxhVXXIFly5ahsLAQ69ev\n71eKhYT5 BREOXwi5KVqMzzAldaIySUy8UgGrToWcXjtviBJDQBDhFyT4giKcfgFdAQEOXyhcpLY7\noZznOKj5cH BIe1OTRKVVKTEhy4QJvRb0CBLDyU5vn5nCj4614a1DTQDCc5j53XmFPTOFxekGWPXJ\nV6WB4zgYNTyM mvDt9w5vEA1OP5QKBewpGmSZtbBoVVSgepgbVAB4yy23YMeOHXj//fdRVVWFqVOn\nYv78+VizZo3c7R s2GGPo8IbAKxWYkWdBhkkb7yYRMmjhorQ89GoAeqBnPX643IQEf0iCX5DgCoTg\n9IWDw4C6gwaXAAAg AElEQVRPCBckQ/hWYM+MoVrJ0Yw3STi8gkNhqgGFqQZcPj4DQPjnu9kd7DNT\neLDRiX8ePZVXmGFUn5 opzAj/m5tEBfsVHAezVgUzuhc9OQM40emDSqmI7MNt1vJJMx4jyaACwAUL\nFmD+/PnYs2cPtm3bhuef fx6HDx+mALCbNyjCFRBQkKpDUaqRltiTESNcbiK8QjAFQKbpVNKQIIaD\nQn9IhDcoossfgjMgoN0rgI EBLFzKg1eEy1WolQq6fUQSCsdxyDJpkGXS4FtjTpUY6/KHUNnqwTfd\nM4UVrW58drwjsmWbUa3sk1NY nG7EaJtuxM+KKxVcZBGZIDHUdnpR3e6FVqVAvkWLDKMWRg3tZzxc\nDCoAXLhwITweD+bMmYN58+Zhz5 49yMjIkLttCU9iQKsnAL2Kx5wCa1LeKiDJ61Qied9fI6x7O6ue\n4LDLH4IrIMDpExCUJPQsGFAAkcBQ RbOGJIGkaFUoz7OgPM8SOeYXRFS1eSMzhRUtbrx1sAn+7rxC\nlZLDmFQDinvNFI5LM/bZ6m0k4RVc5D MvJEqobvfiaKsHBjWPfKsO6QY1LXxMcIP67kyaNAn79u3D\noUOHkJKSAovFgjlz5kCn08ndvoSm4DiM TTOgwGagmQ1CunEcB61KGc5/1amQZT6VDhGK3E4W4QmK\n6PKFZw2d3hBYd2DIgdEiFJJwtLyyX6FwUW KodfjwTcupVcgfV7dj8+FmAOE/dfKsOhSnhYPCnlvJ\nI233J5VSAVt3MBgQJFS0uPA1A8xaHqMseqQa 1Um9wCZRDSoAfPrppwEALpcLL730Em6++WY0NTUh\nEAjI2rhEZtLwmGZPweg0Y7ybQsiw0bsmWXqv45 IU3taKFqGQ4USp4FBg06PApsfi8eFjjDG0uIOR\n0jQVLW4cbnbh/cq2yOvSDOo+M4Xj043ISdGOiD92 NLwCGj6cKuIPiTjc7ILUxGDTq5Fv0VKNwQQy\nqADwueeew44dO7Bv3z4UFBRg1apVmDdvntxtS2gKRf 9teAghF0ZxgYtQWPeeFAqOg1p5Kjik28kk\nXjiOQ6ZJg0yTBvMKT+UVuvwCKnrXK2x14/MTnZG8QoNa GSlJ0zNTWJg6vLcLjdwJQDhXnmoMJpZB\nBYB+vx/33HMPpk+fDp6ne/qEkNg41yKUnlxDb1CAMyCgyy eg3RcCkxBeocw4qJQc1N23k5O5+C+J\nL5OW75dXGBAkVLd7IjOFFa0ebD7cBF/oVF5hoU0fWXAyvrte oUE9/D6H9Wol9GplpMbg/voucACy\nzRrkmKnGYDwM6qfovvvuk7sdhBByXvju28AGDfrkVJ2+CMXpF+ DsnjmkRSgkkWh4BUoyTSjJ7J9X\n2Huxyb9qOvD2kebIOXkWbZ8i1sUZRqQNk7zC02sMtnuCqO8KdG+r qEG2WYsUqjEYE8PvzwhCCDmL\n/otQTj13votQVFS6hsRY77zCRcXhY4wxtHmCqGj14JsWN462uvF1ix sf9MorTNWrIsFgcffWd3ZL\nYucVUo3B+KIAkBCSNM5nEYozEP5PECWA4wAwKDmO9k8mMcdxHNKNGqQb NZg72hY57g4I4VnCVjcq\nWsIzhrv21UHs3gjZoFZibJohUsS6ON2IQps+IWvVUo3B2KMAkBCS9AZahA IAQSE8Y+gPSXAHwgtQ\nnL7w/sno3j+Z67UIhbF49YIkG2N3NYpp9pTIsaAgobrDG5kprGj14J0jLXjj y0YA3Tui2PSRFcg9\nt5JPr+cZT6fXGKyiGoOyoBEkhJCzUPPhBSRmLZDRaxGKKDH4Q92zhiEBXf7wIp SugADRE+gOBMO7\noYR3RgnP5DCg++vu4+g9o9ETPfY6xlj3uYjsrsIixzn0jTd7PWJc91Z9iFy7R89X HNf7617Pc6fO\n43pujfdqUvh1XL/3QO/jp71Pz8nnujYZGjWvwPgMI8ZnnCpRJjGGOoe/z0zhZ8f/f3 t3Hh9VfS5+\n/DNL9n1fICTsZF8AWQIhihALNEIpRWVXRFHsry7c4q39kaq8LhasXm2lRisB11KtqEHL oiIgVAkI\nKkSIhYASyB6yJ5OZ7/1jkiGBBNkmM2Se91+ZM2fO+Z4nh+HJc75Lx36FvXxcGeTrxJQEPa lRfnYz\nzZKTTktAuzkGj5bUkq+UZY7BQE9ny0hjcXkkARRCiCug02rwcNHj4QLgTO/W7aecGwgLC7ak Ykqp\ndj9jmbrG/PO5fS7c1vW+HfZp+2zr67afO9vXpEytnwFT2/sKTKh221uPZzr3s8mkLMc3tZ1Hqf M+\nd+54qrXlJpP5s9D6fvuf1bljWqqmmnYXyoUJrALqGlow1DaZ+3rqtbjqZU7In6LVaOjj50YfPzcm \nDDrX+aGs7tw6yEdK69h3spJPTxzGz82JWwYHMTkmhMFBHnaToJvnGDQng53NMRjg4WKXj7ftlSSA\n QghxDWk0mvNGMNrHf572rvMk+MLk+dSpJnwC/ahraqGiwUBlg4GmRgPmOCuctOakUFaR+WmBHs4E\n9v UntbVfYVnJGQ7XOpF7uJi3vznNmweKGBDozpToEG4ZEmxXI43bzzFY19wicwxeAUkAhRBC2Fxb\nlalj znZhAufqpCPAw5kAD2f6tG4zGE00GIzUNxupajRQ1dBCZb0BE1gelUu18KfptRrS+gWQ1i+A\ns40Gth wpJfdwCc/uPM7zu44zKsqfKdHBjO0XYFcLIXg46/Fw1lvmGNz3YxVajYYwbxd6+bjh6+Yk\no/k7IQmg EEKI61rb6G5v13NrTyulaDAYaWgdvFPROnCnqdHQurKgeZJwV715VLe9POa0Fz6uTsxI\nDGdGYjjHK+ rJPVzMh/kl7DpegZeLnomDApkSE0JcqJfdxO7cHIN6mWPwEkgCKIQQosfRaM6N7A7w\ncCaydbvBaKK+ 2UiDwVwtrKw3UNGuWqjVmJf5lGrhOX393XlgTF/uGx3F3h+qyD1cTG5+Ce98c4ZI\nPzcmRwczKTqE0H aDpGytqzkGnXVaesscg4AkgEIIIRyIk06Lj5sWH7dz1cK2eSAbDCZqmlqobDBQ\nWd9MU4PBMqbZSafB 1cmx15rWaTWMjPRjZKQftU0tbCsoY1N+MS/sPsGa3ScY3seXKdEh3DggADc7\nGpnbYY5Bo4mTncwx6O XqeOmQTa64oqKCmTNnUlhYSFRUFBs2bMDPz6/DPgcOHGDx4sVUV1ej0+n4\n3e9+x8yZM23RXCGEED1Y +3kgAzyciWrd3txian2MbGxNCs9VC5UyTwzuqNVCTxc9U+NCmRoXyo9V\nDWzKL2FTfjH/f/MR3D/RMX 5gIFNigknu5WNXg3H0Oi3+XcwxGOnnRpCnM+7X4VrLV8ImV7ly5UrG\njx/PsmXLWLlyJStXruSpp57q sI+7uzvr169n4MCBFBUVMXToUDIyMvD19e3iqEIIIcS10zYHZGfV\nwvpmI7XNrYlhXTPNRkPrpzQ468 2JoaNUC3v7unHPqEjuHtmHr06dJfdwCR8XlPHB4WJ6ebsyKTqY\nyTHB9PZxs3VTOzh/jsEjJbUcLnac OQZtkgC+9957bN++HYB58+aRnp5+QQI4aNAgy8/h4eEEBwdT\nWloqCaAQQgibOVct1BMIF1QL6w1Gqu rN09NU1BswYh7LrMU8j52rkw59Dx2EoNVoGNrbl6G9ffmv\nG/vz6ffl5OYX8/IXJ3npi5Mk9/JmcnQI Nw8MtKuVR6DjHIMN7eYYDPBwJsKnZ84xaJPfQHFxMWFh\nYQCEhoZSXFx80f2//PJLmpub6d+/f6fvZ2 dnk52dDcCZM2coKiq6tg3uQmlpabecxxFJbK1L4ms9\nElvruh7i6wP4uIByVjS2mGhqTQ7P1ho409hC i7F1dkONBr0OnHVanLVam08ZWVtVcU2PNzoIRgcF\nU1Lnx7bj1Wz5TzVPbitg1affkxrhycR+3iSHut vlFC16AAWlNUZO/mhCA/i5OxHS2l/wSpJ4e7t3\nrZYA3nzzzZw5c+aC7StWrOjwWqPRXLREfvr0aebM mcO6devQajvPvhctWsSiRYsAGDZsGOHh4VfR\n8svTnedyNBJb65L4Wo/E1rqu9/g2t5ioNxipbzYvH1 jR0ExtUwuqNQPUgnnAib77q4W+gSFWOCYM\nioTF4xTfnqkh93AxW46W8UlhDcGezkwaEsyUmBCi/N2v +bmvFaUUdc1GThqMaFuufI5Be7p3rZYA\nbtu2rcv3QkJCOH36NGFhYZw+fZrg4OBO96uurmby5MmsWL GCkSNHWqupQgghRLdp61vo6+ZEuI95\nm8mkLANOqhtbqGqdt7DZaLKssWyet1CHs+7ihRN7pdFoiA/z Jj7Mm4fG9WfnsXI+OFzMq/t+JCfv\nR2JDvJgSE8zEwUH4uDrZurkddDXHoF6noZf39TnHoE0eAWdmZr Ju3TqWLVvGunXruPXWWy/Yp7m5\nmWnTpjF37lx++ctf2qCVQgghRPfQWtaW1hPoeW4+vc6qheX1BhQa lAK9tq3/2vXVt9BFr+XmQUHc\nPCiIsrpm/vVdCbn5xTz16X/4045jpPULYEp0MKMi/exuhHVPmWPQJg ngsmXL+NWvfsXf/vY3IiMj\n2bBhAwB5eXn89a9/5eWXX2bDhg3s2LGD8vJycnJyAMjJySEpKckWTRZC CCG63cWqhfUGIzXtqoVN\nRpNlKT1nnfa6qRYGejgze2hvZqX04khpHZsOF/PREfNIYn93J24ZHMyUmG AGBXnauqkX6HyOwTpc\nnXRE+roR5Olit3MMalTbCtw9xLBhw8jLy+uWcxUVFdnV8/yeRGJrXRJf65HY WpfEt2tNrZNZ1zeb\nJ7OuajBQ29SCSZkfYeo0rSOR9bpO+61VlRVbpQ/glWgxmvi8sJLc/GJ2Hqugxa QYFOjB5JgQfjYk\nyDKXn70yGE1UN7VgVODhpCPSzw1VW0FUn95WP/el5kH2mZYKIYQQ4rK46HW46HWt 1ULznHvGdn0L\naxpbVzlpMNBiUoC5/uOiMz9Cxo7KQXqdlnH9AxjXP4CqBgObj5SyKb+YZ3Yc47mdxx gd5c+UmBDG\n9vW3y+lZzp9j8HBxDfqGOqL62Lhh7UgCKIQQQvRQOu25wQtB7foWtlUL65paqGo0nBt0 UtuEu5PO\nrubp83VzYmZSODOTwvlPeR2bDpfw4Xcl7DxegbeLnozBQUyOCSE2xNMuH3e76LX4uDpRXW dHGTaS\nAAohhBAOp321sBfmauGPzo24+PhyvKKektomdFoNPq5OdjW4pH+AB78e25f7UqP48mQluYdL eP9Q\nMf/4+jRRfm5MiQlhUnQwwe2SXdE5SQCFEEIIgVajIcjThSBPF+qaWiiqbuREZQMGowkPZx0edr RG\nrl6rYXSUP6Oj/KltamHr0VJy80v48+eFvLC7kBsifJkSE0J6/4AevZzb1bCf36YQQggh7IKHi56B \nQZ70C/CgvK6ZwkpzVVCvNU+BYk9VQU8XPdPiw5gWH8YPVQ1syi9m0+ESHvvXETycddw8MJApMSEk\n hXvb5SNiW5EEUAghhBCd0mk1BHu5EOzlQm1TC6erGymsbKDFDquCABG+btw7KopFIyPZ/+PZ1lVH\nSn nvUDG9fFyZHB3M5OgQevm42rqpNmdfvzkhhBBC2CXP1qpgX393KuoNHCuvs9uqoFajYViEL8Mi\nfPmv GwfwyfdlbMov5qV/nyT73ydJ6eXDlJhgxg8MtLsktrs45lULIYQQ4oroddoOVcFTZxs5WWWu\nCno663 F3tq8+d+7OOqbEhDAlJoQz1Y1s+q6E3MPFPL61gD9++h9uHBDIz2OCGRbhi9aBHhFLAiiE\nEEKIK+Lp omdwsCf9A9wpq2umsMJ++woChHq7ctcNfbhzeARfn64h93AxW4+W8tF3JYR4uTBpiHnV\nkUg/d1s31e okARRCCCHEVdHrtIR6uxLq7UpN47kRxEaTwtNZZ3dVQY1GQ2K4N4nh3jyc3o8d/6kg\nN7+YdXk/sHbv D8SHejE5JoSJgwLxdnWydXOtQhJAIYQQQlwzXq56Brueqwoeq6inpK4ZvQZ8XJ06\nXYbOllz1OiYODm Li4CBKa5v46LtScvOLWfnJ9/zps/+Q1i+AKTEhjIz0s7uK5tWQBFAIIYQQ19z5\nVcG2voJGk8LLRYeb Hc7PF+TpwtxhvZkztBffldSSm1/Cv74rYVtBGQHuTvxsSDBTYkIYEOhh66Ze\nNUkAhRBCCGFVXq56hr h6MiDQndLaJo5XNlBS24RTa19Be6sKajQaokO8iA7x4jdj+/L58Qpy80t4\n80ARr+0/xeAgD6bEhHDL 4CD8Wtf8vd5IAiiEEEKIbqHXaQnzcSPMx43qRgOnzjbyQ1UDJgWezvZZ\nFXTSaUkfEEj6gEAq65vZfM S86sjTnx3j2Z3HGRPlz5SYYMb09cdJp7V1cy+ZJIBCCCGE6Hberk54\nuzoxINCDstomjpXX23VVEMDP 3ZnbkntxW3Ivvi+rY1N+MR/ml/DZsXJ8XPVkDA5iSkwI0cGedr/q\niCSAQgghhLAZp/Oqgj+ebeDHqk aMSuHtrLfbtXwHBHrw/8b24/7UvnxxopLc/GI2fnuGDQdP08/f\nnckxwUwaEkyQp4utm9opSQCFEEII YRe8XZ2IcXViYKCnua9ga1XQWafF21VvlxM167UaUvv6k9rX\nn+pGA1uPmlcdeX5XIX/5vJCRffzIGB xEoo/J1k3tQBJAIYQQQtgVJ52WcB83wrxdqW5s4dTZBn6o\nakSh8LLjqqC3qxPTE8KYnhDGicp6NuWX sCm/hOVbjpIe6cWtI2Ns3UQLSQCFEEIIYZc0Gg0+bk74\nuDkxMMhcFTx2HVQFASL93LlvdBT3jork3y cqoaHa1k3qwCbDVSoqKpgwYQIDBw5kwoQJVFZWdrlv\ndXU1vXv3ZsmSJd3YQiGEEELYk7aqYGpff0ZH +RPq5UJFvYGS2iYaW4y2bl6XtBoNQ3v7MtDf1dZN\n6cAmCeDKlSsZP348BQUFjB8/npUrV3a57+9//3 vS0tK6sXVCCCGEsFdtVcHYMG9uHBBIfKg3RhOU\n1DZR1WDApJStm3hdsEkC+N577zFv3jwA5s2bx8aN Gzvdb9++fRQXFzNx4sTubJ4QQgghrgPOei29\n/dwY28+fUVH+hLRWBUvr7LsqaA9skgAWFxcTFhYGQG hoKMXFxRfsYzKZePjhh1m9enV3N08IIYQQ\n1xGNRoOvmxNxrVXBuJDWqmCNVAW7YrVBIDfffDNnzpy5 YPuKFSs6vNZoNJ1OlvjCCy8wadIkevfu\n/ZPnys7OJjs7G4AzZ85QVFR0ha2+PKWlpd1yHkcksbUuia /1SGytS+JrPT0ptlqgv6uiVmukuKaJ\nk2VNAHg463HSdf+gEYNRUXe2otvyk0thtQRw27ZtXb4XEhLC 6dOnCQsL4/Tp0wQHB1+wz549e9i5\ncycvvPACtbW1NDc34+np2Wl/wUWLFrFo0SIAhg0bRnh4+LW7kJ /QnedyNBJb65L4Wo/E1rokvtbT\nE2M7GGhqMVJSYx5BXN9sxMVJi7eLvttW62hqMc8BaE/xtck0MJmZ maxbt45ly5axbt06br311gv2\nef311y0/5+TkkJeXd9HBIkIIIYQQnXHR64jwc6e3rxtVDQZ+qGqgqL oRDRq8XPS46K+fNXyvFZtc\n8bJly9i6dSsDBw5k27ZtLFu2DIC8vDwWLlxoiyYJIYQQoofTaDT4uTuT EO7DjQMCiQnxpNlooqS2\nibONBpQD9RW0SQUwICCAjz/++ILtw4YN4+WXX75g+/z585k/f343tEwIIY QQjuD8quDJynNVQR9X\nPc49vCooK4EIIYQQwmG1VQX93J0ZHOxJcU0TxyrqqWo04KrX4tWNfQW7kySA QgghhBCAq5OOSH93\n+vi5UdlaFTxT3YhGo8HbpWdVBSUBFEIIIYRoR6PR4O/ujL+7M43nVQXd9Do8XX TXfVVQEkAhhBBC\niC60VQUjfN2oajRwoqKeMzVN6DQavF31OOmuz6qgJIBCCCGEED9Bqz1XFWwwmCeY Pl5eT2XD9VkV\nlARQCCGEEOIyuDnpiPJ3p4+vua/gicp6iq+zqqAkgEIIIYQQV0Cr1RDg4UyAx4VVQX cnHR7O9lsV\nlARQCCGEEOIqnV8VLKyop6S2GZ0Gu1xpRBJAIYQQQohr5Pyq4OmzjRyvqEevta9KoCSA QgghhBBW\n4Oako1+gB1H+7pz8scnWzenA/mqSQgghhBA9iFarsbtJpO2rNUIIIYQQwuokARRCCCGEcD CSAAoh\nhBBCOBhJAIUQQgghHIwkgEIIIYQQDkajlFK2bsS1FBgYSFRUVLecq7S0lKCgoG45l6OR2FqX xNd6\nJLbWJfG1HomtdXVXfAsLCykrK/vJ/XpcAtidhg0bRl5enq2b0SNJbK1L4ms9Elvrkvhaj8TWuu wt\nvvIIWAghhBDCwUgCKIQQQgjhYHRZWVlZtm7E9Wzo0KG2bkKPJbG1Lomv9UhsrUviaz0SW+uyp/hK \nH0AhhBBCCAcjj4CFEEIIIRyMJIBCCCGEEA7GYRPAFStWEBsbS0JCAklJSXzxxRdXfcysrCxWr159\n DVp3/dJoNMyePdvyuqWlhaCgIKZMmXJNju+IMS4vLycpKYmkpCRCQ0Pp1auX5XVzc/M1P9+YMWM4\ncO DANT+uLTz44IM8++yzltcZGRksXLjQ8vrhhx/mT3/60yUdy9r3Xk5ODkuWLLHa8btLV/err68v\nMTEx Vj9/T4nj1dDpdJbfQVJSEoWFhRfsU1RUxC9/+ctOP5+enm5X05XYwuXkCDk5ORQVFV31Obs7\n7vpuO5 Md2bNnD7m5uezfvx8XFxfKysqs8h+pI/Lw8ODbb7+loaEBNzc3tm7dSq9evWzdrOtaQECA\nJSHLysrC 09OTRx55xMatuj6kpqayYcMGfvOb32AymSgrK6O6utry/u7du3nmmWds2MKep6v7tbCw\n8Kr+EGxpaU Gvd8j/si6bm5vbRf+Ia2lpITw8nLfffrsbW3X9uNwcIScnh7i4OMLDwy/5HPZwPztk\nBfD06dMEBgbi 4uICmFcPCQ8PJyoqyjJ7dl5eHunp6YD5S+zOO+8kPT2dfv368dxzz1mOtWLFCgYN\nGsSYMWM4cuSIZf tLL73E8OHDSUxMZPr06dTX11NTU0Pfvn0xGAwAVFdXd3jdU0yaNIlNmzYB8Oab\nb3L77bdb3quoqGDq 1KkkJCQwcuRIvv76a0BifCW+//57kpKSLK9XrlzJk08+CUBBQQEZGRkMHTqU\ntLQ0jh49CsBbb71FXF wciYmJ3HjjjQDU19czY8YMoqOjmT59Oo2NjZZjLlq0iGHDhhEbG8vjjz8O\nwJYtWzpUDj766CNmzJhh 9eu9EqNHj2bPnj0AHDp0iLi4OLy8vKisrKSpqYn8/HxSUlJYtWoVw4cP\nJyEhgeXLl1s+39W9l56ezm 9/+1tuuOEGBg0axM6dOwEwGo0sXbrUcqwXX3wRMH/npKWlkZSURFxc\nnGX/tWvXMmjQIG644QY+//xz y/E/+OADRowYQXJyMjfffDPFxcWYTCYGDhxIaWkpACaTiQEDBlhe\nXw+MRiN33303sbGxTJw4kYaGBq Bj5aOsrMyymlNOTg6ZmZncdNNNjB8/XuJ4Fc6PZWFhIXFxcQA0\nNDRw2223ER0dzbRp0yy/F4DFixdb vgPa/m188sknTJ061bLP1q1bmTZtWvdekBV1lSM8/vjjDB8+\nnLi4OBYtWoRSirfffpu8vDxmzZpFUl ISDQ0NF80l5syZQ2pqKnPmzLF93JUDqqmpUYmJiWrgwIFq\n8eLFavv27UoppSIjI1VpaalSSqm9e/eq cePGKaWUWr58uRo1apRqbGxUpaWlyt/fXzU3N6u8vDwV\nFxen6urq1NmzZ1X//v3VqlWrlFJKlZWVWc 73u9/9Tj333HNKKaXmz5+v3n33XaWUUi+++KJ66KGH\nuuuyu4WHh4c6ePCgmj59umpoaFCJiYnq008/ VZMnT1ZKKbVkyRKVlZWllFLq448/VomJiUopifGl\nWr58ueX6CwoKLPFTSqn/+Z//UU888YRSSqn09H T1/fffK6WU2rVrl5owYYJSSqkhQ4aoM2fOKKWU\nqqysVEop9dRTT6m7775bKaXU/v37lVarVV999ZVS Sqny8nKllFIGg0GNGTNGHTp0SBmNRjVw4EBL\n/GfMmKE+/PBDq1731YiKilInTpxQf/3rX9WaNWvUY4 89pjZt2qR27dqlxowZozZv3qzuvvtuZTKZ\nlNFoVJMnT1afffbZRe+9cePGWe6rTZs2qfHjxyulzPdb 2++gsbFRDR06VB07dkytXr1aPfnkk0op\npVpaWlR1dbUqKipSERERqqSkRDU1NanRo0er+++/XymlVE VFhTKZTEoppV566SXLubKystQzzzyj\nlFJq8+bN6he/+EU3RfHKtL9fjx8/rnQ6neXemjFjhnr11VeV UuZ47t27VymlVGlpqYqMjFRKKbV2\n7VrVq1cvy33oqHG8XFqtViUmJqrExEQ1depUpdSFsTx+/LiKjY 1VSin19NNPqwULFiillDp48KDS\n6XSW30fb/i0tLWrcuHHq4MGDymQyqcGDB6uSkhKllFK33367ev/9 97v1Gq2pqxyhLRZKKTV79mzL\nNbe/f5W6eC6RkpKi6uvrlVK2j7tDVgA9PT3Zt28f2dnZBAUFMXPmTH Jyci76mcmTJ+Pi4kJgYCDB\nwcEUFxezc+dOpk2bhru7O97e3mRmZlr2//bbbxk7dizx8fG8/vrrHDp0 CICFCxeydu1awPxX64IF\nC6x2nbaSkJBAYWEhb775JpMmTerw3q5du5gzZw4AN910E+Xl5ZZHchLja6 Oqqop///vfTJ8+naSk\nJO6//35L/5TU1FTmzp3Lyy+/jMlkAmDHjh2WfpvJycnExsZajvXmm2+SkpJC SkoK+fn5HD58GK1W\ny6xZs3jjjTeoqKhg3759TJw4sfsv9BKNHj2a3bt3s3v3bkaNGsWoUaMsr1NTU9 myZQtbtmwhOTmZ\nlJHNIjAAAAsISURBVJQUvvvuOwoKCi567wH84he/AMzzerX1sdqyZQvr168nKSmJ ESNGUF5eTkFB\nAcOHD2ft2rVkZWXxzTff4OXlxRdffEF6ejpBQUE4Ozszc+ZMy7F//PFHMjIyiI+PZ9 WqVZZ7+847\n72T9+vUAvPLKK9fdvd23b19L1bp93C5mwoQJ+Pv7A0gcL1HbI+ADBw7w7rvvWra3j2V7 7b8DEhIS\nSEhIsLy3YcMGUlJSSE5O5tChQxw+fBiNRsOcOXN47bXXqKqqYs+ePfzsZz+z/oV1k65yhE 8//ZQR\nI0YQHx/PJ598YrmfLkdmZiZubm6A7ePusB0qdDod6enppKenEx8fz7p169Dr9Zb/FNs/BgMs peC2\nz7a0tFz0+PPnz2fjxo0kJiaSk5PD9u3bAfN/wIWFhWzfvh2j0Wgpwfc0mZmZPPLII2zfvp3y8v JL\n+ozE+PK0v1/BfM/q9XqUUgQGBnbaB+ill17iiy++IDc3l5SUFL766qsuj19QUMD//u//8uWXX+Lr \n68vs2bMt/y7uvPNOpk+fDsDMmTPR6XTX+OqundTUVHbv3s0333xDXFwcERERPP3003h7e7NgwQI+\n ++wzHn30Ue65554On2s/eKQzbfdr+3tVKcXzzz9PRkbGBfvv2LGDTZs2MX/+fB566CG8vb27PPYD\nDz zAQw89RGZmJtu3b6dtvv6IiAhCQkL45JNP+PLLL3n99dcvJxQ2d/6/8bZHXhf77vXw8LD8nJaW\nJnG8 Cu1jeSmOHz/O6tWr2bt3L35+fsyfP9/y+1mwYAE///nPcXV1ZcaMGTbvz3atnZ8jvPjii3z9\n9dfk5e URERFBVlbWBfdqm0u9n7vSXXF3yArgkSNHKCgosLw+cOAAkZGRREVFsW/fPgDeeeednzxO\nWloaGzdu pKGhgZqaGj744APLezU1NYSFhWEwGC74cpk7dy533HFHj/urs70777yT5cuXEx8f32H7\n2LFjLfHYvn 07gYGBF/0Clxh3LTQ0lKKiIiorK2lsbLT0u/Tz8yMsLMzyl7/JZOLgwYMAHDt2jJEj\nR/LEE0/g5+fH qVOnSEtL44033gDg4MGDlr9qq6ur8fLywtvbm9OnT7N582bLuSMiIggMDGTlypXM\nnz+/G6/68o0ePZ rc3Fz8/f3R6XT4+/tb/noePXo0GRkZvPLKK9TW1gJw6tQpSkpKLnrvdSUjI4M1\na9ZY+pwePXqUuro6 Tpw4QUhICHfffTcLFy5k//79jBgxgs8++4zy8nIMBgP/+Mc/LMc5e/asZfDU\nunXrOpxj4cKFzJ49mx kzZth14n052n/3XmxggsTROtp/B3z77beWvtnV1dV4eHjg4+NDcXExH330\nkeUz4eHhhIeH8+STT/a4 79nOcoTBgwcD5v6AtbW1He5TLy8vampqLK8vNZewddx7Vsp+iWpra3ng\ngQeoqqpCr9czYMAAsrOzyc /P56677uL3v/+9pdPmxaSkpDBz5kwSExMJDg5m+PDhlveeeOIJRowY\nQVBQECNGjOhwc8yaNYvHHnus w+CInqZ37978+te/vmB722CPhIQE3N3dL/hSPp/EuGuurq7893//\nN8OGDaNXr14dpth46623WLx4MV lZWTQ3NzN79mwSExN58MEHOX78OEopJk6cSFxcHP369WPevHlE\nR0cTGxtLcnIyYI59TEwMQ4YMITIy ktTU1A7nv+OOO6iurmbQoEHdet2XKz4+nrKyMu64444O22pr\nawkMDGTixInk5+czatQowPz457XXXr vovdeVhQsXUlhYSEpKCkopgoKC2LhxI9u3b2fVqlU4OTnh\n6enJ+vXrCQsLIysri1GjRuHr69thQE9W VhYzZszAz8+Pm266iePHj1vey8zMZMGCBT3qP91HHnmE\nX/3qV2RnZzN58uQu95M4WsfixYtZsGAB0d HRREdHW5YrS0xMJDk5mSFDhhAREXHBd8CsWbMoLS0l\nOjraFs22mq5yBF9fX+Li4ggNDe3wfTB//nzu vfde3Nzc2LNnD8uXL7+kXMLWcZel4Gzg7bff5r33\n3uPVV1+1dVN6LImx9d17772MGjWKefPm2bopDi UvL48HH3zQMgJWXBmJ49VbsmQJycnJ3HXXXbZu\nikO5VnF3yAqgLT3wwAN89NFHfPjhh7ZuSo8lMba+ pKQk/Pz8OkzXI6xv5cqVrFmzxmH6rFmLxPHq\nDR06FA8PD55++mlbN8WhXMu4SwVQCCGEEMLBOOQgEC GEEEIIRyYJoBBCCCGEg5EEUAghhBDCwUgC\nKITokXQ6HUlJScTGxpKYmMjTTz/dYeJsa1i6dCmxsbEs XbrUqudpv46rEEJcCRkFLITokdqWwwIo\nKSmxzFv4hz/8wWrnzM7OpqKiwuEnFhZC2D+pAAoherzg4G Cys7P585//jFKKwsJCxo4da1nnePfu\n3YB5BZmNGzdaPjdr1izee++9DsdSSrF06VLi4uKIj4/n73// O2CeWLi2tpahQ4datrWJj4+nqqoK\npRQBAQGWdWjnzp3L1q1bMRqNLF26lOHDh5OQkMCLL75o+eyqVa ss25cvX37BtR07dozk5GT27t17\nbYIlhHAIUgEUQjiEfv36YTQaKSkpITg4mK1bt+Lq6kpBQQG33347 eXl53HXXXTzzzDNMnTqVs2fP\nsnv37gtWq/nnP//JgQMHOHjwIGVlZQwfPpy0tDTef/99PD09O12DOT U1lc8//5zIyEj69evHzp07\nmTt3Lnv27GHNmjX87W9/w8fHh71799LU1ERqaioTJ06koKCAgoICvvzy S5RSZGZmsmPHDvr06QOY\nl6y67bbbyMnJITExsVviKIToGSQBFEI4HIPBwJIlSzhw4AA6nY6jR48CMG 7cOO677z5KS0t55513\nmD59+gWLre/atYvbb78dnU5HSEgI48aNY+/evWRmZnZ5vrFjx7Jjxw4iIyNZ vHgx2dnZnDp1Cj8/\nPzw8PNiyZQtff/21ZX3Rs2fPUlBQwJYtW9iyZYtleb7a2loKCgro06cPpaWl3H rrrfzzn//ssAyg\nEEJcCkkAhRAO4dixY+h0OoKDg/nDH/5ASEgIBw8exGQy4erqatlv7ty5vPbaa7z1 1lusXbv2mpw7\nLS2Nv/zlL5w8eZIVK1bw7rvv8vbbbzN27FjA/Fj5+eefJyMjo8PnNm/ezKOPPso999 zTYXthYSE+\nPj706dOHXbt2SQIohLhs0gdQCNHjlZaWcu+997JkyRI0Gg1nz54lLCwMrVbLq6++itFo tOw7f/58\nnn32WYBOE6uxY8fy97//HaPRSGlpKTt27OCGG2646PkjIiIoKyujoKCAfv36MWbMGFavXk 1aWhoA\nGRkZrFmzBoPBAMDRo0epq6sjIyODV155hdraWgBOnTpFSUkJAM7Ozrz77rusX7+eN9544+qD JIRw\nKFIBFEL0SA0NDSQlJWEwGNDr9cyZM4eHHnoIgPvuu4/p06ezfv16brnlFjw8PCyfCwkJITo6mq lT\np3Z63GnTprFnzx4SExPRaDT88Y9/JDQ09CfbM2LECEuiOXbsWB599FHGjBkDwMKFCyksLCQlJQWl \nFEFBQWzcuJGJEyeSn5/PqFGjAPD09OS1116zjDL28PAgNzeXCRMm4OnpedHH0EII0Z6sBSyEEO3U\n 19cTHx/P/v378fHxsXVzhBDCKuQRsBBCtNq2bRvR0dE88MADkvwJIXo0qQAKIYQQQjgYqQAKIYQQ\nQj gYSQCFEEIIIRyMJIBCCCGEEA5GEkAhhBBCCAcjCaAQQgghhIP5P+DM/yq8xDnAAAAAAElFTkSu\nQmCC \n", | "image/png": "iVBORw0KGgoAAAANSUhEUgAAAoAAAAGoCAYAAADW2lTlAAAAOXRFWHRTb2Z0 d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8vihELAAAA CXBIWXMAAAsTAAALEwEAmpwYAACoj0lEQVR4nOzdd3xcV5n/8c8t00czo95tWZZ7iVvi9AopJpgFHBJI CKTgDWUJu4T6W7IssJuwy5IFEooDm1A2MWyAdUhj00hCmuM4zTUucpFk9Tq93Pv7Y4olS7ZlW6ORNM/7 9Uo05c7ce49kzVfn3PMcxTRNEyGEEEIIkTfUXB+AEEIIIYQYXxIAhRBCCCHyjARAIYQQQog8IwFQCCGE ECLPSAAUQgghhMgzEgCFEEIIIfKMnsud/+AHP+Dee+/FNE0+9alP8YUvfGHI86Zpcuutt/LYY4/hdDq5 //77WbZs2THfs6SkhLq6uqM+H4vFsFgsY3D0k5u0Q1K+tkO+nvdI8r0t8v380/K9HfL9/Aebam2xb98+ Ojs7hz2eswC4ZcsW7r33XjZu3IjVauXyyy/nyiuvpKGhIbPN448/zq5du9i1axevvvoqn/70p3n11VeP +b51dXVs2rTpqM+3tLRQVVU1ZucxWUk7JOVrO+TreY8k39si388/Ld/bId/Pf7Cp1hYrVqwY8fGcDQFv 376dlStX4nQ60XWdCy64gD/84Q9DttmwYQPXX389iqJw5pln0tvby6FDh3J0xEIIIYQQU0POAuDChQt5 4YUX6OrqIhgM8thjj3Hw4MEh2zQ3N1NbW5u5X1NTQ3Nz83gfqhBCCCHElJKzIeB58+bxla98hUsvvRSX y8WSJUvQNO2k3mvdunWsW7cOgNbWVlpaWo66bUdHx0ntY6qRdkjK13bI1/MeSb63Rb6ff1q+t0O+n/9g +dIWOZ0EctNNN3HTTTcB8PWvf52ampohz1dXVw/pFWxqaqK6unrY+6xdu5a1a9cCybHu443dT6Wx/VMh 7ZCUr+2Qr+c9knxvi3w//7R8b4d8P//B8qEtcloGpr29HYADBw7whz/8gY997GNDnl+9ejW/+tWvME2T V155Ba/XS2VlZS4OVQghhBBiyshpD+CHP/xhurq6sFgs3HPPPfh8Pn76058CcMstt7Bq1Soee+wxGhoa cDqd3Hfffbk8XDEBJQyTWMLAqqmoqpLrwxFCCCEmhZwGwBdeeGHYY7fcckvmtqIo3HPPPeN5SCJH4gmD UMwgFEsQN0wM08AwIGaYJAwTwzRJmCaGYRI3IRiNE4wmSBjJ1+uaQpnbSpHTglXTsOkqbpuOJqFQCCGE GCanAVDkL9M0CUYT+KMJWvrDdPgjGCaAiUIytCmAqiT/EFCU9P3kcxZNxeewZO4nDJOuQJRD/RFMzOSr TROXTUdXFSyagqaqOC0a1V47bpv86AshhMhf8ikosi5hmASiccIxA38kTncoSk8wRiIV+By6RuGgMHcy NFXBYx9aud00TWKJZO9hKGpimAk6/RH2dgWo9tqpL3ad2okJIYQQk5QEQJEVCcOkNxTjUH+YQwMREoYJ mGiKgl3X8NotWR+eVRQFqz58H6Zp0uGP0twXxhn14ymOS4+gEEKIvCKfemJMDYTjNPWFaOoLE0+Y2HQF 7ylei2eaJpF48vrAcOprKGYQjie/aopCXZGDigIbyih6ERVFweewYJomzX0xXtjbRa3PQX2xE6dV/kkI IYSY+uTTTpwS0zQJRBN0B6Ic7AvRH45jUZVR9/DFDZM9nQG2tg2wrc3Pns4AgWgiE+7SoW80nBaNuiIH M4tdzChyUl/spL7ISYXHNuLwsqIouG06XpeV1oEwB3pDTPc5mF7klB5BIYQQU5p8yokTFk8Y9EfidPij tPSHCccNNMBl1Shz2476umSPW5gtrcmwt7VtgB3tfiKpgOe168wudVHqtmK3aDh0FYdFw25RsevJrw6L hmPIbZVowqSxO0hjd5C9XUFe2tfNn7a1ZfbrsKjJQFjkZOX0Qt47qwRdO1wCU1EUCh1WDNPMBMFCh4W6 IifFLisWLaflMoUQQogxJwFQjEosYdATjNHUF6LDH8U0QVfBbdPxHKW3rDsYZWvrQLJ3rzUZ+PrCcQBs msrccjcfWlTBgvICFlYUUO21j2oIdyTLarxD7veFYzR2BdmbCoV7u4K8tL+HR7a38+MX93Ht8mr+ZkHF kNeoioLPYQUgGE3wZks/mFDpsVHjcyQnqkhZGSGEEFOABEBxTOlr+g72hkgY4LSoFDmPPmN3X3eQv+zp 4i97utjSOgAkS7nMLHZxUUMJ88vdLCgvYGaxc0gv3Fjz2i0sqfaypPpwMDRMkxcbu7nvtSa+95e9/PzV A/zNLC8fP7sI7xEziJ1WDadVwzBNuoPJnk6nVWN5jU+Gh4UQQkx68kkmhoknDHpCMRq7g3QFolhUBd9R rukzTJNtbX6e29PFs7s72dcTAmB+uZtPnz2dZdVe5pa5cVi08T6NYVRF4bz6Ys6rL+bN5j7u39TE/W93 8dvtPXxwYSXXLqumvMA27DUeuwUP4I/EeamxmxXTfBQ5rbk5CSGEEGIMSAAUQHKIty8Uo3UgQkt/hIRh 4LSMfE1fwjB5o7mPp3d38tyeLtr9UTQlOQx71WlVXDCzmIqCo18LeDIShkncMDFNM1UwOindEWlRlRPq UVxS7eU/q71s3nWAP+4J8ds3m/ndWy1cMbeM61fUMKPIOew1bpuOriV4dX8Pp1V6qPI5TvW0hBBCiJyQ AJjHTNOkPxynuS/Ewd4wpmli1VV89uFlW0zTZGubnz/vbOfJdzvpDESx6SpnTS/kM2cXc1798GHU0UgY JtGEQSRuJAMeJpgAqaU/UsWidU3FYVHRNRU9lfPSOdAwIBBLEAnHSL9IUxSsmopdV48ZDOsLbXz78ml8 +qzp/Pcbzfzvllb+tK2NC2cW84kVNSyq9AzZ3q5r6A6FN1r6iRom0wsdJ33dohBCCJErEgDzUCxh0OGP sLexm4FIHKt29Ov69nQF+PPODv5vZwdNfWEsmsI5dUVcNqeU82YUYT+Bod10Lb+YYQAKpmmip0rGlLpt uK0aVl1FUxVURUFTkku4WTV1VJMvYolU2ZjUiiN9kTg9gSiRRAxFAbuWvK5vpKHsKq+dL104k5vPqOW3 b7XwuzcP8Zc9XSyr9vLJ02s4a3phJujpmkqpy8rW1gEGwjHmlhfITGEhhBCTigTAPGGaJn3hOC2p3r6B 7gCVFZ4Rh3hbByI8saOdJ3a2s7sziKrA6bU+bjyjlotmllBgH92PTTiWIBBNkDBNFAUKbHpmNm26vMtY BieLlnw/jx3KUkPQpmkSiiUYiCRoGwjT5o+SMEw8Nh2bPnzfhU4rt5xVx/XLa/njllb+e3MTn//frcwu cfHZc+o4Z0YRkFx6rtxt5VB/hJ5QnKXV3lG3ixBCCJFr8ok1xQWjyXp9+7qDBGMGVk2hyGlBD1mG9N5F 4gZ/2dPJn7a28eqBXkxgcWUBt11Yz3tnlVLsOv6kh3hqzd9oInmtntduYXaZG69dx23Tc9JLpigKTquO 06pTXmAjnjBo90fY1RGgLxzDiCVGfJ3TqnHtsmo+clolT+zo4L5NB7l1w1Y+urSKz587A4umoigKxS4r gWicFxu7WFLtpcJjH+czFEIIIU6cBMApKJ4w6A4mZ/F2B6NoqRUvyo4oX2KmZvD+aVsbf97ZwUAkTkWB jZtW1nLl/HJqvMef5BCOJfBHEximiU1TKffYKHXZ8Nj1ExoeHi+6plLldVBRYKcrGOX1nT20DURwWFQK bPqw6/ksmsr7F5Rz6ZxSfvDCXh58o4W3Wvr51yvmUpOaBOKy6lg1ldebeplV6qah2CX1AoUQQkxoOQ2A d911Fz//+c9RFIVFixZx3333Ybcf7kG5//77+dKXvkR1dTUAn/vc57j55ptzdbgTWixh0BuK0dIXps0f IWGYR12ZoysQ5Q/bunlyfxN7u4LYNJWLZxXz/vnlrKj1HbXGHyRDYzCWIBhLYJrgsevML3dT6LTismqT ZkKEqiqUum0srvTgLCyisStA60AEi5a8JvHINrDpKl++qIEVtT6+/eQurn3gDf7fJbO4dE4pkAyKZW4b e7oC9AZjLK7yTMgALIQQQkAOA2BzczM//OEP2bZtGw6Hg4985COsX7+eT37yk0O2u/rqq7n77rtzc5AT nGma9IRiHOgJ0TYQwTBNHLqWXLHiiAATTxj8tbGbh7e18eK+HhKGyaKKAr5+SQOXzi49bnHjuGEyEIkR S5iUumw0lLjwOSw4rZO/E9nnsLC0xkcgEmd/b5AD3SF0LVn78MhAe3FDCXNL3fy/x3fw9cd38NrBXr54 YT12XUNVFMpcNnrDMV7Y283iygLKZUhYCCHEBJTTT+94PE4oFMJisRAMBqmqqsrl4UwK8YRBXzhOVyDK of4wwVgCu65S7BweVgB2dwZ4eGsbj+9opycUo9hp4dql1VxQpXHazGnH3pdh0h+OETdNrKpKrc9JjdeO a4quhOGy6cwv91BX6KSxK8iB3hBWTcVrHzo0XOW1c+9Vi/nxS/v51etNvH2onzvfNy9TO9BntxCJG2xq 6qWuyMmcUndWVz0RQgghTlTOPsmrq6u57bbbmDZtGg6Hg0svvZRLL7102Ha///3vef7555k9ezZ33XUX tbW1OTja3IrGDfrD6SLNYRKGiUVVcFn1EXvu+sIx/ryzgz9tbWN7ux9dVTi/vojVCyo4c3ohuqrQ29k2 4r4Shok/GicSN9A1lWmFTio9thGvj5uqnFadBZUephc52d3p51B/BKdFG9LWuqby+fNmsKLWyz/9+V0+ /sAbfOWiBq6cX4aiKNh0lXK3jabeMP3hOEuqvRNiNRQhhBACQDFN0zz+ZmOvp6eHD3/4w/z2t7/F5/Nx 1VVXsWbNGq677rrMNl1dXbjdbmw2Gz/72c/47W9/yzPPPDPsvdatW8e6desAaG1tZePGjUfdb0dHB6Wl pWN/QmPINE3CqdDX7o/ij8TBBF1XcOo66gidSQnD5PXWIH/e08dLBwPEDJOZhTYun+nh4joPXvvQ8OHv 7cbtK0rtDwLROLGEmbw2zmWl2GWlwDa8IPRUM5qfB38kzr7uIH3hOAU2HYs2tE06g3HuePEQb7WFeM+M Aj5/RjlOy+Fvkj8axzRhbpkbz0kUy86GyfDvYLzke1vk+/mn5Xs75Pv5DzbV2mL16tVs2rRp2OM56wF8 6qmnmDFjRqaRP/ShD/HSSy8NCYDFxcWZ2zfffDNf/vKXR3yvtWvXsnbtWgBWrFhx3KHkiTjUHIkn6AvF aRsI0x6IEk0YaIoNV6FGyTF6jvb3BHlkWzuPbm+j3R/Fa9f58OJK3j+/nDll7mPu0+ErZSASB6Ch0k6l 1473KGv+TmWj+XmYVWfSPhBha5ufeMKgcFDhbB+wrqaK/9p4gHtfPcC7vXHuuGJupv19QDieYG84znxf wYRZPWQi/jvIlXxvi3w//7R8b4d8P//B8qEtchYAp02bxiuvvEIwGMThcPD000+zYsWKIdscOnSIyspK AB5++GHmzZuXi0PNCsMwGYikruUbCDMQjmOiYNeTJVv0Y4SwQDTOk+928qdtbbzV0o+qwNl1RXzxgnLO m1GEdYQCx5n9msn99gRj6AUG88vdlBXYsOkyPHksiqJQ7rFT5LKyuzNAY1cQj13PDOtqqsKnzpzOshov //j4Tm747Zt84fx6rlpciaIo2HUNi1Nla2s/wWicuWUFUipGCCFEzuQsAK5cuZI1a9awbNkydF1n6dKl rF27lttvv50VK1awevVqfvjDH/Lwww+j6zpFRUXcf//9uTrcUxaJJwhGE/gjycLMncHkihSqouC2aZSO UK5lMMM02dzUx8Pb2nhmVyfhuEFdoYO/O7eO980rp+Q4hZojcYOBSBwTk2qvg2rdw+y64gnREzWZWDSV eeUFVBTYeLuln65AlKJBE3CW1/h44Nql/NP/vcu/PbuH1w72cvt7ZlOQWl+53G1jX0+ImGGyoLxAJocI IYTIiZxdA5gtK1asGHGsO62lpWVcunZDsQQD4TgdgQjt/ijh1IoTqqLgsKg4LNox6+2ltfSF+dO2Nh7d 3kZLfwSXVePS2aWsXlDOwoqCYwa4RKqXMZowcVpU6oudmd6+8WqHie5U2iGeMNjVGaCxO4jXNrTwtWGa /PfmZu5+cR9lLit3rJrLwkpP5vmuQJQCu56zySHy/T8s39si388/Ld/bId/Pf7Cp1hZHy0VTs57HOEoY 5uHevWiCnlCM3lCMSMzAVJKrYzgtGp4TKJ0SiiV4ZndyWbZNTX0owOnTfHzm7DoubCjGfpzh2kjcoD8S Q0GhttBOlccxrJSJOHV6qjewzG3jrZZ+ArEoRY5kb6CqKHx8eQ1Lqzx8/fEd3Pw/b/OF82Zw9ZKqzBJy feEYLzV2s6zGS6Hz+EvtCSGEEGNFAuBJiicMNh7spT8UA0XBNE20VPkPp66eUOCD5Mzftw7186etbTy1 q5NANEG1184tZ03nynllo1pjNhCNE4gmcFg0FpZ7KPfYcrL+br4pdlk5d0YR29sHaO4NU+S0ZNp9YaWH 33xsKd/8v3f53nN7ebOln398zyzcNh2v3UI4luCV/T3MK584k0OEEEJMfRIAT1LCNOkPx4977d7xtPSF eXxnO49ub+dATwiHReU9s0p5//xyllZ7RhUI/JE4wWgCn9PC6bUFFDmtMsFgnFl1lcWVHkqdVt5pHcgs KQfgsVv4j/fP59evN3PPi4282xHgu++bx6xSF3aLhkVT2dY6QF84JtcFCiGEGBcSAE/ByUas/nCMp3Z1 8tj2dt5s6QdgabWHT66o4T2zSnFaj39NmJEKoNGEQbHLyqIqD4WOkVcDEeNDURSqfA58TgtbWwdo80co tFuw6iqKonD9ihoWVhTw9cd38Mn1b/KVi2eyekFFcnJIgY22/gj+SIKl1Z4pscSeEEKIiUs+ZcZJNG7w 133dPL69nb/u6yaWMKkrdPCZs6dz+ZwyqryjWzM2YZj0hmMkDJMan4PphY4JU1xYJDmtOitqfbQNRNja OsBAJJ6ZKbysxst/f2wp//jEDr715C7ebOnnyxfNxK5rFLus9Idj/HVvN6dVeWQdYSGEEFkjATCLDNPk rZZ+HtvezlO7OhmIxCl2WlizuJL3zStnTqlr1D128YRBbzhZtLm+2EmNzyFLi01giqJQ4bFT5LSyu8vP vq4QXntypnCxy8rdH1zEulf284uNB9ne5ue775vHtFSYj6bWEZ5e6GROmVuu4xRCCDHmJABmQWN3kMe2 t/PEjnYODUSw6yoXNZSwam4Zp0/zHbPI85GicYPeSAyLqjKnzE2Vx37MQs9iYrHqKvPLPVQW2HmzuZ9g LEaRM7nayqfPrmNxpYfb/7yTjz/4Bt947yzeM6sUa2od4Za+MB3+KKdVeyiSWcJCCCHGkATAMdIZiPLn nR08vqOdHe1+VAXOnFbIZ86p44L64lFd1zdYsqxMHLtFY1G5hwqPTSYHTGKFTivnDJopXOq2oioK58wo 4r8/tpSvPraDrz66g48u6efz583AoqkUu6yEYgle2ddDfbGLhhKn/AwIIYQYExIAT0EoluCx7e08vqOd Vw/0YJgwr8zNP5xfz6VzSo+7OseRTNPEH0kQiiXwOi2sqPVRLDN6pwyrrrKowoNd19jdGaDEaUHXVCo8 du69ajE/eKGRB99sYUvrAHesmkuFx47DomHTVfb3BGn3RzityoPXIdd8CiGEODUSAE9CPGFw42/f4g9v HyIcN6gssPHJ02u5Ym4ZM4qcJ/x+CcOkLxwjbpiUuW2cVu3BJzN6pyRVVZhT5sZl0XintR+XVcNl1bFo KrddOJMlVR6+/dQurn3gDf75sjmcO6MIVVEocVkJROO8tK+bOaVu6oqc8oeBEEKIkyYB8CTomkpfKMZF DSV8eFEFi6s8o1rW7UjxhEFPOIaqKEwvdFLjteM6wQLSYnKqKXTgcei82Tx0PeH3zC5lVqmLrz66gy9s 2MrHllbzuXPqsOoqLquOXdfY2RGgPRBhUYVHfl6EEEKcFPn0OEm//+QK/rK764SHeSFVyiUUQ1FgblmB TOzIUx67hbPqCtnRNsDB3jDFqSHh6YVO7r9mCT94YS8PvNHM5uY+/uWKOUwvdKKpCmXuZLmYFxq7WFBe QLXXIb2BQgghToikjnEUTxh0BqL0hGLUFTs5f2YxdUVOCX95zKKpLKz0sLjSQ1coRiiWAMCmq3z5oga+ 9/75HOoPc90Db/DItrbM6zx2C4V2C++0DvDawR78kXiuTkEIIcQkJMljHETiBh2BCP3RBLNKXFzYUMzs Ujc2Xer4iWTNwJpCB2fXFRGJG/SGYpnnLpxZzAPXLmNemZtv/t+7fOOJnQSiybCna8lyMcFoghf2drGv O4hhmLk6DSGEEJOIBMAs8kfitPsjRBMGC8s9XDSzmPoSlwQ/MSKfw8I5M4rw2HXa/BESqTBXXmDjJx9e zN+eOY0/72zn2v9+g21tA5nXeewWipxWtrf5eXlfN32DAqQQQggxkpwGwLvuuosFCxawcOFCPvrRjxIO h4c8H4lEuPrqq2loaGDlypXs27cvNwd6ggLROG0DERxWjZXTC7lgZjE1hQ6p4SaOy27RWF7jY26pm85g lHA8OSSsqQqfOnM669YsJmaY3PDbt/jVpqZMSNRT1wbGDZMX93Wzo81PPGHk8lSEEEJMYDlLJM3Nzfzw hz9k06ZNbNmyhUQiwfr164ds84tf/ILCwkJ2797N3//93/OVr3wlR0c7Oungp2sqK6cXcnqtjyKnVcq5 iBOiqgr1JS7OnF5IMGrQHz7co7ek2ssD1y7l/PoifvjXRm763Vvs7gxknnfbdEpdVg70BHmhsZvuYDQX pyCEEGKCy2mXVDweJxQKEY/HCQaDVFVVDXl+w4YNfOITnwBgzZo1PP3005jmxLvGKRxP0OZPBr8z6wo5 a3ohxS4JfuLUFDmtnDOjELtFoyMQwUj97HvtFv7tffP4zuVzaOoLcd0Db/Czl/cTjSd7/FRFodhlxaIq vLyvh+1tA9IbKIQQYoicBcDq6mpuu+02pk2bRmVlJV6vl0svvXTINs3NzdTW1gKg6zper5eurq5cHO6I EqZJuz9CLGGyvNrLWdMLpcdPjCmnVeeMaYXUFbqS15OmQp6iKFw+t4z/+fhy3ju7hHtfPcC1D2zm7Zb+ zGsdFo0yt5UDPSFebOweMrlECCFEfstZHcCenh42bNhAY2MjPp+Pq666it/85jdcd911J/xe69atY926 dQC0trbS0tJy1G07OjpO+pgHSxgm9oifMpeNQoeFhD/KIf+YvPW4GKt2mOwmSzt4gOmWKDsPdWLTVByp taUV4IsrCjmv0spdr7Zx0+/e4gNzfNy4pASnJfn3nQ74YwZPtrUyzeeg2menq7MzZ+cy0UyWn4Fsyffz T8v3dsj38x8sX9oiZwHwqaeeYsaMGZSWlgLwoQ99iJdeemlIAKyurubgwYPU1NQQj8fp6+ujuLh42Hut XbuWtWvXArBixYphQ8lHOt7zo1VbMyZvkzNj1Q6T3WRphypgem2czU29RBIGxc7DRcgvLYFz5k3jxy/t 53dvtvBKS4ivXdzAOTOKMtsYpklXMEo4pFFe4Js05z0e8r0t8v380/K9HfL9/AfLh7bI2RDwtGnTeOWV VwgGg5imydNPP828efOGbLN69Wp++ctfAvDQQw9x8cUXy/CqyGsFdp2z6ooocVppH1QqBsBl1fnShTP5 +UdOw2FRuXXDVr7xxI7M0K+qKJS6bGiqwtuHBthyqJ9IapaxEEKI/JKzALhy5UrWrFnDsmXLWLRoEYZh sHbtWm6//XYefvhhAG666Sa6urpoaGjg+9//PnfeeWeuDleICcOqqyyp9jKn1E13MEpvKDZkctRpVR7+ +2PL+NTKaTz5bidrfrWJJ3a0Z7ZxWDSKHRYO9Yd5fk83TT0hKSAthBB5RjEn4rTaU7BixQo2bdp01Odb Wlryomv3eKQdkiZ7OwSjcd7t8NPSF6HQYRm2rODuzgDfeWoXW1oHOKeukK9d3ECFx05vZxu+knJiCYOe UAyPTWd+RQGFzhNf23qym+w/A6cq388/Ld/bId/Pf7Cp1hZHy0VSmViIScxp1VlS7WN5jRd/NE5vKDqk N7ChxMUvPnIaX7ygnteb+vjIrzfz2zdbMiVlLJpKmduGYcLL+3p4s7mXYFTWFRZCiKlOAqAQU0C5x865 9cWUum20B6KZ9YIhuYrIR5dW87uPL2dxZQH//pc9/P3/HaSxO5jZxmlNlozpCsR4fk8XezplJREhhJjK JAAKMUU4LBqLq7ycXVeEpih0BKJDJolUee386IML+ealsznQF+Vj/72Ze1/Zn1luTlEUfI7kusK7O4M8 t6eLpp7QkPcQQggxNUgAFGKK8TksnFlXxOwSF13BKP7I4d5ARVG4cn45/7W6jotmlvCzVw7wofs38b9b Womngp6mKpS4rDgtGu+0DvD83i4O9UkQFEKIqUQCoBBTkJZaT/jcGcXomkp7YGjJmEK7zr+umsvP1iyi 3G3jO0/t4ppfv84zuzsz1xBadZUytxWbpvJmSz/P7+2irT88IZdjFEIIcWIkAAoxhRXYdc6cXsis4mRv YDA6tO7f8hof/3X1aXzvynkoCnz5ke18cv1bbDrYm9nGpicnilg1hdeb+3h1fw/dwagEQSGEmMQkAAox xWmqQkOpm7PqijCBjkCEwdlNURQubCjhweuW8433zqIzEOGW37/D3/1xCzvaD69vaNc1yt02InGDV/f1 8PL+Hjr9EQmCQggxCUkAFCJP+BwWzq4rZGaxi95QbMi1gQC6qvCBBRX8/pMr+MJ5M9jWNsB1D7zB1x/b QVNvKLOd26ZTVmAjkTB57WAvL+zt5lBfiJjMGhZCiEkjZ2sBCyHGn66pzCp1Y/o9dJgK7YEIRQ4runp4 iUW7rnHd8ho+sKCCX73exANvNPP07k4+tLCCm1ZOo8SVLBbttGo4rRrhWIK3Dg2gKgPU+hzU+hy4bfKr RQghJjL5LS1EHnLbdGZWFLG/O8iuzgAKyR5CbVAQLLDrfPacOq5eUsW9r+znD+8c4k/b2rh2WTUfX16T CXl2i4bdopEwTJp7Q+zrDlLsslJX6KTIaUHXZKBBCCEmGgmAQuSp9Ezhap+d/T0h9nYFUBWFQocFVTkc BEtcVr52ySyuXVbDT17exy82HuShtw9xwxm1XLW4Cltq+TlNVTJLyQWicV5v6kVTVSoKrFR57BQ6rUMC phBCiNyRAChEnrPpGrNL3UzzOdjXHWJfdwBdU/DahwbBaYUO7lg1j+uXD3D3i/v4z+cbWf9GC2vPnMYV c8uwDOrpc1l1XFadhGHSFYjS3BdG11TqCh2Uum14bDqqhEEhhMgZCYBCCCA5lDu33M30IgeN3QH2d4ex agpeu44yKAjOKy/gng8tYuOBHu5+cR/fenIXP/xrI6vmlrN6QTkNJa7Mtpqq4LFb8ABxw6SxK8juzgCa olDitlJRYMNjt+CyakP2IYQQIrskAAohhnBYNOaXe5juc7Kr08+h/gg2XcVjGxoEz5hWyC9rfby8v4cN W9v43VstPPBGMwvKC/jAwnIunV06ZDKIrioUpyaQGKbJQDhO+0AUExNdVShx2yh1WSiwWSiQHkIhhMgq CYBCiBG5bDpLqn3UF8fY3RGgdSCC06JRYD/8a0NRFM6uK+LsuiJ6glEe29HBhq2t/OvTu/mP5/bynlkl fGBBBUurPUPCo6oouG06blvyfsIw6Q/FaB8IY5gKmgqlbhtlLiseuwWnVZPrB4UQYgzlLADu3LmTq6++ OnN/7969fOtb3+ILX/hC5rG//OUvfOADH2DGjBkAfOhDH+L2228f70MVIq957BaW1froC8XY0T5A20AE j13HYdGGbFfotHLtsmo+trSKrW1+Nmxp5f/e7eDR7e3U+uysnl/BlfPLKE2nvkE0NR0Ik7+SDgfCCCaA aeKy6bgsGk6bhtuqYdc1dE1FVZK9izZ9YodEwzAxTJOEaWKYyXM0TBPTBEUB04SEaRJPmMQSBtGEgd2i YVEVNFVBVZJfdVUhnaWHFvROBmuLzLoWQoxCzgLgnDlzePPNNwFIJBJUV1fzwQ9+cNh25513Ho888sg4 H50Q4kheh4UzphXSGYiys91Puz+Cx6ZjPyIIKorCwooCFlYU8MUL6nlqVycPb23lnpf28ZOX93FOXRHv m1fG8hpvZtbwkQ4HwsOPReMG/mic3nCMWMJMBkNM4HAaclg0ClJB0mXVsOoqVk3FoimZHkiFZFhSSAap uGESiSdIL5Wcfl5VFBKGScIwiaf+G7zqiaIomKZJwoR4wiBmmETjBnEjGeDihkHMgEgsQSRhYKReq6Ac Pvb04ZuD3jP1uKYqyYCIktzENDOnijlC0FWS76kpSmoSjobLpuG06Fi1ZDC06ipaqh20VLAUQoyv/nCM 1v4I9cXOnJbJOqUA+P73v/+YF24//PDDo3qfp59+mpkzZzJ9+vRTORwhRJYpikKp20aJy0pnIMq21gHa /VG8dj1TDmYwu0XjyvnlXDm/nAM9If60rY0/bWvjhcZuIDmz+LRKD6dVeVhS5WF6oeOov1Osuor1OIsX xRLJkNgTihE30jHrcMpKhq/U/VSgCnT14BqwgDJ4SbvU8yipl2YS2uAtUr2T6cCYDI2HvyZv23QVp1Ub MqM6mwzTJJYw6Q3F6PBHSKTOIx0glVSKNFOB2Qj4CVsDuG06lnRQTIVFIcTYSBgm3cEo+7tDdAQiJAyT 2kIHunb812bLKQXA2267DYA//OEPtLa2ct111wHw4IMPUl5ePur3Wb9+PR/96EdHfO7ll1/mtNNOo6qq iu9973ssWLDgVA5ZCDEG0kHw3Horh/rC7O0O0heIoingtekj/lU7rdDBZ8+p42/Pms6WQ/282dLPW4f6 eX5vF3/a1gaA166zuMqTCYXzywtGDJZHY9HUEx4CtYQs+Nwj90RORqqiYNOVUbVbLGHQGY6zpyuQDIqm kgzCqR5Il1WnwKZR6LTgtiVna8sQsxDHF0sY9IVidAdj9Edi9ITixBMGTotGmdtGRyCa60NEMcdgJfcV K1awadOm4z42kmg0SlVVFVu3bh0WGvv7+1FVFbfbzWOPPcatt97Krl27hr3HunXrWLduHQCtra1s3Ljx qPvr6OigtLR0NKc1pUk7JOVrO4z1eZumSThu0BWIcqg/TCxhYtdVHNbj/3lrmiZN/TG2dITYmvrvYH8M AF2FWo+VYodOsVNPfnXolDjTXzUK7fopDWX6e7tx+4pO+vXHYpgm0cTg/wxiqdsJk9QQb/KrYZL6L3nb TN0GsGhKsldOUw7/pypDHtcUTqqUztHO3zQhZhjEU8edvlbRpql47DpeuwVHajnA8erdzKZ8/V2Qlu/n P9jJtkU0btAfjtHuj9IXjmGaZHrVLaqKOuhvp95QnGU13hP6A/dkrV69esQ8NibXAAYCAfbu3Ut9fT0A jY2NBAKBUb328ccfZ9myZSP2GHo8nsztVatW8ZnPfIbOzk5KSkqGbLd27VrWrl0LJINnVVXVMfd5vOfz hbRDUr62QzbOeybJoY6eYJR9qaEOq6YOqyV4pMJSWDTz8P3eUIy3D/XzVkt/5n0OtIXpCkRJHPEnqwIU OS2Uum2UuqyUuKyZUKIpDJlAoabua+khWhUiAZWCkJHaXiFhmoTjCaLxZPCJxJP/He125n7CIHrEc+lh 6PGgKlBg0yl2WSlxWpNfXRaKnck2KXZZKXZaKHFZKTiipI+vZPQjNrGEQThm0JpIYIZBiSj4HBbKC2z4 HBYcluQQ8mSs65ivvwvS8v38BzteW5imSSCaIBhN0BuK0eaP4I8kUBQLTm8B00uOXds0FohSUVk8bDLd eBqTAHjXXXdx4YUXUl9fj2ma7N+/n5/97Gejeu2DDz541OHf1tZWysvLURSFjRs3YhgGxcXFY3HIQogs 0VI1/UrcNvyROHu7AsmVQFJFofVR9Nb5HBbOry/m/Pqh/94ThklPKEZnIEqHP0JHIEqHP5r6GqHNH2Fr 2wChWALDSM6qTRjpCSPH0n7M87FpKjY9eV1c5ramYtMVPHY9dc2cgl3Xkr1zqe2senLb9G1r6rUWTU3O 5k29v6KApgz+erhHzyQZuiJxI/k1YWTCaTQVOiOp5wfCcToDUbqCUd5q6aMzECV6ZGIm2SuRDoYlNqgv D1HrdVDrs1Pjc1DstBz1wys9zF6Q+vhI9/6+2+FP9VgmZyqXuKyUu60U2C04LZrUdRSTmmGY+KNx/JHk NcZt/RGihgmYWFQVh0WjbJJdSjImAfDyyy9n165d7NixA4C5c+disw0v9XCkQCDAk08+OSQs/vSnPwXg lltu4aGHHuInP/kJuq7jcDhYv379pPyrUoh85bbpLK7yMrPYRVNfmP09IRJG8jqYk1n9Q0sFixKXlbll 7lG/Lj1bN12KJZ76apjQ09mOu7AkOePXTJeUOTwRYjSBdaJK91J0BqKZ/7qCMboCUTqDyfvvdgV44cDB IT2rDotKrddBjc9Orc9Brc9BjTd5u9RtHTLkqygKDos2pCcjYZj0hWK0DoQxU9cT+uwWfA4LXocFu65i t6jYcnkFvBDHEY0b9KZ+jlsHIiSM5IiDTVdwWTW8k/x62DErA/P666+zb98+4vE4b731FgDXX3/9MV/j crno6uoa8tgtt9ySuf25z32Oz33uc2N1iEKIHHHZdOaUuZlZ7KQ7GGN/T5DOQPI6v/RMWYcle3X8FEVB V1I7O5JDxzdCbcKpQFEO11esK3KOuE1vZxvuwlIODUQ42BviYG+Ypt4QB/vC7OkK8vze7iFD2TZNpa7I wcwSFzOLncwsTn6tKLBlAv2RdR0N0yQSNzjYG2JvdyB1PWGyp9Bj01Ole5Ih0m7RpMdQjLto3CAcTxCJ GzT1hjgQ66EvFMMwwaGr+OyWKVc2aUwC4Mc//nH27NnDkiVL0LTkX3SKohw3AAoh8ouuqZQV2CgrsBFL GAxE4vSH43QHonSHkvX9VAVcVg27PjmvI5uMdE3N9PQdKWGYtA1EONiXDIcHekI0dgfZdLCXx7YfHjp3 WTVmFDkzobC+2ElDiYtipwV1hF7C9HtHEwaHBsLEepND9aaZ/Bnw2C347BYK7BoOi57qNZzYxb7FxGea Jv3hOB2BCMFogmjCoD8UJ5owMmWeQn1hyuzGMS+FmArGJABu2rSJbdu2TemGEkKMLYumUuS0UuS0Ulfk zFxj0xOMcWggQmcghomJmuop0lKTNrTUhI705I7ROLKA82hfM3hbMzM718zM1k2kVvLIfDUOh5jDO0z/ L/WYqRwu6Iw5rMygOXib9NTb1LZHvOnQx83kPtLXF+qagq6e+hC2pipUee1Uee2snDb0uf5wjL1dQfZ0 BdnTFWBPV5Dn9naxYWtbZhuvXWdmsZP6YteQcOhzJHtUHOrwYGimegwPDYQ50JsqwJ1aLiVd7Ntp03Dq yR5Dq65iT11vKZ9DIs0wTEKpQuyhaILuYJTOYIxwLIGuJmfQq4qCy6bjHfTvpDc0vMD9VDQmAXDhwoW0 trZSWVk5Fm8nhMhDamqSiMduYXqRM1nUOdVDGI4nUit2pCY/xBOEI6nVNVLBJxmUkpMQDset5POKejhP JbOEiZl6XSAUJxaIQirwZTJX6k3S99MTNFRVyays4UiVYtFVFYueDlygqWom1OmpbY4Mk5AMoyPFlXRp GDhcDmZwSFQ4vBJJctvDwTQYixOIJAjFDQKRwT0bZubN0wFaVxViieQ1kSdTRsZjt7Ck2suSau+Qx7uD 0WQo7AykwmGQx3e0E4gmMtsUOy3JYeQiZ2Y4eUaRE3dqhrI9NRx8pHSx78MrwhwOwIoKHptOodOC127J TMCx6WpOV1wQ2RdLTYgKxhJ0BaN0BaL4I3GM1O8DBRObpuGwqHhsOVsEbUIZk1bo7Oxk/vz5nHHGGUMm f4x2JRAhhDiSRVMpdFqPulwcHJ7UYZjJFT8ME+KJZM+cpqTDmTLkw99Mhan06w4dilFRWYzC4VIxR4a1 ydyrlEgtdRdNrTEcS5iEY8lrnUKxBEHIDIUN7mlTlMN1BvXMGsSja4d0z+7ptb7MY6Zp0u6PZnoK96Z6 Df+wpZVI3MhsV1FgGzaMXFfkwJ6aMHKsYt/pnsPm3jD7jCCHlwkEq6bgtCULWzv0ZP1Cq56sz6ZrSmap v8n8vc4H6e+xPxKnMxilN5ScmRs30j9DChZVwW5RKXZa5ft5DGMSAL/5zW+OxdsIIcQJUVUF9cg+NMux X6Okyq2kX2fRjj0bdbJ/gGiqgtOqM/IUEGjRglRVlWCmZkcnL4Y3CEbj+CMJBiJxQrEEfQkD0zg8JK1A ZhjNqimpcjZHbytFUSgvsFFeYOPsusOFpw3TpCU14WRwOHz1QG9m8omqQI3XQX3x0GsMpxc6hoTBY/Uc xg2TeMKgYyBBzDAyvabp3tFAdw/b/ckyRYPL/dgsKnZdS/YiqsrhIfbUf8c7b3HiTDPd05/84yUYTdAT itEbihGOG5nLLKxacujfYzu1YvD5akwC4AUXXMD+/fvZtWsX73nPewgGgyQSieO/UAghxISQ7vGzaCou GxS7hve8Dp4pGYkn8EcT+CNxBiKpHkSDzFJypIa303UR09dbHUlVFGp8Dmp8Di6YebjuYzxhJGciZ4aR A6lZyV2kJyVrqsL0QseQYeSZxS6qvfZhgSAZ2DTsR/kDwRKy4HNZk+WAUpNTQrEEiWDyfnrVlvRyeel1 pZVUj1P6HB2W5Ao4dl3FqmnoqV5Ui6akVoPI76BiGGambmU0VdsyZpjEDYNAJDEk5KUpkLnG82TKR4mR jUkAvPfee1m3bh3d3d3s2bOH5uZmbrnlFp5++umxeHshhBATgDVVDPto4qkP8/SKKKFogoFonL5Qsnhu IpXcdDVVNPsYdRZ1TWVGUfK6wPcMejwSN9jfE8z0FO7uCrCtzc+Tuzoz2wwuVVNflBxGPrJUzdGkr48c rcE1JtOhMTYQIZG6LOHIa1JteqrcjZ4MhVqqLUbqYbRo6qTr2UoP0cZSl2LEU2GvPxynO5S8Ls8kNdsp FaTTFZosmoS88TQmAfCee+5h48aNrFy5EoBZs2bR3n70yvpCCCGmHl1T0TVGXN7KNJMzMoPRBL3h5HBe fyhO1DBIz7hJr6hg1Y4+rGrTVWaXupldOrQQeDCaoLF76DDyiZSqOVnHrDE5gniqt6svlMjMIDfMdA9j OhiRng6OnupVtKgqFj053G5Jze5OhtXkpCNNSc78Tk8QSs6WT/awKgqZpQ4H90Aahpk5Hn8kTlcgSjzV AxpLGMmeT8zkqjqp22npwukAKslgHkkYBKPJ80peYXE4AFu0ZNCV6/ImjjEJgDabDav18HBBPB6Xb7AQ QogMRUldi2jVKRlUeDuW6jULRhP0BGN0h5KrlSTD0OHJKOnl9I5W+sdp1VhQUcCCioIhj4+2VM00j4U5 FQPDStWMtfRQ9Gg/fRODAlkoljg86Skz+Sk9USldTig5RJ2c95oMZwzaBpRMZaHkLHpAUQh09+OK2ElO fT8cHNOBMn3dbHrW9ZHfB01NDoVP9dp5U8mYXQP4r//6r4RCIZ588kl+/OMf8/73v38s3loIIcQUlp7V 67FbqPDYgcP128Jxg1AszkA4ORmlJxQjYaYmoCjJnsbj1f47bqmargB7OoO829bLEzva8Y+yVM14OdEh 6eM5Wk3M9DWQIn+MyU/xd7/7XX7+85+zaNEifvazn7Fq1SpuvvnmsXhrIYQQeUZVk8V5XTaAw6HENE2C 0QTBWLq3MEZXMEpy7omSnIAxytVCjixV09vZhre4bExK1Uxk0jsn0k45ACYSCRYsWMCOHTv41Kc+NRbH JIQQQgyjKOlgqFOaGkY2DJNANMFAJEa7P0q7P4KR6iV0WpKFf0cbeo5ZqqY/zJ7OodcYbjzYSyx1IZwC 1PjsmbWRj1aqRoiJ4pQDoKZpzJkzhwMHDjBt2rTjv0AIIYQYI6qqUGDXKbDrVHkdGIbJQCROXyhGmz9C dyiGYZqopNcjPvHl4lRFocbroMZ7lFI1qWHk0ZaqqS92UuN1TLoZvmJqGZMh4J6eHhYsWMAZZ5yBy+XK PC4rgQghhBhPqqrgdVjwOixMK3ISTxjJQBiO0z4QSQ4Zm8kVX+y6itOqjXpN6SMNKVUz6/Dj2S5VI8RY GJMAGA6HeeSRRzL3TdPkK1/5yli8tRBCCHHS9EFLCtYVOUkYJoFonIFwnLaBCJ2B5DWEgVAMPRI/pUCY diqlapwWbdiKJ+lSNRIMxVgakwAYj8e54IILhjwWCoWO+ZqdO3dy9dVXZ+7v3buXb33rW3zhC1/IPGaa JrfeeiuPPfYYTqeT+++/n2XLlo3FIQshhMhDmqrgsVvw2C1U+5JDxv5onL1KAMOm0xmMZq4hTE8qOdVA mHbMUjXdwcww8t6jlKqpT4XC9DDyzGJXVkrViPxwSgHwJz/5CT/+8Y/Zu3cvixcvzjw+MDDAOeecc8zX zpkzhzfffBNITiSprq7mgx/84JBtHn/8cXbt2sWuXbt49dVX+fSnP82rr756KocshBBCZKipQFhWYKOq ypcJhAPhOK0DEToDEdILv9lTq3iM9bV7HruFJVVellQdu1TNnq7ghCxVIyanU/oJ+djHPsYVV1zB1772 Ne68887M4wUFBRQVFR3jlUM9/fTTzJw5k+nTpw95fMOGDVx//fUoisKZZ55Jb28vhw4dorKy8lQOWwgh hBiRekQPYcIw8Ufi9IdjdASidAaiJIxkJDyRsjMn48hSNZAcGTuRUjX1qR7DyVSqRoyPUwqAXq8Xr9fL gw8+eEoHsX79ej760Y8Oe7y5uZna2trM/ZqaGpqbmyUACiGEGBfaoEkltYVODMMkGEskA2Gq7EwitWyb TVNxWjT0LJZ9GW2pmvTqJ8cqVZMeRp5e6Mja8YqJK+d9xNFolIcffpg77rjjpN9j3bp1rFu3DoDW1lZa WlqOum1HR8dJ72cqkXZIytd2yNfzHkm+t0W+n3/aybRDqQIlbpNwPLkGbm8oRmt3lHgcTEw0VcGmq9g0 NbU2bna5gdO8cJrXBvU2oJC4YdI8EGV/b5TG3gj7+qLs7RgYWqpGgWq3xoyiFmZ4bdT5rNT5bFS6LXlZ qsbf2531fQRCcVqdUWx67mpE5jwAPv744yxbtozy8vJhz1VXV3Pw4MHM/aamJqqrq4dtt3btWtauXQvA ihUrqKqqOuY+j/d8vpB2SMrXdsjX8x5JvrdFvp9/2li1QyiWIBCJ0xeO0RWI0RuKYaTW0LVpyWHj8SwO XVIGpx3xWLpUTbqncEdLN7t74jy335/ZJl2qZvAwcr6UqvGVDM8kYykWiFJRWYzDkrsh+ZwHwAcffHDE 4V+A1atXc/fdd3PNNdfw6quv4vV6ZfhXCCHEhJYsOK1R4rYxs4TMsLE/EqczdR1hbziOiYlD03DZxm6m 8WgdWaqmt9OBr6R8SKmadDh8vamXx3eMXKpmcDiUUjWTS04DYCAQ4Mknn+RnP/tZ5rGf/vSnANxyyy2s WrWKxx57jIaGBpxOJ/fdd1+uDlUIIYQ4Kaqq4LbpuG06FR47AOFYgr5wnEP9YdoGIhimiVVTcVuzew3h 8RytVM1AOM6e7sAxS9V4bDozS6RUzWSR0wDocrno6uoa8tgtt9ySua0oCvfcc894H5YQQgiRVXaLht2i UV5gI54w6A0lJ5W0DkQIh2LJeoU2fcKsI1xg10+tVE16jWQpVTNhSOsLIYQQOaRrKiVuGyVuG3PL3QxE 4nT4IxzoDdMTjqGi4LJq2PUTX8c4245XqiY9jCylaiYeCYBCCCHEBKEoh+sQ1he76A/H6QnFkkWpg1FM M3n9ntuqT9gZutkqVTNRekOnCgmAQgghxASkKIdrENYVOYklDPpSYfDQQISEYaCg4LRoOCwTr3fwSKqi UON1UON1cMHM4szjccOkqTfE7q6h1xi+sLcrVWMxWY9xus8xZBi5vthJjdcxYYPwRCcBUAghhJgELIOG iueVm/SHY/SF47QN6h10WjRcVm3Ch8HBdFWhrshJXZGT98w6/PiRpWp2dwXY1ubnyV2dmW1GKlVTX+Sk wmMb95nVk40EQCGEEGKS0VSFQqeVQqeVuiIn0bhBXzjG/u4QHYEoqgJe+8SZRHIyjixVkyalasaGBEAh hBBikrPqKqVuG6VuG8FonNb+CPt7QvSEYlg1lQLbxL1m8ERJqZqxIQFQCCGEmEKcVp36Ep26Iid94eQ1 g019YeIJA6um4rHrU3J49FilavamhpBHU6qm0pZgUcwx5UvVTN0zE0IIIfKYOmiYeHapm75wjJa+MM19 YUxMCqw69hwuRTZe0qVqVoyiVM0ft7QSjhvwarLXcCqXqpEAKIQQQkxxmqpkgtDsUjftAxH29wRpD0TR FcA47ltMKccqVbNjXxMdhnPKl6qRACiEEELkEauuUlPooKbQwUA4Tkt/mK3dHcT9ERx6btYmnihURaGq wMr8kuJTLlWTnoQyUUvVSAAUQggh8lSBXWeO3Y0z6sPu89Hcd3htYpdVw2WVmAAnWKqm/filanwOC6Zp 5uBMDpPvrBBCCJHnNFXJzCKOpdYm3tMZoH0ggsOi4bZNrtqC4+V4pWr2ptdJPqJUjV1XWbO4MheHnCEB UAghhBAZFi1ZUqbEZaUnFGNfd5C2gQiqouCx6Vj1yXOdW64cr1RNY3cINcfDwhIAhRBCCDGMohyeOBKJ J2jrj7CnK0hvOI5NVyb0esQTVbpUTbXXketDkQAohBBCiGOz6RrTipzU+Bx0B6O0+SO09EeIJ0w8Ni0v yslMNTntx+3t7WXNmjXMnTuXefPm8fLLLw95/i9/+Qter5clS5awZMkSvvWtb+XoSIUQQgihqgolbhsL Kjxc3FDCkqoCDKB9IEJ/OJbziQ1i9HLaA3jrrbdy+eWX89BDDxGNRgkGg8O2Oe+883jkkUdycHRCCCGE OBpNVaj0Oqjw2OkNxTjQE6I1NYPYocvEkYkuZwGwr6+P559/nvvvvx8Aq9WK1WrN1eEIIYQQ4iQoyuEV R+anZhA39YZoG4igKAo+u44+iQok54ucfUcaGxspLS3lhhtuYOnSpdx8880EAoFh27388sucdtppXHHF FWzdujUHRyqEEEKI0UjPIF5a4+PChhJmlbjoiyRoD0QIROMyRDyB5KwHMB6Ps3nzZn70ox+xcuVKbr31 Vu68806+/e1vZ7ZZtmwZ+/fvx+1289hjj/E3f/M37Nq1a9h7rVu3jnXr1gHQ2tpKS0vLUffb0dEx9icz CUk7JOVrO+TreY8k39si388/Ld/bIVvnbwfmukx6g1Ha+6K0hWJYUzOIJyp/b3fW9xEIxWl1RrHlsKRO zr4DNTU11NTUsHLlSgDWrFnDnXfeOWQbj8eTub1q1So+85nP0NnZSUlJyZDt1q5dy9q1awFYsWIFVVVV x9z38Z7PF9IOSfnaDvl63iPJ97bI9/NPy/d2yOb5T0t9DUTibG/30z4QwW2buCuN+ErKs/r+sUCUispi HDmcPZ2z6FlRUUFtbS07d+4E4Omnn2b+/PlDtmltbc10F2/cuBHDMCguLh72XkIIIYSY+Fw2neU1XlZO L8SqqbQNhBkIx3N9WHkpp9H7Rz/6Eddeey3RaJT6+nruu+8+fvrTnwJwyy238NBDD/GTn/wEXddxOBys X79eZhQJIYQQk5iiKBS7rBQ5C5NLznUFafdHsGoqXrsun/PjJKcBcMmSJWzatGnIY7fcckvm9uc+9zk+ 97nPjfdhCSGEECLL0rOHVzitDITj7O0K0NIfxqIqeB0WVAmCWTUxB9+FEEIIkTcK7DqnVXtpKHGxvyfI gZ5QMiA6LLLcXJZIABRCCCHEhOCy6cyv8FBf7OJgb4jGruQCET4JgmNOAqAQQgghJhS7RWNWqZtphQ4O 9ITY0xVAVxW8dhkaHisSAIUQQggxIdn0ZBCs8Tlo7AqwvyeMRQWPXXoET5UEQCGEEEJMaA6LxvwKD9ML nezrDtLcHyFhGLitOk5r7mrpTWYSAIUQQggxKbhsOgsqPcwpM+gJxdjVGaB9IILTquG2SaQ5EdJaQggh hJhU9NSawyUuKz2hGHs7g7QNRLDpUktwtCQACiGEEGJSUhSFIqeVomlW+sMxGruCtPSH0VWFApuORcvd WrsTnQRAIYQQQkx6HrslU0uwdSDMgd4wPaEYBTY9p2vuTlQSAIUQQggxZbhsOjNtbuqLXXQFouxo99Pu j1DksKBLj2CGBEAhhBBCTDmKolDitnG200pzX4itbQOp9YYtuT60CUGisBBCCCGmLFVVqC10ct6MYgps Om0DEcKxRK4PK+ckAAohhBBiynPZdFbU+jhjmo+ECe3+CP5IPNeHlTMyBCyEEEKIvJAeFj7PZaU7GGNP V4C21PWB+TZjWAKgEEIIIfKKoigUu6wUOS209IXZ2jqApir4HPlzfWBO425vby9r1qxh7ty5zJs3j5df fnnI86Zp8vnPf56GhgYWL17M5s2bc3SkQgghhJhqFEWh2ufgvJnFFDostA1EiCXMXB/WuMhpALz11lu5 /PLL2bFjB2+99Rbz5s0b8vzjjz/Orl272LVrF+vWrePTn/50jo5UCCGEEFOVw6KxtMbL8hovwWgiL64N zFkA7Ovr4/nnn+emm24CwGq14vP5hmyzYcMGrr/+ehRF4cwzz6S3t5dDhw7l4GiFEEIIMZUpikK5x85p 1R4URaEnFM31IWVVzgJgY2MjpaWl3HDDDSxdupSbb76ZQCAwZJvm5mZqa2sz92tqamhubh7vQxVCCCFE nnBYNM6cXkiBTacrMHVDYM4mgcTjcTZv3syPfvQjVq5cya233sqdd97Jt7/97RN+r3Xr1rFu3ToAWltb aWlpOeq2HR0dJ33MU4m0Q1K+tkO+nvdI8r0t8v380/K9HfL9/AdLt0WVZuIP+tnXHcNnt4AydvsIhOK0 OqPY9NxdiZezAFhTU0NNTQ0rV64EYM2aNdx5551DtqmurubgwYOZ+01NTVRXVw97r7Vr17J27VoAVqxY QVVV1TH3fbzn84W0Q1K+tkO+nvdI8r0t8v380/K9HfL9/AdLt0VVlcm7HX72dgXx2sduTeFYIEpFZXFO 1yjOWfSsqKigtraWnTt3AvD0008zf/78IdusXr2aX/3qV5imySuvvILX66WysjIXhyuEEEKIPKOpCvPK Czi7rhAjVTw6HJ8aq4jktA7gj370I6699lqi0Sj19fXcd999/PSnPwXglltuYdWqVTz22GM0NDTgdDq5 7777cnm4QgghhMhDhU4r584oom0gzI6OAP3hCMVOK5o6huPC4yynAXDJkiVs2rRpyGO33HJL5raiKNxz zz3jfVhCCCGEEEOoqkKl10Gp28b+niDvdgSwpIpHK8rkC4KyEogQQgghxCjpmsrMEjcVBXb2dgdp6g1h 1VS8dn1SBcH8WvhOCCGEEGIMuGw6iyo9nFdfTLHLQkcgOqkKSEsAFEIIIYQ4SW6bzpJqH+fMKELXVDoC EQxz4i8nJwFQCCGEEOIUeewWzpxeSH2xiw5/lHBsYs8WlgAohBBCCDEGNFVhdqmbM+sKiSRMuoJRzAna GygBUAghhBBiDBU5rZwzo5Aqj512/8S8NlBmAQshhBBCjDGbrrGw0kONz8G7HX7a/REUBQod1lwfGiAB UAghhBAia3wOC2dMKyQcS9A6EGF72wAJI/fDwhIAhRBCCCGyzG7RqCtyUuKysqczgJbjmoESAIUQQggh xonbpnNatTfXhyGTQIQQQggh8o0EQCGEEEKIPCMBUAghhBAiz0gAFEIIIYTIMxIAhRBCCCHyjARAIYQQ Qog8o5gTdZG6k1RSUkJdXd1Rn+/o6KC0tHT8DmiCknZIytd2yNfzHkm+t0W+n39avrdDvp//YFOtLfbt 20dnZ+ewx6dcADyeFStWsGnTplwfRs5JOyTlazvk63mPJN/bIt/PPy3f2yHfz3+wfGkLGQIWQgghhMgz EgCFEEIIIfJM3gXAtWvX5voQJgRph6R8bYd8Pe+R5Htb5Pv5p+V7O+T7+Q+WL22Rd9cACiGEEELku7zr ARRCCCGEyHcTPgAePHiQiy66iPnz57NgwQJ+8IMfANDd3c173/teZs2axXvf+156enoAME2Tz3/+8zQ0 NLB48WI2b94MwLPPPsuSJUsy/9ntdv73f/93xH1efvnl+Hw+rrzyyiGPX3vttcyZM4eFCxdy4403EovF snfiRxirdgD48pe/zIIFC5g3bx6f//znOVon8B133EFDQwNz5szhz3/+c+bxG2+8kbKyMhYuXJjFMx7Z RGmHox3HVD/vcDjMGWecwWmnncaCBQv4p3/6p6ye90gmSlukJRIJli5dOuz3RbZMpPOvq6tj0aJFLFmy hBUrVmTxrIebSO3Q29vLmjVrmDt3LvPmzePll1/O4pknTZTz37lz55DPVo/Hw3/+539m9+SPMFHaAuCu u+5iwYIFLFy4kI9+9KOEw+EsnvkpMie4lpYW8/XXXzdN0zT7+/vNWbNmmVu3bjW/9KUvmXfccYdpmqZ5 xx13mF/+8pdN0zTNRx991Lz88stNwzDMl19+2TzjjDOGvWdXV5dZWFhoBgKBEff51FNPmQ8//LD5vve9 b8jjjz76qGkYhmkYhnnNNdeYP/7xj8fyVI9prNrhxRdfNM8++2wzHo+b8XjcPPPMM81nn3122P62bt1q Ll682AyHw+bevXvN+vp6Mx6Pm6Zpms8995z5+uuvmwsWLBiHMx9qorTD0Y5jqp+3YRjmwMCAaZqmGY1G zTPOOMN8+eWXs3beI5kobZH2H//xH+ZHP/rRYb8vsmUinf/06dPNjo6OcTjr4SZSO1x//fXmvffea5qm aUYiEbOnpyfLZz+xzj8tHo+b5eXl5r59+7J45sNNlLZoamoy6+rqzGAwaJqmaV511VXmfffdl/0GOEkT vgewsrKSZcuWAVBQUMC8efNobm5mw4YNfOITnwDgE5/4RKY3b8OGDVx//fUoisKZZ55Jb28vhw4dGvKe Dz30EFdccQVOp3PEfV5yySUUFBQMe3zVqlUoioKiKJxxxhk0NTWN4Zke21i1g6IohMNhotEokUiEWCxG eXn5sP1t2LCBa665BpvNxowZM2hoaGDjxo0AnH/++RQVFY3PiR9horTD0Y5jqp+3oii43W4AYrEYsVgM RVGydt4jmShtAdDU1MSjjz7KzTffPD4nz8Q6/1yaKO3Q19fH888/z0033QSA1WrF5/PlzfkP9vTTTzNz 5kymT5+e3ZM/wkRqi3g8TigUIh6PEwwGqaqqGp9GOAkTPgAOtm/fPt544w1WrlxJW1sblZWVAFRUVNDW 1gZAc3MztbW1mdfU1NQM+2Bev349H/3oR0/6OGKxGL/+9a+5/PLLT/o9TsWptMNZZ53FRRddRGVlJZWV lVx22WXMmzdv2D5G0465NlHaYfBxjIdcn3cikWDJkiWUlZXx3ve+d9zOeyS5bosvfOEL/Nu//Ruqmptf pbk+f0VRuPTSS1m+fDnr1q3L5qkeUy7bobGxkdLSUm644QaWLl3KzTffTCAQyPIZD5Xrn4O0U/1sHQu5 bIvq6mpuu+02pk2bRmVlJV6vl0svvTTLZ3zyJk0A9Pv9fPjDH+Y///M/8Xg8Q55L98qNxqFDh3jnnXe4 7LLLTvpYPvOZz3D++edz3nnnnfR7nKxTbYfdu3ezfft2mpqaaG5u5plnnuGFF17I5iFnxURph2MdRzZM hPPWNI0333yTpqYmNm7cyJYtW074PMZCrtvikUceoaysjOXLl5/U8Z+qXJ8/wF//+lc2b97M448/zj33 3MPzzz9/wudxqnLdDvF4nM2bN/PpT3+aN954A5fLxZ133nlS53Iycn3+adFolIcffpirrrrqhF87VnLd Fj09PWzYsIHGxkZaWloIBAL85je/OalzGQ+TIgDGYjE+/OEPc+211/KhD30IgPLy8szQ7qFDhygrKwOg urqagwcPZl7b1NREdXV15v7vfvc7PvjBD2KxWAB49dVXMxevPvzww8c9ln/+53+mo6OD73//+2N2fqM1 Fu3wxz/+kTPPPBO3243b7eaKK67g5Zdf5o9//GOmHTZt2nTcdsylidIOIx1HPpx3ms/n46KLLuKJJ57I 9qkPMxHa4sUXX+Thhx+mrq6Oa665hmeeeYbrrrsub84//d4AZWVlfPCDHxz3oeGJ0A41NTXU1NRkesLX rFkzZFLBVD//tMcff5xly5aNOGQ6HiZCWzz11FPMmDGD0tJSLBYLH/rQh3jppZfGsRVOUK4vQjwewzDM j3/84+att9465PHbbrttyMWdX/rSl0zTNM1HHnlkyMWdp59++pDXrVy50nzmmWeOu99nn3122EXd9957 r3nWWWdlLvAcT2PVDuvXrzcvueQSMxaLmdFo1Lz44ovNhx9+eNj+tmzZMuQi1xkzZgy54LexsTEnk0Am Sjsc7TiyZaKcd3t7e+YC92AwaJ577rnmn/70p+yd+AgmSlsMNtLvi2yZKOfv9/vN/v5+0zRN0+/3m2ed dZb5+OOPZ/HMh5oo7WCapnnuueeaO3bsME3TNP/pn/7JvO2227J12hkT6fxN0zSvvvpq87/+67+ydLbH NlHa4pVXXjHnz59vBgIB0zAM8/rrrzd/+MMfZvfkT8GED4AvvPCCCZiLFi0yTzvtNPO0004zH330UbOz s9O8+OKLzYaGBvOSSy4xu7q6TNNM/iB85jOfMevr682FCxear732Wua9GhsbzaqqKjORSBxzn+eee65Z UlJi2u12s7q62nziiSdM0zRNTdPM+vr6zHH88z//c/ZO/Ahj1Q7xeNxcu3atOXfuXHPevHnm3//93x91 n9/5znfM+vp6c/bs2eZjjz2Wefyaa64xKyoqTF3XzerqavPnP/95dk9+kInSDkc7jql+3m+99Za5ZMkS c9GiReaCBQvG9d9A2kRpi8HGMwBOlPPfs2ePuXjxYnPx4sXm/Pnzze985zvZP/lBJko7mKZpvvHGG+by 5cvNRYsWmR/4wAfM7u7u7J68ObHO3+/3m0VFRWZvb292T/ooJlJb3H777eacOXPMBQsWmNddd50ZDoez e/KnQFYCEUIIIYTIM5PiGkAhhBBCCDF2JAAKIYQQQuQZCYBCCCGEEHlGAqAQQgghRJ6RACiEEEIIkWck AAohxBj75je/yfe+971cH4YQQhyVBEAhhBBCiDwjAVAIIcbAv/zLvzB79mzOPfdcdu7cCcAPf/hD5s+f z+LFi7nmmmtyfIRCCHGYnusDEEKIye71119n/fr1vPnmm8TjcZYtW8by5cu58847aWxsxGaz0dvbm+vD FEKIDOkBFEKIU/TCCy/wwQ9+EKfTicfjYfXq1QAsXryYa6+9lt/85jfouvy9LYSYOCQACiFEljz66KN8 9rOfZfPmzZx++unE4/FcH5IQQgASAIUQ4pSdf/75/O///i+hUIiBgQH+9Kc/YRgGBw8e5KKLLuK73/0u fX19+P3+XB+qEEIAcg2gEEKcsmXLlnH11Vdz2mmnUVZWxumnn46iKFx33XX09fVhmiaf//zn8fl8uT5U IYQAQDFN08z1QQghhBBCiPEjQ8BCCCGEEHlGAqAQQgghRJ6RACiEEEIIkWckAAohhBBC5BkJgEIIIYQQ eUYCoBBCCCFEnpEAKIQQQgiRZyQACiGEEELkGQmAQgghhBB5RgKgEEIIIUSekQAohBBCCJFn9FwfwFgr KSmhrq5uXPYVi8WwWCzjsq98JO2bXdK+2SXtm13Svtkl7Ztd49m++/bto7Ozc9jjUy4A1tXVsWnTpnHZ V0tLC1VVVeOyr3wk7Ztd0r7ZJe2bXdK+2SXtm13j2b4rVqwY8XEZAhZCCCGEyDMSAIUQQggh8owEQCGE EEKIPCMBUAghhBAiz0gAFEIIIYTIMxIAhRBCCCHyjARAMeGYpklzb4i3D/XT4Y9gmmauD0kIIYSYUqZc HUAxufkjcba29tMViGHEDV470Et5gY25ZW5cNvlxFUIIIcaC9ACKCSGeMNjT6ef5vV0EownKC2w4rBrl BTb6wjGe39vFrg4/8YSR60MVQgghJj3pUhE51x2M8k5LP6F4ghKnFU1VhjzvtVtIGCZ7u4I09YaZX+6m rMCGoihHeUchhBBCHIsEQJEzkXiCd9v9HOwN47HrlLpsR91WUxVKXFYicYPXm/oodVuZV16AW4aFhRBC iBMmn55i3JmmSUtfmG1tAwCUua2j7s2z6SrlBTb6wzFe2NvNzBInM4qcWDS5mkEIIYQYLQmAYlwNnuRR 5LScdHDz2C24TZPGriAHe0IsqCigXIaFhRBCiFGRACjGRTxhsK8nyK6OII5UL96pUpXDw8Kbm/sodlqY V16Ax24ZgyMWQgghpi4JgCLrugJR3jnUTzieoHiESR6nyqarlLttDITj/HVvN/XFLuqLnVh1GRYWQggh RiIBUGRNOJbg3Q4/Tb1hvHadgmNM8hgLBXYdl03jQE+Qpr4QC8rdVHjsMiwshBBCHEECoBhzgyd5KMqJ TfI4VaqiUOyyEo0bvNnSj68nxPzyArwOGRYWQggh0iQAijE1EI6zra2f7mCMQsfJT/I4VVZdpcxtwx+J 8+K+buoKHcwscWHTtZwcjxBCCDGRSAAUYyKeMGjsDrK7M4BD1yhzZ3e4d7TcNh2XVaOpL0xzX4R5ZW6q vHbUMb4OUQghhJhMJACKU5btSR6nSlEUip1WYgmDd1r72d8TZEGlB58MCwshhMhTEgDFSUtP8jjYG8Jn t2R9ksepsmjJYeFANM5Ljd1MK3TQUOLCbpFhYSGEEPlFAqA4YYaRnOSxvT05yaPcPbkKMLusOk6LxqH+ MC19YeaVu6n2OmRYWAghRN6QAChOyEA4zpbWfnpCMYqyNMnDNE2efLcTLRrgkpIxf3sgOSxc5LQSTxi8 0zrA/tRqIoVOa3Z2KIQQQkwgEgDFqBw5yaM8S5M8Wgci/MtTu3h5fw8AF+0P88ULZlIxBiuHjETXkkWk g9EEL+/vocZrZ1apG4cMCwshhJjCcrpUwhNPPMGcOXNoaGjgzjvvPOp2v//971EUhU2bNo3j0Ym0Tn+E Fxq72dsVpMRlpcA+9n83mKbJ/25p5epfv84bzX186cKZ3LikhJf29XDVrzbxq01NxBPGmO83zWnVKHNZ afdHeH5PF/u7gyQMM2v7E0IIIXIpZz2AiUSCz372szz55JPU1NRw+umns3r1aubPnz9ku4GBAX7wgx+w cuXKHB1p/grHEuzs8NPcG8Jrt+BxZWd4tLU/zHee2sUrB3pZVu3l9ktnUeN10Nup8TdLZ/Dvz+3hh39t 5JHtbXzt4gaWVnuzchyKolDosBI3TLa1Hx4WLs7SeQshhBC5krMewI0bN9LQ0EB9fT1Wq5VrrrmGDRs2 DNvuG9/4Bl/5ylew2+05OMr8ZBgmTT0hnt/TRYc/QpnblpWZsplev99s5q1D/Xz5opn8dM0iaryOzDZV Xjt3rV7Af7x/PqFogk/9z9t888876Q5Gx/x40nRVocxlQ1Xglf3dvNncSzAaz9r+hBBCiPGWswDY3NxM bW1t5n5NTQ3Nzc1Dttm8eTMHDx7kfe9733gfXt7qD8d49UAP77T247XrFDqys4xba3+Yv/vjFr7z1C7m lrl58LplfOS0KtSj7OuCmcX87vrl3HB6LU/s7ODDv3ydh94+lNVhWoclea1jVyDG83u72NsZyOowtBBC CDFeJuwkEMMw+Id/+Afuv//+4267bt061q1bB0BraystLS1ZPrqkjo6OcdnPeEgYJs19YZp6Q9h1FYdV wx8e+/2Ypsnju/v56eYODNPk704v4/2zvaixfno7+4ds6+/tHvb6a+c4OLdiGj/a2M6dz+zmf99q4tYz yphVnN0eYtWAN7o72KqpzCxxTYki0lPp53cikvbNLmnf7JL2za6J0L45C4DV1dUcPHgwc7+pqYnq6urM /YGBAbZs2cKFF14IJIPd6tWrefjhh1mxYsWQ91q7di1r164FYMWKFVRVVWX/BFLGc1/Z0umP8M6hAaKa hem1RUfthTtVg6/1W17j5RvvnTVkuHckvpLyER6De+tr+fPODu56fi+ffeIAaxZX8umz6rIyQSWtmOR1 kY3hGJVWO3PK3LhsE/ZvqFGZCj+/E5m0b3ZJ+2aXtG925bp9c/bpdfrpp7Nr1y4aGxuprq5m/fr1PPDA A5nnvV4vnZ2dmfsXXngh3/ve94aFP3HywrEEO9oHaOkLJyd52LMz2cE0TTZsbeOu5/dimCZfvmgmaxZX nlLQVBSFy+eWcU5dET95eR8PvX2Ip3d18oXz67l8TmnWClPbLRoVFo2eUHJYeHapi+mFTvQs1EMUQggh siVnAVDXde6++24uu+wyEokEN954IwsWLOD2229nxYoVrF69OleHNuWlV/LY1jaApkJZFlfyOJlevxNR YNf58kUNvH9+OXc8s5tvPLGTDVta+crFDcwoco7Zfo7kc1hIGCa7OgMc6AmzoMJN6SRbEUUIIUT+yun4 1apVq1i1atWQx771rW+NuO1f/vKXcTiiqa8/HGNr6wC9qZU8stVzlZ7h+58vNGKYJl+5aCYfPsVev2OZ V17AfVcv4Y9bWrnnxX189Deb+fjyGm46ozZra/1qqkKpy0Y4nmDTwT7KCmzMLXPjnuTDwkIIIaY++aTK E7H0Sh4dAVxWjbIsreQBw3v9bn/vbKq92S/jo6kKaxZXcnFDMT98oZH7XjvIEzvaue3CmVwwszhr+7Xr GvYCjb5wclh4VomLuiJnVpbJE0IIIcaCBMA8kJ7kEUsYlLqtWeuFG+9ev6Mpclr55mVzWL2ggjuf3c0X /7SN8+uLuO2CmVRlMYh67RbchkljV5CDvWHml7spL5BhYSGEEBOPBMApLBRLsLN9gOa+MD5H9iZ5QO56 /Y5lWY2XBz62lAfeaGHdK/u56tevc/MZ07hueXXWeuc0VaHYZSUSN9jc3Eepy8rcsoKszk4WQgghTpR8 Kk1BhmHS3BdiW5sfXYWKguwFsSN7/b560Uw+lINev6PRNZXrV9Rw6ZxS/uO5Pdzz0j4e3d7GVy5u4PRa X9b2a9NVyt02BsJx/trYxYwiF/XFTqy6DAsLIYTIPQmAU0x/OMaW1gH6sjzJA5K9ft9+ahevHuhlRY2X b0yAXr+jqSiw8e9Xzuevjd38+1/28Onfv8MVc0u59bx6SrK41m+BXcdlahzoCdLcF2J+uZsKj12GhYUQ QuSUBMApIpYw2NsVZG9XAKclu5M8Jnqv37GcO6OIFbVe7n/tIL/c1MTze7v5zNl1rFlciaZm5/hVJTks HI0bvNHcT1FPiPkVBXjsk381ESGEEJOTBMApoH0gzNZWP9GEQYkre5M8YHL1+h2NXde45aw6rphbxnef 3cO//2UPf9rWxlcvbmBhRUHW9mvVVcoLbPgjcV5s7GZ6kYOGYrcMCwshhBh3EgAnsVAswY62AVr6sz/J Y7x7/QzTJBRN4DXNrA2XTi90cs8HF/LUrk7+47m93LD+TT60qILPnlOX1d45t03HadVo6gnT3Bthfrmb So8dNUs9kEIIIcSRJABOQoZh0tQXYvs4TPKA8e/1i8QNekIxdE2l3R/B67Bg17NTzFlRFN47u5Szphfy s1f289s3W3hmdxe3njeD980ry1r4TA8LxxIGbx/qZ39viPnlBfgcMiwshBAi+yQATjJ9oRhb28Znkkcu rvXrDUUxUThjmo9YfwKrp5B3Dg3gj0Qpclqytm+3TeeLF8zkynnlfPfZ3Xzz/95lw9ZWvnJRAw0lrqzs E8CiqZS5k8PCLzV2M73QQUOpC1uWAq8QQggBEgAnjVjCYE9nkMbu7E/yADiUquv36oFeTq/18o33zM5q EeW4YdIdjFLmtrGgogC7RaOlH0rcNs6ttwyZ4JLNpdbmlLn5+UdO4+Gtbfzor41c+8AbfGxpNZ9aOQ2n NXuhzG3TcVk1mvvDtPSHmVvmptrrkGFhIYQQWSEBcBJoHwizpdVPbBwmeZimyR+3tPKDcez1C0Tj+KMJ FpQXMK3QMWzY1aKpzClzU1FgY8uhftr8EYqdVvQsztr9m4UVXDizmB/9tZFfv97E/+1s54sXzuSimcVZ GxZWFIVip5V4wmBL6wAHUrOFC53Zu7ZTCCFEfpIAOIGlJ3kc6o/gdeh4szjJA5K9ft9+ahcbx6nXzzRN uoMx7BaNc2cUHXfihddh4ay6Ig72htjePoBFVbN6zZzPYeEb752dXFLumd18+ZHtnFNXyJcumkmN15G1 /eqpYeFANM7L+3uo8dqZXerGbpFhYSGEEGNDAuAEZBgmB3tD7Gj3o6sK5QXZHe7NRa9fcqJHlBlFTmaX ukd9LaOqKkwvclLqtrK9zU/bQASfw4Iti6VUTqvy8OuPLeV3b7bw05f3c/WvNnPDGbVcv7wmqyVcXFYd p0Wj3R+htT/CnDI3NT5H1uoVCiGEyB8SACeYvlCMLYf66YvEKc7yJA8Y/14/gN5QDMOE02t9lJ3kDGan VWdZjZf2gQjvtA7gj8QpclqyNjyrqwofW1bNe2aXcNdze/npy/t5bHs7X75oJmdOL8zKPiE5LFzoSA4L b2vzs78nxMLKAopkWFgIIcQpkAA4QaQneeztDuCyaJRneZLH4F4/04SvXtzAhxdVZHWJsoRh0hWMUuqy sqDSg+MUhzQVRaHcY6fQaWV3p599PSEKrHpWJ2uUuW3c8b55fGB/D999djef++MW3ju7hH84v57SLH7P ksPCVoLRBK/s66HalxwWPtU2FEIIkZ8kAOaYaZp0+CNsafUTTxiUZnmSB+Sm1y8YTeCPxplXXsA039jO brXqKvMrPFR67LxzaICOQIQihzWrQ6VnTi9k/XXL+dWmg9z32kFe2tfD3545nY8sqcra5BQAp1XDYVHp 9Ec41B9mblkBtTIsLIQQ4gRJAMyhYDTOjjY/renr2OzZ/XaYpskf3kn2+sH49PqlJ3rYdJWz64rwZnHS RqHTyjkzitjfHWRnhx+7rmZ1RQ+brvKpM6dzxdwy/u3ZPXz/+b2ZJeVOq/Jkbb+KouBzWIkbJtvbB9jf HWRhpYdilwwLCyGEGB0JgDmQnuSRnsma7UkekJtev2jcoDsUZXqhkzllbixZvp4RQFMV6ktclBXY2Nra T9tAhCKnJav7rvE5+MHfLODZPV38x1/2cNPv3uJvFlbwuXPqsjpLWVcVylw2wrEEr+7vpqLAztxyN06r /LMWQghxbPJJMc6GTPLIYi27tCN7/b52cQMfynKvH0BfOEY8YbKixke5J7tBcyRum84Z0wpp6QuzrW0A RQGfPXuTRBRF4eKGEs6cVsi9rx7ggTeaeXZ3J3937gxWLyjP6rC+3aJht2j0hGI8v6eLWaUuphc6sz6B SAghxOQlAXCcxBIGuzsDNHYHx2WSBwzt9Tuj1sc/vmdW1nv9EoZJZzBKidPKoqpTn+hxKhRFodrnoNhl 5d0OP029Ibx2S1br6TmtWmYd4Tuf2c13ntrFw1tb+erFDcwudWdtv5CsW5gwTHZ1BjjQG2ZhRQElLmvW w74QQojJJ6ddBE888QRz5syhoaGBO++8c9jz3//+95k/fz6LFy/mkksuYf/+/Tk4ylNjmiZt/WFe2NvN wZ4QpS5rVpcyS+/z928f4upfb2bLoQG+dnED93xoYdbDXyiWoCsYZW6pmxW1vgkzQ9Vu0Vhc5eWMaYVE EyadgSiGaWZ1nw0lLu69ajHfvHQ2B3pDfPyBN/j+c3sJRONZ3a+mKpS6bFg1hdcO9PJ6Ux+BSHb3KYQQ YvLJWQBMJBJ89rOf5fHHH2fbtm08+OCDbNu2bcg2S5cuZdOmTbz99tusWbOGL3/5yzk62pMTjMbZ3NTH pqY+7LpK8TjN8P3sH7dwxzO7WVhRwPrrlvHhxZVZn+jRFYgSN0zOqiuivsQ1IdewLXHbOK++iBnFTjoD UfxZDkaKonDl/HJ+/4kV/M3CCh58o5k1v3ydJ9/twMxyALXrGuUFNvrDMZ7f28WujuRSgkIIIQTkMABu 3LiRhoYG6uvrsVqtXHPNNWzYsGHINhdddBFOpxOAM888k6amplwc6gkzDJP93UGe39tFbyhGRYEtqytV QO56/WIJgzZ/lEqPjXNmFGV10sNY0DWV2aVuzplRhEVXafNHiBvZDWNeu4WvXTKL+64+jSKnha89toO/ ++MWDvSEsrrf9L6LnVb2dgV5YW83bf3hrIdPIYQQE1/OrgFsbm6mtrY2c7+mpoZXX331qNv/4he/4Ior rhiPQzslvaEYWw/10x9JUDQOkzwgda3fk7vYeHD8rvUD6A/HiCZMllV7qMzi2rjZ4LFbOHNa4ZAl97Id XhdWevjVR5fy0NuH+PFL+7j6N6/zyRW1fOL0Gux69obLNVWhxGUlEjd4vamPUreVuWUFWdufEEKIiW9S TAL5zW9+w6ZNm3juuedGfH7dunWsW7cOgNbWVlpaWsbluDo6OjK3YwmTpr4QLX1hnBYVu0XDH87u/k3T 5NFdffxsc/I4vnBGGe+b5UWJ9dHb2ZfF/UJPKIbHrjOrxIUZiNMS6Bnz/Qxu32yxALMcCRq7g+ztiFFg 07Fo2Q3tl9VonP7+6fz09Q7uffUAj2w9xN+dXsYZ1a6s7hfABhwaiLP/oInLCNATjGHVFayalvXzzjfj 8fObz6R9s0vaN7smQvvmLABWV1dz8ODBzP2mpiaqq6uHbffUU0/xL//yLzz33HPYbCPPnF27di1r164F YMWKFVRVVWXnoEdQWVlJ+0CE7a0DJHQLdbXFWb/OD47o9Zvm4xvvmUXlOJRbCccS9EXiLJvmYkZR9q/1 G6/v5YxpJu0DEba0DpAwzKyuKwzgA/6ttprXDvZy5zO7+fqzzVzcUMw/XDCTiizXhfQBhmnS3NzCwbgd 4gqYJpqqUGC34LXpeOw6DquGXVex6ZqsNHKSxvN3UT6S9s0uad/synX75iwAnn766ezatYvGxkaqq6tZ v349DzzwwJBt3njjDf72b/+WJ554grKyshwd6dGFYwk2N/XRll7JI8vX+UHu6voBdAWjWFSVs6YXUuic WqtODFtXuDtEgS276woDnF7rY/11y/jN6838fOMBXt6/ibVnTuejS6qyWsdPVRQK7Do+1+GwmTBMYgmD QwNhDvQamCR/phRM7LqGx5EMh26bjt2iYtc1rOPwMy+EEGLs5SwA6rrO3XffzWWXXUYikeDGG29kwYIF 3H777axYsYLVq1fzpS99Cb/fz1VXXQXAtGnTePjhh3N1yEPEEwbvHOrHXWQfl5U8AFr6wnznqfHv9Ysn DDqDMWp8duaVFUzpD/0j1xVuD0QozvK6whZN5YYzarlsTin//twefvBCI3/a1sbXLm5gabU3a/s9kqYq aKo2Yp3EWMKgPxSj0x8hYZqA9BoKIcRkltNrAFetWsWqVauGPPatb30rc/upp54a70MatYRpEjcYl1mv pmny+3da+WGq1+/rlzTwwYXj0+s3EI4TSSRYUuWhymvPm6LC472uMECV185dqxfw3J4u/v0ve/jU/7zN lfPKuPW8GTnvcbVo6ojL6UmvoRBCTE6TYhJIPmvpC/Ptp97ltYN949rrZ5gmXcEoHruF06f5cGW5ePVE NHhd4e1tA+OyrjDABTOLOWOaj//aeJBfv97E83u7+ew5dXxwUcW4XF96IqTXUAghJqf8+1SfJHLZ6xeO JegLx2kodTGz2JX3H8pum86KWt+4rSsM4LBofPacOlallpS745ndPLy1ja9d0sDcsuwuKTdWTrTXENPE YZFeQyGEGA8SACegXPX6AXQHo2iqypl1hRRNsYkep+LIdYUP9obwZXldYYAZRU5++uFFPLGzg/98fi/X P/gGV51WxafPmp71JQWzRXoNhRAi9ybnJ8gUZaRm+Oai1y+eMOgKxagssDG/ogBbFgsTT2bpdYWrvQ7e PtSPPxClyGnJ6tCsoihcMbeMc+uK+PHL+/jdmy089W4Hf39+PZfNKZ1S12VKr6EQQoyPUQXAH/3oR1x3 3XUUFhZm+3jy1uBev5XTkqt5jFevnz8SJxRLsLjCQ7UvfyZ6nIpil5XzZhSxtzvI7o4ALquW9R65ArvO Vy5qYPX8cu54Zjf/+MRO/ndLK1+9uIG6ImdW951r0msohBBja1SfWG1tbZx++uksW7aMG2+8kcsuu0xC whgxTJM/vH2IH/y1EVVR+H+XNPA349Trl57oUWDVObe+eNIOKeZKel3higIbW1oHaPdHKHJYslq/D2Be eQH3Xb2EP25p5Z4X93HNbzbz8eU13HRGbdaHpCci6TUUQogTN6pP/O985zt8+9vf5v/+7/+47777+Nzn PsdHPvIRbrrpJmbOnJntY5yyjuz1+8Z7ZlExTr1+4Xhyokd9kYtZpTLR41Sk1xVu6guxvW181hXWVIU1 iyu5uKGYH77QyH2vHeSJHe186aKZnF9fnNV9TxYn2mtomia69BoKIfLEqLt8FEWhoqKCiooKdF2np6eH NWvW8N73vpd/+7d/y+YxTjm57PUD6A1FMVFYOa2QYpdM9BgLqqowrdBJqdvG9tYBDg1EKByH1WGKnFa+ edkcVi+o4M5nd/MPD2/j/PoibrtgJlXe8fljYjKSXkMhRL4bVQD8wQ9+wK9+9StKSkq4+eab+fd//3cs FguGYTBr1iwJgCcgl71+ccOkKxClvMDGwkqZ6JENDovG0hov1al1hf2ReNbXFQZYVuPlgY8t5YE3Wlj3 yn6u+vXrfGrlNK5dVp31uoVTyVj2GhqmiWGYpL/1ctmMEGIiGVUA7O7u5g9/+APTp08f8riqqjzyyCNZ ObCpJte9fv5InGAswcLKAmp9DvkwyqIh6wp3+dnXNT7rCuuayvUrarh0dgn/8fxe7n5xH49sa+OrFzew otaX1X3ngxPtNQx09eAaSP2KNVMrpKT/2SmgkPpPUTK3Sd0f/Dwke5jJbA8Kh//9KsrQ90je5/D2JB9I P6YOft2g1yefG3ScyqDXD3pfJfXI4NeNtG9VUYec8+DfOINfN6RdjmyHYzznj8SJxBPyh6wQJ+mYAbC7 uxuAW2+9dcj9tKKiIubNm5elQ5s6mvvCfPvJd9nUNP69fqZp0hWM4bRqnDujmAK7TPQYL1ZdZX65hyqP g3cO9Y/LusIAFR47/37lfP7a2M2/P7uHW37/DlfMLeXW8+opkSH/MXe0XkNLyILPNXydcNM0D9/OPDb0 /uAHj9xmyGOYyceNo79nersjHztiN4e3GeG50Rz7sOMftL2iDHrOTCfC1HNDXqcMeUwZvM9BodE0wd/d z96IHauqUOSyUuy04E79oSWhUIjjO2YaWL58OYqiDPlHn6YoCnv37s3agU0Fue71i8QNekJRZhQ7mV3i zvrsVDEyn8PC2XXju64wwLkzilhR6+X+1w7yy01NvLC3m8+cU8eHF1XKhIYcGvzvXxl2Y8iW43A0k5cl bMHnshI3TPpCMdoGIqSrAFlVhWKXlSIJhUIc1TEDYGNj41GfGykUisNy2esH0BuOYRhweq2PsgKZDJBr 6XWFywtsbGtLlowpdGR/XWG7rnHLWXVcMbeM7z67h397dk9ySbmLG6iWzmAxBeiqgtum4x7U2RpPGPSG YrSmQqGJid2iUeSwSCgUImVUHwG333473/rWtzL3DcPg4x//OP/93/+dtQObrHLd6xc3TLqDUUpdVhZW evKyLtxE5kqtK9zaH2ZLqx+IU+jI/iSR6YVO7vngQp58t5PvP7+XT65/kyUVTupL+6ny2qn22Kn22qny 2vHYdLlGVExquqbi1tQTDoUuqy6zukXeGFUAPHjwIHfccQdf+9rXiEQifOQjH2Hp0qXZPrZJZ3Cv35mp 1TzGs9cvEI0TiCaYX17AtEKZ6DFRKYpCpddBkcvKu+1+DvaG8dr1rId1RVG4dE4pZ9cV8ouNB3m1sYOn dnXSF44P2c5l1ag+IhRWeezUeO1UeuxZL20jRDYcLxQaqVEtCYUiX4wqAP7Xf/0X1157LXfccQfPPvss q1at4gtf+EKWD23yMEyT3799iB+mev3+8T2z+MCC8nELYOmJHg6Lxjkzisbl+jJx6my6xqIqL1XjuK4w gNumc+t5M+id58RXUo4/Eqe5L0xLf5jm/nDydl+Yxu4gL+3rIZIwhry+xGVNBkOPnWqvjWqPgyqvjWqP nVK3Ta4vFJPGaEKhAtgGhcICuwWnReo/isnvmAFw8+bNmdu33norf/u3f8s555zD+eefz+bNm1m2bFnW D3Ciy3WvXzQ10aOuyMnsUpnoMRml1xVu7A6yuzOA05L9dYUHc9t05pS5mVPmHvacYZp0B2M09YVo6Ysk Q2Jf8r83mvt4YkdkyMxPXVWo9NhS4dCe+Zq+7bXL8LKY2I4dCsMYJkNCYbHLgtsmoVBMPsf8lPniF784 5H5hYSHbtm3ji1/8Ioqi8Mwzz2T14CYywzB5Yk8f/711X056/QB6QzEM02R5jY/ycQydYuzpmsqsUjfl BTa2juO6wsejKgolLislLitLqoY/H0sYtA5EMqGwpT/Ze9jcH+bpow0vew4PK6fDYbXXTqXHhl0uyhcT 0OFQePgjc3AoNAFMCYVicjlmAHz22WfH6zgmlVAswRU/38hze7py0uuXMEw6g1FKnFYWVXlwyESPKcNj t7ByWiHNfSG2jdO6wqfCoqnU+hzU+hwjPu+PxAeFwgjNfSFa+iMc6Anx8v4eIvGhw8vFTgvVXgfV3uG9 iGUyvCwmkKOFwp7gyKGwxGXFZdMlFIoJY1TjTG1tbXz961+npaWFxx9/nG3btvHyyy9z0003Zfv4JiSH RWNWiZN5XoWbzps7rr1+wWiCgUicuWVu6oqcmRUCxNShqgq1hU5K3DZ2tA1wqD+CbxzWFc4Gt01ndqmb 2aXDh5fT166mewwz1yH2hXmzuZ8/7+wYXN8YXVWoKLANnbU8qBdRhpdFrumaSoGmUsDxQ2Gx00KxU0Kh yJ1RBcBPfvKT3HDDDfzLv/wLALNnz+bqq6/O2wAIcPeHFvHIxh3jOtGjOxjDpqucPaNoQvcKibHhsGgs qfZS7Y2wpdWPPxKncBwmiYwXZdDw8uIqz7Dn4+nh5XQPYiootvRFeHZPJ72h4cPLVZ7DoTA9MSUdFKUk ksiFo4XC7kCMQ/3JUGiaydnHJU4LRRIKxTgZVQDs7OzkIx/5CHfccUfyRbqOpp36L9MnnniCW2+9lUQi wc0338xXv/rVIc9HIhGuv/56Xn/9dYqLi/ntb39LXV3dKe93soklDLqDMaYVOphT5s568WAxcSiKQlmB nfOcVnZ3BmjsCuK2abisU7+Ks66p1Pgc1BxleDkQjdPSNyggpr4e7AvxyoGjDS8nw2BV+trDVGAsK7Ch S2+6GCcjhcJYwqArEKNlUCh0pHoKJRSKbBjVp4jL5aKrqyvT2/XKK6/g9XpPaceJRILPfvazPPnkk9TU 1HD66aezevVq5s+fn9nmF7/4BYWFhezevZv169fzla98hd/+9rentN/Jpi8cI54wWVbjHdfrDMXEYtFU 5pUXUOmxsyW1rnCRw5rXocVl1ZlVqjOr1DXsuXSPeWbW8qBexLcP9fPkux0kBg0va6nh5cE9hlVeW/J6 RI8N3zgU6xb5zaKpWE4iFLqsmnQKiJMyqgD4/e9/n9WrV7Nnzx7OOeccOjo6eOihh05pxxs3bqShoYH6 +noArrnmGjZs2DAkAG7YsIFvfvObAKxZs4bPfe5zmKaZF7+IE0by+qgip86iSg/OPOjxEcfnc1g4q66I g70hdrQNYNVVvFL3cRhFSa4FW+yysqjyKMPL/ggtfWFa+ofOYv7Lni56QrEh2zstGlWDJqZUD+pFrPLY ZSKWyIrjhcL0NbJOi0aRhEJxgkaVKpYtW8Zzzz3Hzp07MU2TOXPmYLGc2odOc3MztbW1mfs1NTW8+uqr R91G13W8Xi9dXV2UlJQM2W7dunWsW7cOgNbWVlpaWk7p2EYjljAI9ffQ2zn2wSwSNwhEE0wvdFCt2+nt DNM75nuZ+Do6OnJ9CBOWFZjlTNDYFWRvewyPTUfXTuwPI39vd3YObpJwA7OdMNupQIUDODzUHIoZtAZi HBqI0RqI0epP3j7Q7WfjgR7C8aFrofvsGpVuCxVuC5Wp/+yJEJ5DAayagkVVsWrKkP8sqoJVU9FV8uKP 2rGW7z+/gz95wkGTfV0G7yYMTBMUBWyaiseu47VbsFs1HBbthEYM5Pdvdk2E9h1VegkGg3z/+99n//79 3HvvvezatYudO3dy5ZVXZvv4RmXt2rWsXbsWgBUrVlBVNULBsjEWiSdwHOzDV1I+Zu9pmiY9oTgOVeGs ag+FTuuYvfdkNR7fy8msfpqZWVfYwDzhdYXH8ud3KvEBlcBIC14m/50mZy83pWsfpkrcvNsd4fn9A4OG l/uPuy8FsOoqNk3NfLVoyrDHrLqKVUsFySMesx3x3ODHbHqyFyl5f/j7WjR10pbXkZ/fo4slDMIxg0OJ BGYYlAg49MM9hW6bjvM4PYXy+ze7ct2+owqAN9xwA8uXL+fll18GoLq6mquuuuqUAmB1dTUHDx7M3G9q aqK6unrEbWpqaojH4/T19VFcXHzS+5zI0hM9anx25pYVyIW+YlQGryu8qyPAgZ4QHrsuQ5JZpCgKRU4r RU4rC0caXjZM2gYiNLW2YSvwEY0bRBMmkbhBNGFkvkYTRuo5g0jczNyPJAxiqa/p5/vC8eR2qcdiQ97H HOEoT4ymKqlQqBwRNo8MoMrhQDlSANWVzOtsw55L94IOf86iKdILOsaONXzc3B8GE1BOPBSKqWNUAXDP nj389re/5cEHHwTA6XRimqf2S+f0009n165dNDY2Ul1dzfr163nggQeGbLN69Wp++ctfctZZZ/HQQw9x 8cUXT8lfEgPhOOFEgiVVHiq99il5jiK7bLrGwkoPVV4777T005GaJDJZe3YmM11VqPbaccXs+EpObbLc aBimSSxhHg6Pg8NhJkiax3jucECNDQqZgwNoOG4wEIkPeWzw+4xBBh0WDgf3UNrSwXJQGHUpMU6brjC/ vIAa+b05KkcLhZ2B6LBQqAYD2LxRCh0WqTc7RY0qAFqtVkKhUOYf2J49e7DZbMd51XF2rOvcfffdXHbZ ZSQSCW688UYWLFjA7bffzooVK1i9ejU33XQTH//4x2loaKCoqIj169ef0j4nGsNMrujhs1s4fZoP1ziu /yqmpiKnlXNyuK6wGH+qomDTkz1zBTk6hrhhHjVcJoOnefTnUr2fw3pIj3itP5ogGowRSW3TFYjyu209 ALitGnPL3Mwrdye/lhVQ47NPmZqZ2ZQOhYPFEgZtoSgbD/Rg1VSmFzmoKLDL75IpZlTfzX/+53/m8ssv 5+DBg1x77bW8+OKL3H///ae881WrVrFq1aohj33rW9/K3Lbb7fzP//zPKe9nIgrHEvSF48wqdVFf7JKe GjFm0usKVxTY2dLaP2HWFRZTl64q6Ko2rpcedLS10qW42dHuZ3vbANvb/ax/s4VYqjtSQuHJs2gqbquO z20jnjDY2xVkV0cAn8NCXaGDErdNhomngFEFwF/+8pe8733vY82aNdTX1/ODH/xg2ExcMXrdwSiaqnJm XSFFMtFDZEmBXWfltEJa+sJsaxtAU8HnkJ83MTVYNIW5Jclw9zcLK4Bkz9WeruBRQ6ErFQrnSygcNV1T KU59TgWjCd481I+KklmCUWpkTl6jCoA33XQTL7zwAk8++SR79uxh6dKlnH/++dx6663ZPr4pJZ4w6ArF qPLYmF/ukYkeIutUVaGm0EGx25pZV9jr0LHrMklETD0WTWVu2cmFwnmp3kIJhUfntGo4rRqGmZzodLA3 hN2iMaPISZnbKvVqJ5lRfbcuuugizj//fF577TWeffZZfvrTn7J161YJgCfAH4kTiiU4LXWhvvzFJMaT w6KxtMZH9UCyZEwgEkUdgwv3hZjoRhsKf/vWyKEw2WMooXAwVVEy69FH4wY72wfY3gbFLit1hU6KnHLJ yWQwqgB4ySWXEAgEOOusszjvvPN47bXXKCsry/axTQmGadIVjFJgs3BurU8uohU5lV5XeE9nkC1dHcT9 UVBMVJRMOQ5dU/N6iTkx9Y0UCuOpULh9UCj83VstmTI7EgpHZtVVSvTkpNBANM7rTb1oqkqNz0a1x4HH rkuHxwQ1qjSyePFiXn/9dbZs2YLX68Xn83HWWWfhcIy8SLtICseTEz1mFrtoKJGJHmJisGgqc8vd2CJe fCU+ogmTUCxBIBpnIJIgEEnWnGPQj6uCkixOrKlYVEX+uhdTjq6pzClzM+cUQuG8cje1PkfehkKXVcdl 1UkYJof6IuzvDuGy6swoclDqtmGX+qQTyqgC4F133QXAwMAA999/PzfccAOtra1EIpGsHtxk1hOKoqCw clohxS658F5MPDZdPepqMwljUGHiuEE4liAQTRCIJUNiJBwDU0FRMqXD0NVBvYiqFPYVk9/xQuGOdj/b 2gYkFB5BUw8PEUfiBltb/ZgMUOa2Mb3QQaFTapROBKMKgHfffTcvvPACr7/+OnV1ddx4442cd9552T62 SSlumHQFolQU2FhQWYBNLrYXk5CmKjiOUdbDSAfEVE22SDyBP5ogGEkwEInTFzcYfImhgomuqkNCogRE MRkNDoVpR4bC7W3DewrnlA6afZxHodCmq5S6rZimiT8S57WDveiayjSfgyqPnQK7XBaVK6Nq+XA4zD/8 wz+wfPlydF2+WUfjj8QJxhIsqiygxueQDzgxZamqgl3VjjqkY5rpHsTk18M9iAmC0ThdoTimYYKSHF4G 0JTDRWktmpIXH45iajiVUJiceTz1Q6GiKLhtOm6bTtwwOdATZG9XAI9Np67ISanbJpUxxtmo0txtt92W 7eOY1EzTpCsYw23VOHdGsfxFI/KeoijYdI2jzXky08uXDepFDETjBCLJoNgbipEwU4PLqa5ETQWLmgyH Fk2VISQxoR0tFO7tDrKt7XAo/J88DIW6qmRq4IZjCd5p7QegssBOjc8hy8+NE0kqpygSN+gJxagvdjKr xCUXxwsxCoqiYNWVY/7FHxu07mw0YRKIxJMhMWbgj8STH5oKgInC4Ykq6V5EmcksJhpdU5ld6mZ26fBQ uD0VCI8XCueWuZlWOHVCod2SHEkwTZPuYJSW/jBWTaUutfycLJGaPdKypyBhmgRjCc6Y5qPUfWprIwsh hkoHOVf6gYKh/8biicPhMBo3CKZmMgciyaHmSCyRDIgmoCQHmi2akulFlIkqYiIYHAo/sCD52OBQuKPN z7Y8CIWKouCxW/BwePj8XVl+LqskAJ4kXU1exLpkRpFMbRciB3RNRddUnEd53jBMIoN6EcOxBP5IciZz IJJITlRJT2Hm8EzmwSFRAqLIhZMPhS7mlRdM+lB45PJzbx0aQGFAlp8bYxIAT5KmKkwrdEj4E2KCUkcx kzlmJK8/TJe7GYjGCaZ6EPtD8WRABDCTw82W1ExmmagixttoQuH29pFD4dyygswM5MkWCmX5ueyRlhNC 5CVVVbCp2lFLNaUnqkQy1yEamWLZwWicnlAcI5MQk5NVNBWsmoquKRhGciWg9Eet9FiIsTbaUPj7tw/x QMIAhobC9BDyZAiFRy4/9267n+1tUOKyMF2WnzspEgCFEGIEJzJRJT3UHIwm8Efj+CMJgrE4ZigGkOlJ TA45p+8k92GapApqm5kZz+lrFodsP2hpFkVJBtQhy7WkdpAuzo2pDH2ZaSb3N/QFh98TZdjxpdvh8DaH 95++f2SwHfJc6hVHZgtFGf5cZpPBz43wnuk75tATESlHC4WN3SG2tQ8MCYWRY4RCzwRuYKuuUqwnawsG oonM8nO1PjtVHrssPzdKEgCFEOIkDZuoMkiLLUxV1dA1083Uh6o5KGNlHstsk37OHLLdka8fafvhzw1/ 76Pv7+jbm5gYyaxA6guGkdzj0OdSrzcY9FzysdQXjPQ+TTOzvZHZPrU/M3X+qdeZhpk5L5PkfX80nlzL GhNNVXBaNGy6Kh/8I9A1lVmlLmaVuoaFwu3tA8nZx0eEQp9dY9W8IFfOLxsya3kiGVxbMGGYNPeG2NcT xGWR5edGQwKgEEKMk3Q4GZpRJLCcjJaWGEWlxfgjcXrDMTr8UToD0UzvqV1XsVs0KQd0FIND4eoRegqf 3XGI373VwgNvNDO7xMX75pdzxdzSTP2+iUZTlczSluF4gm1tfszWAcoKbEzzyfJzI5EAKIQQYlJK15Ar cdtoKEmuYR2IxhkIx+kMROkKRIkkDBRFQVfAYdWwadJLeDSDQ+EF5Qq4ivjzzg4e3d7GXc/v5Ycv7OXs GUVcOa+c82YUTdiVO+y6hl1P1hbsD8V5baAPi6YwvTBZW1AWa0iSVhBCCDElaGqqlpzdQrXPgWmahOMG gUicnlCyl7ArGMMwTVQlGRQcFk16ho7C57Bw9ZIqrl5SxZ6uAI9sa+fxHe28sLcbr13n0tmlvG9+OQvK 3RMyVCuKQoFdpwCIGyb7uoPs7grisSVnEZe48nv5OQmAQgghpiRFUXBYkiGvxG1jVmlymDMQTTAQidER iNEViBJL9RJaVAW7RcV+lJnh+WxmsYtbz5vBZ8+pY+OBHh7Z1s7DW9v4n7cPMaPIwfvmlbNqXhllE3RR hCOXn3v7UD8KChUFNmoLHfjs+bf8nARAIYQQeUPXVLwOFa/DQo0vOekkFEuuQd0djNEZiNDhj2JioioK dl2VXsJBdFXh7Loizq4rYiAc56ldHTyyvZ27X9zHj1/axxm1Pq6cX86FM4sn7ASM9KUDxqDl52yaSl2R k/ICW94sP5eTs+zu7ubqq69m37591NXV8bvf/Y7CwsIh27z55pt8+tOfpr+/H03T+H//7/9x9dVX5+Jw hRBCTFGKouC06jitOqVuG3NwE0v3EoZjdKSuJUykZiZb1WQgtOXx0GFagV3ng4sq+eCiSg70hHh0exuP bm/nH5/Yicuq8Z5ZJbx/fjmnVXkm5BCxOmj5uVjCYFdngJ0dfgodFuqKnBS7rFN6+bmcBMA777yTSy65 hK9+9avceeed3HnnnXz3u98dso3T6eRXv/oVs2bNoqWlheXLl3PZZZfh8/lycchCCCHyhEVT8TlUfA4L tYXOTC+hP5KgOxSl0x+lIxABkjULHZZkKJzoxZSzaVqhg0+fXcffnjWdzU19PLKtjf97t4MNW9uo8dp5 37wy3jevnCqvPdeHOiKLplLiOrz83BvN/agK1HjtVPsceKdgbcGcBMANGzbwl7/8BYBPfOITXHjhhcMC 4OzZszO3q6qqKCsro6OjQwKgEEKIcTW4l7CswAZlyR4jf+TwjOPOYDRV69DEoqo4LVpeTjBQFYUVtT5W 1Pr48kUNPLO7k0e2tfGzVw7ws1cOsKzay/vnl3PxrGJcE3QZt8HLz/3/9u48oKoyf/z4+y7sF9kv4gai 5MIqaooKkhuNGOo01tdSIyOnabTJyvnaVF9tvvn9NWP7NGPRItheTmphi1qRmpSiaYsblZgKwgXZ1wv3 +f2B3hFR0+Rygft5/eU999xznvO5x8PnPud8nudkVQM/l9Xh5qyz3iK+0PSSXY1dol9UVERQUBAAPXv2 pKio6KLr79y5k8bGRgYMGHDe99PT00lPTwfg5MmTFBQUtG+DL8BkMnXIfhyVxNe2JL62JfG1rc4SXz3Q UweBhpaK4zqzhYo6M6fKzdSZm1tmNdG0jEvYMlC1vVt8aarLT7XLdsYZYZwxkKJqXzYfqWTzT5U8vPkw f/tUw7h+BqaEehHTs3NPRecMNNQq9hQ3Y1Hg46an5+kZR37ts6Gd4fy1WQI4adIkTp482Wb5ihUrWr3W aDQX7VYtLCxk7ty5ZGZmotWe/9fUggULWLBgAQAjRoygV69eV9Dyy9OR+3JEEl/bkvjalsTXtjp7fBub WuaPrqhvoqSmgVO1ZpotLdP1Oetaegk78zNm3v6B7bgtGBQCf0xU7CusZOP+YjYdNrHlSBWBni5MHWxk 2lAjwT7u7bbP9uYP1unnfjY3o2vW0s/bjV5eLni6XP4tYnufvzZLALds2XLB9wIDAyksLCQoKIjCwkKM RuN516usrCQ5OZkVK1YwevRoWzVVCCGEaHfOei3Oemd83J0J8XXHYlHUnq44Lj1dbVxeZ0ahQacBNycd rk7aTt0bdqU0Gg0xvbyI6eXFvYmhfP5jKRv3F5OZe4zVu44RFeRJ8pBAplwV0CkHbD53+rnj5bUcOVWD h3PL9HNGTxdcusgwQnaJbkpKCpmZmSxdupTMzEymT5/eZp3GxkZmzpzJvHnz+N3vfmeHVgohhBDtR6v9 T/IQ6NkyXl5DU0tCWFHXhKm6gbJaM80otGhw1rWMY9iZewmvhKteR9IgI0mDjJiqG/jwoIms/UX8v09/ 4PHPf2R8qB/ThgYyKtinU07pd77p5747WdUytmAXmH7OLgng0qVLueGGG3jppZcIDg7m7bffBiA3N5fn nnuOF198kbfffputW7dSWlpKRkYGABkZGcTExNijyUIIIUS7c9HrcNHr8HV3pr9fSy9hTWMzNY0txSWm mkbK65tQSqHXtiSErvruN51dgMGFeSP6MHd4bw4UV5O1v4iPD5nYnFeCn7sTU09XEQ/097B3U8/r7Onn KuqaONkFpp/TKKWUvRvRnkaMGEFubm6H7KugoMDu9/C7M4mvbUl8bUvia1uOFN+GppYhaCrqWsYlLK9r RKEBxemBqrXo27mXsLykqF2fAfw1zM0Wth85Rdb+Yrbnn6LZohhsNDBtiJFrBxvxdnOya/t+SVOzhcqG JpoUbaaf68jz90J5UedLSYUQQghhdaaX0M/DmVB/D5otitrT09mVnu4lbKhrQoNCp9Xgfnqg6q7eS+ik 03LNQH+uGehPWW0jHx1quUX82Oc/8eS2I8T392XaECNj+/t2ytvkep3WOv1c3VnTzwX1cMGl3mzn1kkC KIQQQnQpOq0GT1c9nq56enm5AS3z21Y3NFFeb6akxkxJTSNoNGgAF50WN2ddp3yO7lL5uDsze1hvZg/r zQ8lNWTtL+LDg8Vk/1iKt5uepEFGpg0xMtho6JSJ75k5qS1KUVLTSJmpiuC+zXadLk8SQCGEEKKLOzO/ rb/BhYH+0GxR1DT+Z6Dq0ppGGpotaDQa9Bpwc9bhouuavYQD/T24OyGUheP68+XRMrL2F/Hut4W8tbeA UD93rhsayG8GG60ze3QmWo0GL1cnytBg7+fvJAEUQgghuhmd9vQ8t65O9PZ2Q6mWgaprGpooqzNjqm6k tNaMRSm0mtNFDE5dq5dQr9Uwrr8v4/r7UllvZtPhEjbuL+LpbUf4x/YjjA72YdqQQMYP8JO5m89DEkAh hBCim9NoNNbbkP4GF8ICWooUahpbbh2bTvcSmi0WlNLQ2NCEwaK6TELYw9WJ30UF8buoIPJP1bLxQDEf HCjiLx8exOCsY/JVAVw3NJDIIM8u2etpC5IACiGEEA5Ir9Pi5abFy+0/vYR1pweqzrNUUtXQhLnZgote i6eLvssMUB3i684fx4ZwR1wwucfLydpfzAcHi1n33Un6ebuRPNRI8mAjPXu42rupdiUJoBBCCCHQaDS4 O+txd9Zj9nGnZ09/yuvNFFTUU1BZT7NF4e6kw8NZ1yV60XRaDaP6+TCqnw9LGwfwSV4JWfuLWLXjKM/t OMqIvl5MGxrIhIH+uNmxGMNeJAEUQgghRBtarQZfd2d83Z0ZbDRwqtbMsfI6TNUNoAGDs77LJE4eznpS wnuSEt6T4xV1fHCgmI0Hiln28WH+9umPTAzzJ3mIkdg+Xl2mp/NKSQIohBBCiIvS67QYPV0werrQ0NRM aU0j+WV1FFc3oNVo6OGix7mLFFr08XJjwehgbh/Vj70FlWTtL2JLXgnv7y+iVw8Xpg4xMm1IIH283ezd VJuSBFAIIYQQl8xFr6OXlxu9vNyoOV1Akn+qlvJ6M05aDZ6uTl2ieESj0TCstxfDenuxJHEAn/1YStb+ Il766hgvfnWMmF49mDY0kElh/hhcul+61P2OSAghhBAdwsNFj4eLnmAfNyrrmzhZ1cCx8rouVzzi6qTj N4ON/GawkaKqBj48WEzW/iIe2ZLHys9+JHGgH9OGBHJ1P290XSC5vRSSAAohhBDiimg0GrzcnPBycyLM 34PyejMnKuopqKjHosDdSdtlikcCPV1IHdmXW0b04fuTVWQdKGbTIRMfHzIR4OHccot4aCD9fd3t3dQr IgmgEEIIIdrNucUjZecUj3g66+06Bdql0mg0RAT1ICKoB/ckhLL1SCkb9xfz6u7jZOYeZ2iggWlDA5ly VQDebk72bu5lkwRQCCGEEDbhdFbxSL25mZLqRo6W13a54hFnvZZJYQFMCgugtKaRDw8Vs3F/MX//7Eee +PwnEkJ9mTY0kDHBPuh1nf94QBJAIYQQQnQAVycdfXzc6OPTUjxSVNXA0fI6yuubcNLSZYpH/DycmRPb hzmxfThUXE3WgSI+Omji0x9K8XV3ImlQANOGBDLIaLB3Uy9KEkAhhBBCdCgPFz2hLnr6+7m3KR5x1Wsx dJHikUFGA4OMBv40rj87jpbx/v4i3tlXyBtfFxDm70HyUCO/GWTEz8PZ3k1tQxJAIYQQQtjF2cUjA/09 KK8zc6KijsLKhi5VPKLXaUkI9SMh1I/yOjObDpvI2l/EU1uP8I9tRxgT4kvyUCMJ/f06zS1vSQCFEEII YXc6rQY/D2f8PJwZEmihrNbMz2V1mGpanhc0OOu6RPGIt5sTN0T34oboXvxUWsPGA8V8cKCYbUdO0cNF z5RBAQz306CUsms7JQEUQgghRKfSXYpHQv08WDSuP3eOCWHnz+VkHSji/e+L+ECjWDAhEnc73hmWBFAI IYQQndbZxSPVDU0Ud8HiEZ1WQ1yID3EhPlQ3NLF1f77d51G2S/p86tQpJk+eTFhYGJMnT6asrOyC61ZW VtKnTx8WLlzYgS0UQgghRGdjcNET6u9B4gA/xoT40NvbjcqGJoqrG6msN2Ox823VS2Fw0TPU3/7zDNsl AXz00UeZOHEieXl5TJw4kUcfffSC6z700EMkJCR0YOuEEEII0ZmdKR4ZEujJhIH+XN3PGz8PZ07Vmimu bqSmscnuz9h1dnZJADds2MAtt9wCwC233ML69evPu97u3bspKipiypQpHdg6IYQQQnQVZ4pHonp5MSHM n2G9e+DmpMNU00hJTSP15mZ7N7FTssszgEVFRQQFBQHQs2dPioqK2qxjsVi49957efXVV9myZUtHN1EI IYQQXYyTTkvPHq707OFKvbkZU3UDR8vqKK5pRKeBHi56nLrITB22ZrMEcNKkSZw8ebLN8hUrVrR6rdFo zju+z7/+9S+mTp1Knz59fnFf6enppKenA3Dy5EkKCgp+Zasvj8lk6pD9OCqJr21JfG1L4mtbEl/b6i7x 1QGhrlCna+ZUTSOFRQ00Nllw0mlwc9Jjr1ywrrKMk4WFuNixktlmCeDFeu0CAwMpLCwkKCiIwsJCjEZj m3VycnLYtm0b//rXv6iurqaxsRGDwXDe5wUXLFjAggULABgxYgS9evVqvwP5BR25L0ck8bUtia9tSXxt S+JrW90tvgMApRQV9U0UVtZzvKKexmaFq17T4TOPlNc10TMoyK6VwHa5BZySkkJmZiZLly4lMzOT6dOn t1nntddes/47IyOD3NzcixaLCCGEEEJcjEajwdvNCW83J64KMFBeZ+Z4ecvMI2jOzDziGCPk2aXvcenS pWzevJmwsDC2bNnC0qVLAcjNzSUtLc0eTRJCCCGEAzlTPBLdu6V4JKZXD1yddBRXN2KqbqS+qXsXj9gl zfXz8+OTTz5ps3zEiBG8+OKLbZanpqaSmpraAS0TQgghhKNx1v+neKTO3EyJAxSPOEY/pxBCCCHEJXBz 0tHXx52+Pu5UNzRRVFXPz2X1lNWZcdZp8XTRo+vkM49cCkkAhRBCCCHOw+Cix+BiINTPo1XxSFOzBTe9 DoOL7rwjmXQFkgAKIYQQQlzEucUjZbWNHK+op6iqAQsKDyddlyse6VqtFUIIIYSwI51Wg7/BBX+DC41N FkprGvi5vJ7i6ka0GjC46HDV2294l0slCaAQQgghxK/grNcS5OVGkJdb6+KR6gb0Wg2enbh4RBJAIYQQ QogrdHbxSFV9E0XV9fx8qo6G5s5ZPCIJoBBCCCFEO/J01ePpaiDU14OKevPp4pEGmi0txSNKKXs3URJA IYQQQghb0Go1+Lg74+PuzCCjoqy2kWPldVToNdi7L1ASQCGEEEIIGzu7eCRAU4OrHecBBjtNBSeEEEII 4ai0nWDsQEkAhRBCCCEcjCSAQgghhBAORhJAIYQQQggHIwmgEEIIIYSDkQRQCCGEEMLBaFRnGI2wHfn7 +xMSEtIh+zKZTAQEBHTIvhyRxNe2JL62JfG1LYmvbUl8basj45ufn09JSUmb5d0uAexII0aMIDc3197N 6LYkvrYl8bUtia9tSXxtS+JrW50hvnILWAghhBDCwUgCKIQQQgjhYCQBvAILFiywdxO6NYmvbUl8bUvi a1sSX9uS+NpWZ4ivPAMohBBCCOFgpAdQCCGEEMLBOGwCuGLFCsLDw4mKiiImJoavvvrqire5fPlyHnvs sXZoXdel0WiYM2eO9XVTUxMBAQFMmzatXbbvyDEuLS0lJiaGmJgYevbsSe/eva2vGxsb220/2dnZ7fZ9 dRaLFy/mqaeesr5OSkoiLS3N+vree+/liSee+MXt5OfnExERYYsmWhkMBptuvyNd6Jz19vZm6NChNt9/ RkYGCxcutPl+OjOdTmf9DmJiYsjPz2+zztSpUykvL2+z3JGvt2e7nHwhIyODgoKCK95nSEjIeYduaU96 m269k8rJySErK4s9e/bg4uJCSUlJu/4BdWQeHh5899131NXV4ebmxubNm+ndu7e9m9Ut+Pn5sXfvXqDl wmwwGLjvvvvs26guYuzYsbz99tvcfffdWCwWSkpKqKystL6/Y8cOnnzySTu2sHu60Dmbn59/RT8ympqa 0Osd8s/XZXNzc7N+B+dSSqGU4oMPPujYRnUhl5svZGRkEBERQa9evS55H/Y6nx2yB7CwsBB/f39cXFyA lsGje/Xq1Srjzs3NJTExEWi5cM2fP5/ExERCQ0N55plnrNtasWIFV111FePGjePQoUPW5S+88AIjR44k Ojqa66+/ntraWqqqqujfvz9msxmAysrKVq+7i6lTp7Jx40YA3njjDWbPnm1979SpU8yYMYOoqChGjx7N N998A0iMf63U1FTWrl1rfX1279HKlSsZOXIkUVFRLFu2DICamhqSk5OJjo4mIiKCt956C4CPPvqIwYMH Exsby7vvvmvdxs6dO4mLi2PYsGGMGTPGGv+EhIRWf1TGjRvHvn37bHmoV2TMmDHk5OQA8P333xMREYGn pydlZWU0NDRw4MABNBoN48ePZ/jw4SQlJVFYWAjA7t27iY6OJjo6mn/+85/WbWZkZPDb3/6Wa6+9lrCw MP785z9b39u0aRNxcXHExsYya9YsqqurAVi6dClDhw4lKirKmrwfOXKEuLg4IiMjefDBB63bqK6uZuLE icTGxhIZGcmGDRsA+J//+Z9WvZkPPPAATz/9tG0CZ0PNzc3cfvvthIeHM2XKFOrq6gBITEy0jo9WUlJi Hdg/IyODlJQUJkyYwMSJEyksLCQhIYGYmBgiIiLYtm0bAKtXr+aqq67i6quv5osvvrDu7/3332fUqFEM GzaMSZMmUVRUhMViISwsDJPJBIDFYmHgwIHW191Rfn4+gwYNYt68eURERHDs2LFWf/vketvahfKFv/71 r4wcOZKIiAgWLFiAUoq1a9eSm5vLzTffTExMDHV1dRfNK+bOncvYsWOZO3cupaWlTJkyhfDwcNLS0ji7 PGPGjBkMHz6c8PBw0tPTAXj55Ze5++67reu88MILLF68+PIOTjmgqqoqFR0drcLCwtQf/vAHlZ2drZRS Kjg4WJlMJqWUUrt27VLjx49XSim1bNkyFRcXp+rr65XJZFK+vr6qsbFR5ebmqoiICFVTU6MqKirUgAED 1MqVK5VSSpWUlFj398ADD6hnnnlGKaVUamqqWrdunVJKqeeff17dc889HXTUHcPDw0Pt27dPXX/99aqu rk5FR0erzz77TCUnJyullFq4cKFavny5UkqpTz75REVHRyulJMaXa9myZWrlypXqlltuUe+88451uYeH h1JKqY8//ljdfvvtymKxqObmZpWcnKw+//xztXbtWpWWlmZdv7y8XNXV1ak+ffqow4cPK4vFombNmmX9 vioqKpTZbFZKKbV582b129/+VimlVEZGhvrTn/6klFLq0KFDavjw4R1x2FckJCREHT16VD333HNq1apV 6sEHH1QbN25U27dvV6NHj1ZxcXGquLhYKaXUm2++qW699VallFKRkZHq888/V0opdd9996nw8HCllFKr V69W/fv3t8awX79+6ueff1Ymk0nFx8er6upqpZRSjz76qHr44YdVSUmJuuqqq5TFYlFKKVVWVqaUUuq6 665TmZmZSimlnn32Wet3aDabVUVFhVJKKZPJpAYMGKAsFos6cuSIGjZsmFJKqebmZhUaGtrq/0Jndeac VUqpI0eOKJ1Op77++mullFKzZs1Sr7zyilJKqfHjx6tdu3YppVqOOzg4WCnVEu/evXur0tJSpZRSjz32 mHrkkUeUUko1NTWpyspKVVBQoPr27auKi4tVQ0ODGjNmjPrjH/+olFLq1KlT1ti/8MIL1uvC8uXL1ZNP PqmUavl/c+Yc7y60Wq2Kjo5W0dHRasaMGerIkSNKo9GonJwc6zpn/vbJ9batC+ULZ85DpZSaM2eOeu+9 95RSrc9fpS6eV8TGxqra2lqllFKLFi1SDz/8sFJKqaysLAVYP3dmX7W1tSo8PFyVlJSoqqoqFRoaqhob G5VSSsXFxalvvvnmso7NIXsADQYDu3fvJj09nYCAAG688UYyMjIu+pnk5GRcXFzw9/fHaDRSVFTEtm3b mDlzJu7u7vTo0YOUlBTr+t999x3x8fFERkby2muv8f333wOQlpbG6tWrgZZfqrfeeqvNjtNeoqKiyM/P 54033mDq1Kmt3tu+fTtz584FYMKECZSWllpvxUmM28+mTZvYtGkTw4YNIzY2loMHD5KXl0dkZCSbN2/m v//7v9m2bRteXl4cPHiQ/v37ExYW1uYZzoqKCmbNmkVERASLFy+2xnjWrFlkZWVhNpt5+eWXSU1NtdOR XroxY8awY8cOduzYQVxcHHFxcdbXvXv35rvvvmPy5MnExMTwyCOPcPz4ccrLyykvLychIQHAeu6eMXHi RLy8vHB1dWXo0KEcPXqUL7/8kv379zN27FhiYmLIzMzk6NGj1vVuu+023n33Xdzd3QH44osvrL3kZ29f KcVf/vIXoqKimDRpEidOnKCoqIiQkBD8/Pz4+uuvrd+xn59fB0Wx/fTv35+YmBgAhg8fft5n0841efJk fH19ARg5ciSrV69m+fLlfPvtt3h6evLVV1+RmJhIQEAAzs7O3HjjjdbPHj9+nKSkJCIjI1m5cqX1XJ4/ fz5r1qwBWnpVutv14swt4L1797Ju3ToAgoODGT16dJt15Xrb1oXyhc8++4xRo0YRGRnJp59+ao3H5UhJ ScHNzQ2ArVu3Wq+9ycnJ+Pj4WNd75plniI6OZvTo0Rw7doy8vDwMBgMTJkwgKyuLgwcPYjabiYyMvKz9 O+xDFDqdjsTERBITE4mMjCQzMxO9Xo/FYgGgvr6+1fpnun/PfLapqemi209NTWX9+vVER0eTkZFBdnY2 0PIsUn5+PtnZ2TQ3N9v8gXJ7SUlJ4b777iM7O5vS0tJL+ozE+PKdfc5aLBbrsylKKe6//35+//vft/nM nj17+OCDD3jwwQeZOHFiq4v8uR566CGuueYa1q1bR35+vvX2hbu7O5MnT2bDhg28/fbb7N69u/0Prp2N HTuWHTt28O233xIREUHfvn15/PHH6dGjB4mJiZw4ccJ6m/iM8z0Yf7bznbNKKSZPnswbb7zRZv2dO3fy ySefsHbtWp599lk+/fRToKV46lyvvfYaJpOJ3bt34+TkREhIiPW6lJaWRkZGBidPnmT+/PmXG4pO4dzY nbkFfLHrsIeHh/XfCQkJbN26lY0bN5Kamso999xDjx49Lri/RYsWcc8995CSkkJ2djbLly8HoG/fvgQG BvLpp5+yc+dOXnvttfY6xE7r7DheKke+3p6bLzz//PN888035Obm0rdvX5YvX97mXD3jUs/nC8nOzmbL li3k5OTg7u5OYmJiq+vA//3f/zF48OBflXg7ZA/goUOHyMvLs77eu3cvwcHBhISEWP+Q/fvf//7F7SQk JLB+/Xrq6uqoqqri/ffft75XVVVFUFAQZrO5zQVl3rx53HTTTd3ul9LZ5s+fz7Jly9r8IomPj7fGIzs7 G39//4tetCXGF3f2Ofvee+9Zn71JSkri5Zdftj57duLECYqLiykoKMDd3Z05c+awZMkS9uzZw+DBg8nP z+fHH38EaJW4VFRUWIt4zu0lT0tL46677mLkyJGtfq12VmPGjCErKwtfX190Oh2+vr6Ul5eTk5PD7Nmz MZlM1gTQbDbz/fff4+3tjbe3N9u3bwe4pORg9OjRfPHFF/zwww9Ay3OXhw8fprq6moqKCqZOncqTTz5p fWZy7NixvPnmm222X1FRgdFoxMnJic8++4yjR49a35s5cyYfffQRu3btIikpqX0C1EmcfU6f/XzruY4e PUpgYCC33347aWlp7Nmzh1GjRvH5559TWlqK2WzmnXfesa5/9rmcmZnZaltpaWnMmTOHWbNmodPpbHBU XYNcb9s6X74waNAgoOV5wOrq6lbnqaenJ1VVVdbXl5pXJCQk8PrrrwPw4YcfUlZWBrSctz4+Pri7u3Pw 4EG+/PJL62dGjRrFsWPHeP3111s9a3+pHLIHsLq6mkWLFlFeXo5er2fgwIGkp6dz4MABbrvtNh566CFr T8fFxMbGcuONNxIdHY3RaGTkyJHW9/73f/+XUaNGERAQwKhRo1qdEDfffDMPPvjgr/rCuoo+ffpw1113 tVl+ptgjKioKd3f3Nhfic0mML+72229n+vTpREdHc+2111p/UU6ZMoUDBw4QFxcHtNzGePXVV/nhhx9Y smQJWq0WJycnVq1ahaurK+np6SQnJ+Pu7k58fLw1ln/+85+55ZZbeOSRR0hOTm617+HDh9OjR48uc9GP jIykpKSEm266qdWy6upqjEYja9eu5a677qKiooKmpibuvvtuwsPDWb16NfPnz0ej0TBlypRf3E9AQAAZ GRnMnj2bhoYGAB555BE8PT2ZPn069fX1KKWsw848/fTT3HTTTfztb39j+vTp1u3cfPPNXHfddURGRjJi xAgGDx5sfc/Z2ZlrrrkGb2/vbpew3Hfffdxwww3Wc/JCsrOzWblyJU5OThgMBtasWUNQUBDLly8nLi4O b29v6y1maLn2zJo1Cx8fHyZMmMCRI0es76WkpHDrrbd2mXPZVuR629aF8gVvb28iIiLo2bNnqzilpqZy xx134ObmRk5ODsuWLbukvGLZsmXMnj2b8PBwxowZQ79+/QC49tpree655xgyZAiDBg1qc+v+hhtuYO/e vb/qR7jMBGIHa9euZcOGDbzyyiv2bkq3JTG2vYKCAhITEzl48CBarUPeTLAbi8VCbGws77zzDmFhYfZu TpeXm5vL4sWLrZXE4vLI9dZ+pk2bxuLFi5k4ceJlf9YhewDtadGiRXz44Ycy7pINSYxtb82aNTzwwAM8 8cQTkvx1sP379zNt2jRmzpwpyV87ePTRR1m1apVDPPtnC3K9tY/y8nKuvvpqoqOjf1XyB9IDKIQQQgjh cOSnuxBCCCGEg5EEUAghhBDCwUgCKIQQQgjhYCQBFEJ0azqdjpiYGMLDw4mOjubxxx+3DsxqK0uWLCE8 PJwlS5bYdD/5+fndcuBdIYTtSRWwEKJbOzMVFkBxcTE33XQTlZWVPPzwwzbbZ3p6OqdOnep2Y/QJIboP 6QEUQjgMo9FIeno6zz77LEop8vPziY+PJzY2ltjYWHbs2AG0zGywfv166+duvvlmNmzY0GpbSimWLFlC REQEkZGRvPXWW0DLoMLV1dUMHz7cuuyMyMhIysvLUUrh5+dnnYN23rx5bN68mebmZpYsWcLIkSOJiori +eeft3525cqV1uXLli1rc2w//fQTw4YNY9euXe0SKyFE9yY9gEIIhxIaGkpzczPFxcUYjUY2b96Mq6sr eXl5zJ49m9zcXG677TaefPJJZsyYQUVFBTt27Ggza827777L3r172bdvHyUlJYwcOZKEhATee+89DAaD tdfxbGPHjuWLL74gODiY0NBQtm3bxrx588jJyWHVqlW89NJLeHl5sWvXLhoaGhg7dixTpkwhLy+PvLw8 du7ciVKKlJQUtm7dap0t4NChQ/zXf/0XGRkZREdHd0QYhRBdnCSAQgiHZTabWbhwIXv37kWn03H48GEA xo8fz5133onJZOLf//43119/PXp968vl9u3bmT17NjqdjsDAQMaPH8+uXbtISUm54P7i4+PZunUrwcHB /OEPfyA9PZ0TJ07g4+ODh4cHmzZt4ptvvrHOLVpRUUFeXh6bNm1i06ZNDBs2DGiZniovL49+/fphMpmY Pn067777LkOHDrVRpIQQ3Y0kgEIIh/LTTz+h0+kwGo08/PDDBAYGsm/fPiwWC66urtb15s2bx6uvvsqb b77J6tWr22XfCQkJ/POf/+Tnn39mxYoVrFu3jrVr1xIfHw+03Fb+xz/+QVJSUqvPffzxx9x///38/ve/ b7U8Pz8fLy8v+vXrx/bt2yUBFEJcMnkGUAjhMEwmE3fccQcLFy5Eo9FQUVFBUFAQWq2WV155hebmZuu6 qampPPXUUwDnTazi4+N56623aG5uxmQysXXrVq6++uqL7r9v376UlJSQl5dHaGgo48aN47HHHiMhIQGA pKQkVq1ahdlsBuDw4cPU1NSQlJTEyy+/THV1NQAnTpyguLgYAGdnZ9atW8eaNWt4/fXXrzhGQgjHID2A Qohura6ujpiYGMxmM3q9nrlz53LPPfcAcOedd3L99dezZs0arr32Wjw8PKyfCwwMZMiQIcyYMeO82505 cyY5OTlER0ej0Wj4+9//Ts+ePX+xPaNGjbImmvHx8dx///2MGzcOgLS0NPLz84mNjUUpRUBAAOvXr2fK lCkcOHCAuLg4AAwGA6+++qq1ytjDw4OsrCwmT56MwWC46G1oIYQAmQtYCCHOq7a2lsjISPbs2YOXl5e9 myOEEO1KbgELIcQ5tmzZwpAhQ1i0aJEkf0KIbkl6AIUQQgghHIz0AAohhBBCOBhJAIUQQgghHIwkgEII IYQQDkYSQCGEEEIIByMJoBBCCCGEg5EEUAghhBDCwfx/CecBxu6DOpcAAAAASUVORK5CYII=\n", | |||
"text/plain": [ | "text/plain": [ | |||
"<Figure size 648x432 with 2 Axes>" | "<Figure size 648x432 with 2 Axes>" | |||
] | ] | |||
}, | }, | |||
"metadata": {}, | "metadata": {}, | |||
"output_type": "display_data" | "output_type": "display_data" | |||
} | } | |||
], | ], | |||
"source": [ | "source": [ | |||
"fig = m.plot_components(forecast)" | "fig = m.plot_components(forecast)" | |||
skipping to change at line 316 | skipping to change at line 339 | |||
}, | }, | |||
{ | { | |||
"cell_type": "markdown", | "cell_type": "markdown", | |||
"metadata": {}, | "metadata": {}, | |||
"source": [ | "source": [ | |||
"There are upstream issues in PyStan for Windows which make MCMC sampling ex tremely slow. The best choice for MCMC sampling in Windows is to use R, or Pytho n in a Linux VM." | "There are upstream issues in PyStan for Windows which make MCMC sampling ex tremely slow. The best choice for MCMC sampling in Windows is to use R, or Pytho n in a Linux VM." | |||
] | ] | |||
} | } | |||
], | ], | |||
"metadata": { | "metadata": { | |||
"celltoolbar": "Edit Metadata", | ||||
"kernelspec": { | "kernelspec": { | |||
"display_name": "Python 2", | "display_name": "Python 3", | |||
"language": "python", | "language": "python", | |||
"name": "python2" | "name": "python3" | |||
}, | }, | |||
"language_info": { | "language_info": { | |||
"codemirror_mode": { | "codemirror_mode": { | |||
"name": "ipython", | "name": "ipython", | |||
"version": 2 | "version": 3 | |||
}, | }, | |||
"file_extension": ".py", | "file_extension": ".py", | |||
"mimetype": "text/x-python", | "mimetype": "text/x-python", | |||
"name": "python", | "name": "python", | |||
"nbconvert_exporter": "python", | "nbconvert_exporter": "python", | |||
"pygments_lexer": "ipython2", | "pygments_lexer": "ipython3", | |||
"version": "2.7.14+" | "version": "3.8.3" | |||
} | } | |||
}, | }, | |||
"nbformat": 4, | "nbformat": 4, | |||
"nbformat_minor": 1 | "nbformat_minor": 1 | |||
} | } | |||
End of changes. 19 change blocks. | ||||
151 lines changed or deleted | 181 lines changed or added |