diff --git a/README.md b/README.md
index 8c563372..c0a835f5 100644
--- a/README.md
+++ b/README.md
@@ -188,7 +188,7 @@ The easiest way to launch a data generation from a trained model consists in usi
 ...	'path/to/your/trained/model'
 ... )
 >>> my_sampler_config = MAFSamplerConfig(
-...	n_made_blocks=2,
+...	n_blocks=2,
 ...	n_hidden_in_made=3,
 ...	hidden_size=128
 ... )
diff --git a/docs/source/pipelines/pythae.pipelines.rst b/docs/source/pipelines/pythae.pipelines.rst
index 32372275..177916bf 100644
--- a/docs/source/pipelines/pythae.pipelines.rst
+++ b/docs/source/pipelines/pythae.pipelines.rst
@@ -75,7 +75,7 @@ provided in Pythae you only need 1) a trained model, 2) the sampler's configurat
    ...	'path/to/your/trained/model'
    ... )
    >>> my_sampler_config = MAFSamplerConfig(
-   ...	n_made_blocks: int = 2
+   ...	n_blocks: int = 2
    ...	n_hidden_in_made: int = 3
    ...	hidden_size: int = 128
    ... )
diff --git a/examples/notebooks/models_training/normalizing_flows_training.ipynb b/examples/notebooks/models_training/normalizing_flows_training.ipynb
index a564e93d..08f31817 100644
--- a/examples/notebooks/models_training/normalizing_flows_training.ipynb
+++ b/examples/notebooks/models_training/normalizing_flows_training.ipynb
@@ -12,9 +12,18 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 5,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The autoreload extension is already loaded. To reload it, use:\n",
+      "  %reload_ext autoreload\n"
+     ]
+    }
+   ],
    "source": [
     "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",
@@ -31,7 +40,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -44,7 +53,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -52,11 +61,11 @@
     "\n",
     "prior = MultivariateNormal(torch.zeros(2).to(device), torch.eye(2).to(device))\n",
     "\n",
-    "conf = MAFConfig(input_dim=(2,), n_hidden_in_made=3, hidden_size=24, n_made_blocks=4, include_batch_norm=False)\n",
+    "conf = MAFConfig(input_dim=(2,), n_hidden_in_made=3, hidden_size=24, n_blocks=4, include_batch_norm=False)\n",
     "flow = MAF(conf)\n",
     "\n",
-    "# conf = IAFConfig(input_dim=(2,), n_hidden_in_made=3, hidden_size=24, n_made_blocks=2, include_batch_norm=False)\n",
-    "# flow = IAF(conf)\n",
+    "#conf = IAFConfig(input_dim=(2,), n_hidden_in_made=3, hidden_size=24, n_blocks=2, include_batch_norm=False)\n",
+    "#flow = IAF(conf)\n",
     "\n",
     "\n",
     "contained_flow = NFModel(prior, flow)"
@@ -64,7 +73,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -78,7 +87,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -86,13 +95,15 @@
      "output_type": "stream",
      "text": [
       "Preprocessing train data...\n",
+      "Checking train dataset...\n",
       "Preprocessing eval data...\n",
       "\n",
+      "Checking eval dataset...\n",
       "Using Base Trainer\n",
       "\n",
       "Model passed sanity check !\n",
       "\n",
-      "Created dummy_output_dir/IAF_training_2022-06-13_20-17-16. \n",
+      "Created dummy_output_dir/MAF_training_2022-10-11_17-30-56. \n",
       "Training config, checkpoints and final model will be saved here.\n",
       "\n",
       "Successfully launched training !\n",
@@ -102,7 +113,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "d5b4acaa8b324d8ea7bbcd4220c7a22f",
+       "model_id": "35d4e586f3d04d30bfdee4dcd39b47ec",
        "version_major": 2,
        "version_minor": 0
       },
@@ -116,7 +127,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "0f7da1ea5cd7420daf99b72a95bdefb0",
+       "model_id": "2e56fab1926d4a1e9b8ab5c5d358bbc7",
        "version_major": 2,
        "version_minor": 0
       },
@@ -132,15 +143,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 196.502\n",
-      "Eval loss: 170.852\n",
+      "Train loss: 184.328\n",
+      "Eval loss: 161.8518\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "0a41a183c9b04113b2cb80ece717c3bc",
+       "model_id": "a69d940f4dc34ee8aec0fbaaaa965f49",
        "version_major": 2,
        "version_minor": 0
       },
@@ -154,7 +165,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "ca5eba93763c455ba52cbfccf071bc98",
+       "model_id": "c5710de309a846e5be5af97ff8f875fc",
        "version_major": 2,
        "version_minor": 0
       },
@@ -170,15 +181,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 160.8794\n",
-      "Eval loss: 149.645\n",
+      "Train loss: 152.1601\n",
+      "Eval loss: 146.8646\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "8e1896e06c544bbfbc65be01695c0930",
+       "model_id": "fa1506b62f7547c3a699abe9bcaabb90",
        "version_major": 2,
        "version_minor": 0
       },
@@ -192,7 +203,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "aabbd38611b84bb8ba350f9a89ef0ae9",
+       "model_id": "a1718634cf304de28f2232c03efd8002",
        "version_major": 2,
        "version_minor": 0
       },
@@ -208,15 +219,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 143.3026\n",
-      "Eval loss: 136.63\n",
+      "Train loss: 132.7612\n",
+      "Eval loss: 123.2201\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "06c7c90850ff41a895e17fe37c905b86",
+       "model_id": "c17a4c2a79444b6c917818eae2fa7463",
        "version_major": 2,
        "version_minor": 0
       },
@@ -230,7 +241,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "40052dd95f8c47f99f41b9ce040b676a",
+       "model_id": "ab48ccdd2e824497bf2ac6e96ad4554b",
        "version_major": 2,
        "version_minor": 0
       },
@@ -246,15 +257,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 134.135\n",
-      "Eval loss: 128.9466\n",
+      "Train loss: 114.7159\n",
+      "Eval loss: 100.2041\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "3e976d434e2047f6bcad4ded805310cd",
+       "model_id": "cb4bfba783924c8a96d7033d01c53bca",
        "version_major": 2,
        "version_minor": 0
       },
@@ -268,7 +279,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "80781e4b476740609b5d6ccc26fc8cb2",
+       "model_id": "1e2e99acba5e40749ef08e0b2c2cebda",
        "version_major": 2,
        "version_minor": 0
       },
@@ -284,15 +295,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 128.7787\n",
-      "Eval loss: 125.3792\n",
+      "Train loss: 110.5958\n",
+      "Eval loss: 101.2492\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "380762e321c3484f96897aae58433e1d",
+       "model_id": "29c8647ba38b42c0bf7ca05460ae6846",
        "version_major": 2,
        "version_minor": 0
       },
@@ -306,7 +317,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "0d36e852ac94421f937918ceb3920208",
+       "model_id": "f00fd8484491471c9d5bf814f0df3576",
        "version_major": 2,
        "version_minor": 0
       },
@@ -322,15 +333,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 124.8889\n",
-      "Eval loss: 131.5444\n",
+      "Train loss: 89.4724\n",
+      "Eval loss: 78.5732\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "bccd0ab269d143818e2480abb6896cab",
+       "model_id": "0f5158edc9164449b5a87682868c1bef",
        "version_major": 2,
        "version_minor": 0
       },
@@ -344,7 +355,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "a19e3d4d2ae44875b24c256ec2b699d9",
+       "model_id": "3e3f8307b13246479ff5dc355f327492",
        "version_major": 2,
        "version_minor": 0
       },
@@ -360,15 +371,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 132.9134\n",
-      "Eval loss: 120.4659\n",
+      "Train loss: 73.8978\n",
+      "Eval loss: 60.217\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "757a7776313e402eaccfbab683c7dd46",
+       "model_id": "558ec75df84245e088237ea2d21ee291",
        "version_major": 2,
        "version_minor": 0
       },
@@ -382,7 +393,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "8f0ad9e907fa4f49b57e0a9c72b3df8b",
+       "model_id": "f22eab113d8a459d82479ee0c3ec0c93",
        "version_major": 2,
        "version_minor": 0
       },
@@ -398,15 +409,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 115.3224\n",
-      "Eval loss: 116.0495\n",
+      "Train loss: 64.3036\n",
+      "Eval loss: 59.2912\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "70417b1bd7714f2e93755b803d72c3c4",
+       "model_id": "c54c1453786d48d68213ce0fb50ba8f0",
        "version_major": 2,
        "version_minor": 0
       },
@@ -420,7 +431,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "61f6655fa472444892c58afdd35dd741",
+       "model_id": "29572661c7394b63b380b1429952e9de",
        "version_major": 2,
        "version_minor": 0
       },
@@ -436,15 +447,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 113.405\n",
-      "Eval loss: 109.1003\n",
+      "Train loss: 58.2209\n",
+      "Eval loss: 53.6635\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "4c8ed7c985bf43b29bb5c892f5b2ef4a",
+       "model_id": "cad47a11594b4a5e8803dd4ffd099048",
        "version_major": 2,
        "version_minor": 0
       },
@@ -458,7 +469,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "c0a270b88f2b4f0491eefbfad7202035",
+       "model_id": "6695951f75534b359964a98deacb1a5d",
        "version_major": 2,
        "version_minor": 0
       },
@@ -474,15 +485,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 108.749\n",
-      "Eval loss: 107.0812\n",
+      "Train loss: 57.1512\n",
+      "Eval loss: 56.1623\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "c20737ccb4ff4234abae047cdf619e17",
+       "model_id": "d460714d9be8415daff0f166a4b1fa9f",
        "version_major": 2,
        "version_minor": 0
       },
@@ -496,7 +507,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "a2a206580b2e4154ac17a921422a4b22",
+       "model_id": "1090dd186add44c78dccfdf35f6ca526",
        "version_major": 2,
        "version_minor": 0
       },
@@ -512,15 +523,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 106.9947\n",
-      "Eval loss: 103.0454\n",
+      "Train loss: 56.963\n",
+      "Eval loss: 56.4587\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "bc7cfaa7052b4fa097721e6b88f6023f",
+       "model_id": "95a336f683cb468cb0c030b6abd16289",
        "version_major": 2,
        "version_minor": 0
       },
@@ -534,7 +545,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "6d323205cb5c4b53b84eba5ab13782d2",
+       "model_id": "833c80b1d948408a95680dc9a11114d6",
        "version_major": 2,
        "version_minor": 0
       },
@@ -550,15 +561,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 99.1485\n",
-      "Eval loss: 93.6906\n",
+      "Train loss: 54.9752\n",
+      "Eval loss: 50.3529\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "94b94ce3c93944fba5f0eb4ddc179bed",
+       "model_id": "e6001303199545bf9307d492e9777894",
        "version_major": 2,
        "version_minor": 0
       },
@@ -572,7 +583,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "50267d3e762a4d7f9aa32907b9605498",
+       "model_id": "dc531aadb338442e9e0d5357a79e4e32",
        "version_major": 2,
        "version_minor": 0
       },
@@ -588,15 +599,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 85.6769\n",
-      "Eval loss: 82.0904\n",
+      "Train loss: 50.3636\n",
+      "Eval loss: 44.0703\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "8a91431c788d49e0953565352542d426",
+       "model_id": "bd784ca3ecbf44a19d855ba4d8c23e7a",
        "version_major": 2,
        "version_minor": 0
       },
@@ -610,7 +621,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "0565360eb7904723b2bc24ff09b28d82",
+       "model_id": "f803f4ec04984e0c9d46e0b1a84715cd",
        "version_major": 2,
        "version_minor": 0
       },
@@ -626,15 +637,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 74.6891\n",
-      "Eval loss: 75.3146\n",
+      "Train loss: 49.1614\n",
+      "Eval loss: 46.4413\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "eea31a6788e04bfa88276760683a615b",
+       "model_id": "ea4317c004484e2dbc51bdd7c8422084",
        "version_major": 2,
        "version_minor": 0
       },
@@ -648,7 +659,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "5af4f21b9b5a4151aa8c30cc387ab45c",
+       "model_id": "c0f3aaf626e0443e961b412025355cae",
        "version_major": 2,
        "version_minor": 0
       },
@@ -664,15 +675,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 73.2037\n",
-      "Eval loss: 75.3926\n",
+      "Train loss: 47.4819\n",
+      "Eval loss: 44.7632\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "0072d6b8740b4044a2f0c8305be898f8",
+       "model_id": "ee35897cd2fd4af198b8ecb5731418ef",
        "version_major": 2,
        "version_minor": 0
       },
@@ -686,7 +697,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "40a1f0a1f05f407f8cb421a04dc65245",
+       "model_id": "9197fa62a15e47e893ed8e173ea365f2",
        "version_major": 2,
        "version_minor": 0
       },
@@ -702,15 +713,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 69.9102\n",
-      "Eval loss: 73.4069\n",
+      "Train loss: 47.0086\n",
+      "Eval loss: 44.9806\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "9071768cbc28448cad4d23a3088626ec",
+       "model_id": "12829758c3864403a794966b4849785f",
        "version_major": 2,
        "version_minor": 0
       },
@@ -724,7 +735,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "5c7eabed3d4e44388c83764c071a78c4",
+       "model_id": "2e651b1b0437419e87bbfc7148c1902b",
        "version_major": 2,
        "version_minor": 0
       },
@@ -740,15 +751,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 67.7733\n",
-      "Eval loss: 68.4136\n",
+      "Train loss: 46.9667\n",
+      "Eval loss: 44.1112\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "d14576255d224cb08850a062426a422c",
+       "model_id": "ed2ce98073d04c258ebb6f8368bcc18a",
        "version_major": 2,
        "version_minor": 0
       },
@@ -762,7 +773,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "09173c98513a478cb261de66695a16c4",
+       "model_id": "63689ae4e99447deb9ec395d62ff7d9e",
        "version_major": 2,
        "version_minor": 0
       },
@@ -778,15 +789,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 67.2819\n",
-      "Eval loss: 71.3228\n",
+      "Train loss: 45.0875\n",
+      "Eval loss: 38.6945\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "83234a9b9f5d49fb81399c1bf1ed2f76",
+       "model_id": "0c137ff4672045d9b2b821914eed3dd7",
        "version_major": 2,
        "version_minor": 0
       },
@@ -800,7 +811,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "f5d1016e6d8d4cf18bab788b3b9b816d",
+       "model_id": "2816ec6bcf084714bbd9bfe2e54bad35",
        "version_major": 2,
        "version_minor": 0
       },
@@ -816,15 +827,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 67.9069\n",
-      "Eval loss: 68.826\n",
+      "Train loss: 44.0051\n",
+      "Eval loss: 38.5322\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "c355901907864553a3521a795e53636f",
+       "model_id": "7763c1f75ce5423881955c4872627e1b",
        "version_major": 2,
        "version_minor": 0
       },
@@ -838,7 +849,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "404180ef20a64af0a4e32ffe5f32d346",
+       "model_id": "f6589e54f715487b9a03f48a417b0e8b",
        "version_major": 2,
        "version_minor": 0
       },
@@ -854,15 +865,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 65.4511\n",
-      "Eval loss: 65.7339\n",
+      "Train loss: 44.6618\n",
+      "Eval loss: 42.3022\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "2c92aeeefbe54d7bb0ab81231e2bd7fb",
+       "model_id": "6ef26d0e53fa4e21b88b4150eb0c6138",
        "version_major": 2,
        "version_minor": 0
       },
@@ -876,7 +887,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "be94925ea59145cdbc5e37ca3de47417",
+       "model_id": "8d2f2ad7850840aaa4ab8e964f143dd5",
        "version_major": 2,
        "version_minor": 0
       },
@@ -892,15 +903,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 65.7002\n",
-      "Eval loss: 64.076\n",
+      "Train loss: 43.1473\n",
+      "Eval loss: 40.0984\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "11af2d040e4047868335f79dae50e742",
+       "model_id": "640fe5e144a945d7a7eeb39e19b2fd8d",
        "version_major": 2,
        "version_minor": 0
       },
@@ -914,7 +925,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "ebe2d2f5555f4dd7a732fbb6a8db05cf",
+       "model_id": "86deacc7961146828cdab7f69d8f7c65",
        "version_major": 2,
        "version_minor": 0
       },
@@ -930,15 +941,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 63.9603\n",
-      "Eval loss: 67.954\n",
+      "Train loss: 44.6584\n",
+      "Eval loss: 39.8881\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "abd2f574d97f42af9b398a07f63cbb65",
+       "model_id": "17f4c46492374dc69bc3b4e88036d233",
        "version_major": 2,
        "version_minor": 0
       },
@@ -952,7 +963,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "30aa0478cd874637992b7fa5649f3d29",
+       "model_id": "cb363f2558144ebf8ca6377b220eaca6",
        "version_major": 2,
        "version_minor": 0
       },
@@ -968,15 +979,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 63.3227\n",
-      "Eval loss: 64.0264\n",
+      "Train loss: 45.5855\n",
+      "Eval loss: 37.6275\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "67bae0c9d34846958f7e4a56b20ccdc7",
+       "model_id": "0640e09e33be4373a0dc299c2e0fd9c4",
        "version_major": 2,
        "version_minor": 0
       },
@@ -990,7 +1001,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "b7fa8755b18949268f0394dc9c7b0439",
+       "model_id": "2758b9f04e7340878b003b88dc95ce94",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1006,15 +1017,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 63.8905\n",
-      "Eval loss: 66.8284\n",
+      "Train loss: 44.3301\n",
+      "Eval loss: 42.4146\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "e034722d61d4439db1ab8d75af961d55",
+       "model_id": "1dca223973b8481cabe986e461153db5",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1028,7 +1039,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "ce01689368f3418b859d3114cf0aebe3",
+       "model_id": "7a388a41de5e44548cf661e4ffeffa67",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1044,15 +1055,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 63.0264\n",
-      "Eval loss: 64.7744\n",
+      "Train loss: 43.6667\n",
+      "Eval loss: 40.0082\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "253a6c951d254300a99e01726243ded3",
+       "model_id": "a1775308900c47dda2110bdb42c891e9",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1066,7 +1077,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "d3362b09bcf745c6b772a539ff1b4bfb",
+       "model_id": "9175f4f8d6b941029b817d667e6977b0",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1082,15 +1093,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 62.6988\n",
-      "Eval loss: 65.8102\n",
+      "Train loss: 42.445\n",
+      "Eval loss: 42.7074\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "85bc433a6a7a4a979e3719d35354d0b1",
+       "model_id": "e772c96f4cb84a83a1bd13fde8c6cd73",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1104,7 +1115,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "003c72487617416bb8404182b762362d",
+       "model_id": "53a48baa204a47cba852bce7bb92ef13",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1120,15 +1131,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 64.4531\n",
-      "Eval loss: 69.3875\n",
+      "Train loss: 44.2301\n",
+      "Eval loss: 37.0219\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "ae5a2f203b7a4c0a9e83a83a37682702",
+       "model_id": "2c24edf4c2134a578851be03cfb2909f",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1142,7 +1153,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "d25e999f9e1f4f0fb96f28220c14195b",
+       "model_id": "a679f7c74852413893974a907c77a219",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1158,15 +1169,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 64.0672\n",
-      "Eval loss: 70.9859\n",
+      "Train loss: 43.2677\n",
+      "Eval loss: 42.9303\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "4a53ac86969141d7baa266180a3c73d6",
+       "model_id": "1f4af8d4ce8e4ec597117e3e60162313",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1180,7 +1191,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "7f7d910e3bdc4dae9a0110a721046bc3",
+       "model_id": "2e2ea9b74ba04ca3a03552092cca848e",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1196,15 +1207,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 62.9348\n",
-      "Eval loss: 63.0601\n",
+      "Train loss: 42.2071\n",
+      "Eval loss: 40.9839\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "b4be7dfbac6c48579a23372061faa324",
+       "model_id": "96af73fec53a43929e71392cce9525ac",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1218,7 +1229,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "78bb9d67acfe4a70ac21bc7e615e788b",
+       "model_id": "1485cb2105d740f385e98ea2f82e6045",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1234,15 +1245,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 63.0094\n",
-      "Eval loss: 63.3553\n",
+      "Train loss: 42.8744\n",
+      "Eval loss: 43.2838\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "86a843d3ca1d404fb3f9c24ca96601f1",
+       "model_id": "fef22c6e5b464b0b97f615e375a0c7e8",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1256,7 +1267,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "075907fe16c14b3cbe87624de4c12feb",
+       "model_id": "56c12153fbed42e3b6a4b120e9319a97",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1272,15 +1283,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 63.8406\n",
-      "Eval loss: 65.506\n",
+      "Train loss: 42.7862\n",
+      "Eval loss: 37.937\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "ea9f829c08f64155a8ea050c83ce0d0f",
+       "model_id": "7c089546df00478693ebe5bb9431e33c",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1294,7 +1305,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "34c687ee18824dc987fdbb52ca032200",
+       "model_id": "f7de402d89b74086a8d74a402a1cf291",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1310,15 +1321,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 63.0173\n",
-      "Eval loss: 60.3433\n",
+      "Train loss: 43.1582\n",
+      "Eval loss: 40.082\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "9a60c614b5084c13b11fc50ad4e89f9c",
+       "model_id": "66f0cc51af2a4a34aec2af0ecd95319b",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1332,7 +1343,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "e1a4e09db5584286994e7f7dace14860",
+       "model_id": "27ad054517f94b4fb94d77bdbed25d7f",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1348,15 +1359,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 61.2818\n",
-      "Eval loss: 60.9274\n",
+      "Train loss: 42.2759\n",
+      "Eval loss: 42.197\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "02e4f336ae7244aca0618f3e16b4f4e6",
+       "model_id": "0b14c53161f24c76a366939f939c199d",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1370,7 +1381,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "a06e8ea8db1e48daabc021d435793101",
+       "model_id": "b8071d2b324541e588282122a392ce08",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1386,15 +1397,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 61.5882\n",
-      "Eval loss: 63.5523\n",
+      "Train loss: 43.974\n",
+      "Eval loss: 36.066\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "4154c03809d442d4895669d36b459d7d",
+       "model_id": "5f726ab20fa14c80a95691834d0169ee",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1408,7 +1419,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "d66aa3b03e2a430ca21176cb34875d83",
+       "model_id": "a02c754ce4a64fdeb1381917209947a4",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1424,15 +1435,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 61.0341\n",
-      "Eval loss: 65.3404\n",
+      "Train loss: 40.9478\n",
+      "Eval loss: 41.9381\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "2c0a2df80bab479aba69a4616df7157f",
+       "model_id": "a1c629b4497f41f68cd8f76f0fdb1bfe",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1446,7 +1457,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "d0d6ed393d1b4552938e7826414a6f45",
+       "model_id": "382bded151e44bd1b0707ae143500911",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1462,15 +1473,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 60.7392\n",
-      "Eval loss: 61.1621\n",
+      "Train loss: 43.7921\n",
+      "Eval loss: 39.4629\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "33fe2cec712a4f1f8d25b1468e64f5a6",
+       "model_id": "fbf08b7717384f30bc9d86320ad798d1",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1484,7 +1495,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "6cfed3b1989740129c04ec7ab756891c",
+       "model_id": "ee30190c2b624f6a9b64fa857bc4107f",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1500,15 +1511,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 61.3899\n",
-      "Eval loss: 64.2951\n",
+      "Train loss: 40.0904\n",
+      "Eval loss: 38.101\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "612c0e22d0ac4a4da4014cfe4670ba52",
+       "model_id": "de97038172f643a19995c3834d5834dc",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1522,7 +1533,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "0d0f032802fd43a7bb8eb73ade26ed90",
+       "model_id": "6b18ab89b54d41acb490a5dfff50640d",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1538,15 +1549,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 61.0669\n",
-      "Eval loss: 62.3087\n",
+      "Train loss: 42.0358\n",
+      "Eval loss: 34.0293\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "ece6aa3fee674cb696540cfd5cbb4a87",
+       "model_id": "b0c31968d693473aa0f650427e20b77e",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1560,7 +1571,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "9b34a64d5d2246debc2d742a2ecf757d",
+       "model_id": "be3d1cbac09c484f9b061557c6a67ba5",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1576,15 +1587,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 60.5069\n",
-      "Eval loss: 62.6113\n",
+      "Train loss: 39.7718\n",
+      "Eval loss: 36.4644\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "7d3e2d4697d5489d9172914edc348fe3",
+       "model_id": "22bed6bf5f92482abf9fabc6738e78fa",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1598,7 +1609,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "ebadc53006cf4e5f90a716a2273474bf",
+       "model_id": "ba122aa1972545c3aecf867dfc5fc96e",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1614,15 +1625,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 60.4862\n",
-      "Eval loss: 63.8374\n",
+      "Train loss: 40.3231\n",
+      "Eval loss: 36.3404\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "ef55830298ca41e1942c44368ee25f4e",
+       "model_id": "a96e8b4090804bc2aacd6f617e1dc5e6",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1636,7 +1647,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "e32c41a1d1d449d19c27a53d5223ce9e",
+       "model_id": "843a483505bd46a695fe1c9194eb193a",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1652,15 +1663,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 61.2231\n",
-      "Eval loss: 61.2632\n",
+      "Train loss: 45.2427\n",
+      "Eval loss: 49.6391\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "429b0713f14d4f3db0891aa60c1f6e36",
+       "model_id": "4d2a40a7cdb94e11975bb91fcc1d10e8",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1674,7 +1685,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "1bfb612b8e1d4fe29ea3a0684fa603bd",
+       "model_id": "195602853d174573bee0f22c050d4ae4",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1690,15 +1701,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 60.7346\n",
-      "Eval loss: 62.7917\n",
+      "Train loss: 42.101\n",
+      "Eval loss: 41.5577\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "3aca37c6da2a430fbffb654b5aea2d0d",
+       "model_id": "72bff0fbd73c445a9699414540e73886",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1712,7 +1723,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "f969328ea9ef4b7bb238d28b9ab007c9",
+       "model_id": "8d1e69edda584c2ca9c17f1444ef8b16",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1728,22 +1739,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 59.5126\n",
-      "Eval loss: 60.9537\n",
+      "Train loss: 40.5898\n",
+      "Eval loss: 41.6189\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Epoch    43: reducing learning rate of group 0 to 5.0000e-04.\n"
-     ]
-    },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "de7bb71b5e964b74b73b501ccb11aeae",
+       "model_id": "0eafafa127fb430c925b406956149b49",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1757,7 +1761,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "bf9d34cf69174afaa6579f2bedfd5b7d",
+       "model_id": "88cbeda02ce845bcb513a415f3a15a03",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1773,15 +1777,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 58.7464\n",
-      "Eval loss: 58.6463\n",
+      "Train loss: 39.3039\n",
+      "Eval loss: 42.3499\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "f89e1baadba64c5a8745673a53e72707",
+       "model_id": "5fa1f611253d4f348bd15b67e655fef7",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1795,7 +1799,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "bcb60e650a474f458d70c3dbcdc7e898",
+       "model_id": "a69635b1e47d4148963e0bbe9b11689e",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1811,15 +1815,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 57.969\n",
-      "Eval loss: 58.2375\n",
+      "Train loss: 40.2525\n",
+      "Eval loss: 40.2899\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "15160c531ed044568d8e5ed1cf54b386",
+       "model_id": "9a659a91a7b640aeb2ee9d82e13f2cbb",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1833,7 +1837,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "557b803034534e43adb13fdbf7f1d126",
+       "model_id": "43054d890dd54d698991c7ffb21969db",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1849,15 +1853,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 57.8539\n",
-      "Eval loss: 58.1819\n",
+      "Train loss: 38.8709\n",
+      "Eval loss: 34.4457\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "4f726916c58249d08fb1d117f84be2eb",
+       "model_id": "36f6db455988459c94c066e896b85143",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1871,7 +1875,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "3b6ee7735727416bb57ec7592d183ff8",
+       "model_id": "85e6e48f19cd4ec39e534bd61b77fdd7",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1887,15 +1891,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 58.3385\n",
-      "Eval loss: 59.312\n",
+      "Train loss: 42.3591\n",
+      "Eval loss: 36.3393\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "c6eda59fe1664e6eaac9475b6c0ed434",
+       "model_id": "235673171e644eee8d489d74d760fc88",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1909,7 +1913,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "175761b2eb2b4e4eb620798e0772d71a",
+       "model_id": "56664177932f4e6f9beb5c2dfe25970c",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1925,15 +1929,15 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 57.5298\n",
-      "Eval loss: 58.8087\n",
+      "Train loss: 39.2903\n",
+      "Eval loss: 38.7344\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "76d1200fe09f403c9a4579ce45460dba",
+       "model_id": "4fa3657ff6de4cefb3a958b528e3635c",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1947,7 +1951,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "005abfe2d46549cf8d31f32cbc20d39b",
+       "model_id": "cfe6e521b7cf4ce99ff48f8e379cab6c",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1963,15 +1967,22 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 57.6616\n",
-      "Eval loss: 57.7834\n",
+      "Train loss: 41.2091\n",
+      "Eval loss: 38.0018\n",
       "--------------------------------------------------------------------------\n"
      ]
     },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 00049: reducing learning rate of group 0 to 5.0000e-04.\n"
+     ]
+    },
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "24e3862b5f6442c8a9d0dc3db02ea5fe",
+       "model_id": "5303558161764293b03d6677a2003c7e",
        "version_major": 2,
        "version_minor": 0
       },
@@ -1985,7 +1996,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "6a42a37facf44abfa4fda8a64e2c2144",
+       "model_id": "b7e410c296c24eb3becb13635d258e2f",
        "version_major": 2,
        "version_minor": 0
       },
@@ -2001,11 +2012,11 @@
      "output_type": "stream",
      "text": [
       "--------------------------------------------------------------------------\n",
-      "Train loss: 58.3789\n",
-      "Eval loss: 58.8588\n",
+      "Train loss: 37.3718\n",
+      "Eval loss: 33.6677\n",
       "--------------------------------------------------------------------------\n",
       "Training ended!\n",
-      "Saved final model in dummy_output_dir/IAF_training_2022-06-13_20-17-16/final_model\n"
+      "Saved final model in dummy_output_dir/MAF_training_2022-10-11_17-30-56/final_model\n"
      ]
     }
    ],
@@ -2018,7 +2029,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -2028,22 +2039,22 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "<matplotlib.legend.Legend at 0x7fc29e0157f0>"
+       "<matplotlib.legend.Legend at 0x7f4676a4baf0>"
       ]
      },
-     "execution_count": 21,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     },
     {
      "data": {
-      "image/png": "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",
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYIAAAD4CAYAAADhNOGaAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/MnkTPAAAACXBIWXMAAAsTAAALEwEAmpwYAADXZklEQVR4nOydd3wb9f3/nyfptE62ZTsecZzl7OEMyCSMBJpAWS10UOgA0pYCZgQCdCZAGE2BfJsATimU8YUC/f5KS0sLLTMBMsiCxIlxppN4xlu2dVon3f3++JzkEScEcCZ6PR562DqdTjff+/16S4ZhkEQSSSSRxFcXluO9A0kkkUQSSRxfJBVBEkkkkcRXHElFkEQSSSTxFUdSESSRRBJJfMWRVARJJJFEEl9x2I73DnwR9OnTxxg0aNDx3o0kkkgiiZMKmzZtajQMI6v78pNSEQwaNIiNGzce791IIokkkjipIEnS/p6WJ0NDSSSRRBJfcSQVQRJJJJHEVxxJRZBEEkkk8RXHSZkjSCKJUxmaplFVVUUoFDreu5LESQqn00l+fj6yLB/R+klFkEQSJxiqqqpISUlh0KBBSJJ0vHcniZMMhmHQ1NREVVUVgwcPPqLvJENDSRx3qCpUV4u/SUAoFCIzMzOpBJL4QpAkiczMzM/lUSY9giSOK0pKYPlyCATAMOCmm2Dq1OO9V8cfSSWQxJfB571/kh5BEscEPVn9qiqUQDAIn34KmzfDtdfC+vXHbTeTSOIriaQiSOKQ6K2QTUkJzJ8PCxeKv1u3iuU+n/AESkvBbofMTLBY4LHHxG8mQ0bHBz6fj+XLlx+z3xs0aBCNjY0AnHHGGYdd98EHHzzs5xdeeCE+n499+/YxduzYz7UfK1euZM2aNYn3TzzxBM8///zn2sbJimRoKIkeEQ/ZaBrIMhQVQWFh13VUVQhzrxcUpeftxK1+j0e8/H4oLoZFi4QS0DSxjmFAJAJOJ8Ri8Npr8M47Yhvdf7/z78Lh9+FI9jGJrogrghtvvPGgz6LRKDbb0RMbnQVxT3jwwQf51a9+ddBywzAwDIM33ngDEMfwebFy5Uo8Hk9CGV1//fWfexsnK5KKIImDcCjhvWRJhzA9EkUBQghrmthOJAK6Lqz8W28Fa0il7lMfVbu8hKwKFgsMGyZCQx99JH7rzDPF3/jv79nTEU5qahKeRHp6132IC//KSnjuua9G/qE3Fd4vfvEL9uzZw4QJE5g9ezYXXXQRCxYsID09ne3bt/PWW29x8cUXs23bNgAeeeQR/H4/99xzD3v27KGoqIiGhgbcbjdPPfUUI0eO7LL9pqYmrrzySqqrq5k+fTqdpyR6PB78fj+1tbVcccUVtLW1EY1G+cMf/sDrr79OMBhkwoQJjBkzhgceeIDzzz+fqVOnsmnTJt544w3OOeecBP1MNBrl+9//Ph9//DFjxozh+eefx+12Jyhq+vTpw8aNG7njjjt47rnneOKJJ7Barfz5z3/mscce491338Xj8XDHHXewefNmrr/+egKBAEOGDOGZZ54hPT2dmTNnMnXqVFasWIHP5+Ppp5/mrLPO+nIX4DggGRpK4iB0Ft4g/mqaWA5dFUX//uBwwEMPQX19xzbiYR1ZFq+9e+Gtt+DNN+H996HhvRJm/Xs+V+1cyEPGfEZGt6JpIkxUVSWEfH09fPCBEPaaBjU1HUqgpARWr4YVK4QH4fHA0qXCk7jlFrjzTvj+92HnTti27dTOPxwq9PZFsXjxYoYMGcLmzZt5+OGHAfj4449ZtmwZO3fuPOx3r7vuOh577DE2bdrEI4880qNXce+993LmmWdSWlrKZZddRkVFxUHrvPTSS5x//vls3ryZLVu2MGHCBBYvXozL5WLz5s28+OKLAOzatYsbb7yR0tJSBg4c2GUbO3bs4MYbb6SsrIzU1NTDhrsGDRrE9ddfz2233cbmzZsPEuY/+tGP+N3vfkdJSQmFhYXce++9ic+i0Sjr169n6dKlXZafTEh6BEkAXS3KeMilthZSUqC9XbyXZdi1Cw4cEMI4Nxfq6mDDBmhrE0LorruE9d3ZWzjrLHjgARH/NwywaypX+ZcRNWw0kIOCyp08xJ3GEurJxjAgHBZhoro68ZJlYdk3NcHu3eLzcFh4GK++ClOmCGWzYoVYFg5DY6NYlpICcRnx2GPwxBOnTpjoSLy33sCUKVM+sybd7/ezZs0avvOd7ySWhcPhg9b74IMP+Pvf/w7ARRddRHp6+kHrTJ48mblz56JpGt/85jeZMGFCj785cOBApk2b1uNn/fv3Z8aMGQD84Ac/4NFHH+WOO+447DH0hNbWVnw+H+eccw4AV199dZdjvPzyywE4/fTT2bdv3+fe/omApCJI4qAwz+zZQrBv3AgtLUIxDBsGP/gBVFQIQRuNitenn3ZY5BkZwioHEa6JC6b//hcmTBBKYNUqmBBaw3RWE8SFHSEoZKI8zHwe4i5KI4VYLNDaClarUADf/jY8+ih88olQBlar2A9NEyGnd94Bl0v8digkfiuOtjaxnykpQjnU1IDbfWrkDXry3lpaxPLePDal08ZsNhu6rifex+vVdV3H6/WyefPmL/17Z599Nh988AGvv/4611xzDbfffjs/+tGPDrtf3dG9hDL+vvP+90b3tsPhAMBqtRKNRr/09o4HkqGhrzBUVVj4y5Z1DfMsWABZWUJQDhgAaWlCeG7aJP7v00dY9ytWCOu8qkoI60hEbLO1VQjpSERsV5KguRn+/W/wVatcwV8I4SCMnUyayKIBPx6ayaCIYtyoXb7/m9/AP/8prPwpU4SQb20Visipq/Q1qulDPenBaqSg2kUJxBGLifU//BDmzhWho/nzRajoZK5M8nqF8vb7xXu/X7yPe3VfBCkpKbTH3cAekJOTQ319PU1NTYTDYf79738DkJqayuDBg/nrX/8KiATuli1bDvr+2WefzUsvvQTAf/7zH1paWg5aZ//+/eTk5PDTn/6Un/zkJ3z88ccAyLKMpmlHdBwVFRWsXbsWEKGmM888ExBhoE2bNgHwt7/97TOPOy0tjfT0dD788EMAXnjhhYR3cKog6RF8BdBTIjHuBfh8In4+a5YQulZrh7UPwspvaOh4b7EIi7upSYSHYjGxrKUF3n4bBg0SXkNZmdjWqFHi86oqIaSGUIMHlQ1MZgrrkYliILGVMfhIJ59KvPgIoGAYwpp/8NcqG9/xEbB7adcV3G4Rrhqtl3Ajy8mhjhHsYDsjqCeHYoooRWSu3ah48eHDSzCooOuwbp3YvzFj4JprYPx4sNngqquEAhwwALKzj+kl+sJQFJEkLy4W1yCeNP8y3kBmZiYzZsxg7NixfP3rX+eiiy7q8rksyyxcuJApU6bQr1+/LsngF198kRtuuIH7778fTdP43ve+x/jx47t8/+677+bKK69kzJgxnHHGGQwYMOCgfVi5ciUPP/wwsizj8XgSZZzXXXcd48aN47TTTuOBBx447HGMGDGC4uJi5s6dy+jRo7nhhhsSv//jH/+YBQsWMHPmzMT6l1xyCd/+9rf55z//yWOPPdZlW//7v/+bSBYXFBTw7LPPfvaJPIkgGT2ZTyc4Jk2aZCQH0xwZuod95s4VYZvFi8Vfux1ef12sO2eOsNxXr4Zzz4W1a4WgB/G3rValIMPH1kovbTGFWEwIe8MQYZlwWCgOBRV7QAjfppCC1ytCMmMp4RaWMYPVhHHwCROYwgZiWPk3l2Anggc/d7CEAEKSjUUIewca2GX+IBVRYhSSalVZFJxPGAczWI0BSMBqZuAgzB0soYA93MoyFFRUFJYyj1IKcbtFaMjvF3mOlBSh2BoaICdHCNHbbxfJ5uMROiorK2PUqFGf6zvJMtkkuqOn+0iSpE2GYUzqvm7SIziF0T2RuHevsIBHjxYKYupUEQ464wwRx3/1VWEZ9+8vQkY+n1AMqakwJ7eEC23LaSvXCBlywuqOK4pgUISDcupLuIHl2NGISjKPGUWUNhbiRuVGluMjnZXMYjprmM46PmU0UazkUIeG2G5cCcS/48dDm8VOWqSJm3mYRSzAbgM7GgHcWInRRhqptBLDioxGX2r4DfcxnJ1IGNiIcg/NXM2fcUShHz7KI14aGkTZal2dUHZ1dUKp3Xkn/Oc/8OMfC2/pRBeuinLi72MSJy6SiuAURvca/tJSYcHLsrDQ//UvEQYZO1bkBmbMEBaxqgohOGKECPNYgipzdizD5rHhc+QQDUUooriL5a7rQnDfYApuFQ+K4aeIYhayiOHsIJNGmskggp21TCefSu7hbsoZmgjfxLcH4MWHjIaCymR9JQp+cjlAJvXURPvhoY12PMSw4sZPDCtWYmjIuAgwjq2EcJBFIzai5FHD1TxDYaQUuVETikctorS8owFC00QYTJJEAnrFCqEIFi3quaEtKXyTOBWQVASnMDonEnVdxPbtdlF5I0nifUWFUAqDB4uE7+7dQhgeOCDKRzUN5khrGB9aTbjdzkBgPVOwYCRi+XH0pQYvPprJAEDFQwF7eJq5jGAn2dQziQ3oQAatSBjcw73czb2JmH5n+PBiANNZQwgn6bSgIdOfalrx4sJPHtU04WUAVZQxCgdhXuJKCtiDTIhMmghjJ4wDGxq3sYzXuYg6clHwH6TQQIS6DEOcH0UR+YTlD6vcN9/H+p1eXvi7gt0uPIdDNdIlkcTJhKQiOAXR2WKNJxLjoZsBA0QJp8MhlILDIapmamsh3t0vSSLBG4sJK/8S/oKBTjZ1SBhczt9ZxxQidAy9GEsJt/MIp7OB0ZSymjOJYGc0pRhYaCadEA5GsB0bOmFkgiiMZhvzWMqtPEoApUtyN4DCy1zJmazGRgwbMdpIYTg7GcBeXIRpJgM/KZQyimKKyOEAT3ADCn76UoOEgYaDIC4aycKCjgWdFNoI4URGO0ihxRGNimT1mFgJc95czsZ3NQ40yFQ4i2jsW8i4caJc9tFHhcJIegpJnKzoFUUgSdIzwMVAvWEYBzE9SaKAdxlwIRAArjEM42Pzs6uB35ir3m8Yxv/2xj59VdE5OQxw5ZUirNHaCtu3w/PPi88sFpHY3bOnoyIoDsMAR0wIZBcBZDRiyEgYyERR8DOeEh7mDh7hTvZSkIjHR5HJo4YL+A9ljMRFkFTayaaORvogAVGs+MgghpU+NJNBEyMpw0qMa3kWN0EkdJ7iJ1QwkHVMRcPG2bxPAeWABTdRJHS8tFJNPwZSwVye5jQ+IYgbLz7aSMVLK2FkJHS2UMhpfMI5rCSGDQmdnQzHh/eQ59NlqPzQv5yKkAdD8WCz+vmpVsz8/Ut4t0GhTx+RVM/OPjLKjSSSOBHRWx7Bc8DjwKGo+r4ODDNfU4E/AFMlScoA7gYmAQawSZKk1wzDOLiwOInPROfksKoKC3/1alHCabOJpK/LBUOHimTwzp30WHMfr9SREdokg2YchLCgo9COFR0PfqazmsXUs4h7GM8W2kkhgEIQF15aCOLCRoQ02pAwyMAHiAudQSNtpGEjwli2cRtLmMgWdjKUfGpIpYWL+TcfciYhnKQQQyGABESwYkdDQkImwgAqaKQPfWjETgQf6VjQUUnFQRALMSR0JrKFA2STgopMBP0I2mi8+LCjURf1YA9CLObBHWvBLfmoM0tZn35aVCF1bqI7Gt29SSRxtNArDWWGYXwANB9mlW8AzxsCHwFeSZL6AucDbxuG0WwK/7eBC3pjn76KiCeH7XZB++B0Csu/tBR2b1HJilSTYlE5cECEfborATcqQ9jFLSzDj4cq+tNCOgp++lNJKm3YiRJFQsHPAKr4Gu9RTBF9qaGAvUzgEwazl0wa6UcVfWgh3oMqdfrrQCOLRuxorGMqdfTFQGIGazEAD0FiWBnEfmrJM8tNx9NGKgEUU4gbGEjoWMiigRbSiWIjhVYs6Hjw4TYFfgwLZQyjLweQEJ3MOhZsRPGaCqrHc4qXMDIKfiQtQlasFh1oNrxomuBDev99KC8X5x0O5mY62XAsaaivvPJKxo0bx+9///tj8nvd8dxzz3HTTTcdl9/uCZ9Fw320cKxyBP2Ayk7vq8xlh1p+ECRJug64DuixAeWris5xaVkW1UF1daLhKs73PzRQwvXGcpzlGhFD5gO9iJpuydm4F+DFx3g2s5JZqHiIYGcAVdSSRSoBrPiwI2pGrUSRgBFsx8CCmzZsGNgJoWNlAluwoxHDgoHQOhIkFEMMK1Gglr7mZzo2NOxEcBBCQ8ZAIoYVBT+FbMNOBCchJHN7BhJptNKClw85i4Hs43Q+QULHio4OpKISxcrZrMJGlCDtRJFJp5kU2hO5ju75CYAACsUUsZBFjDO2ogNbKWQw5ex2FKLrov/A7xd5lrPOEt3XX7a793jiWNFQHzhwgA0bNrB79+4j/s7RpsE+3vgsGu6jhZOGYsIwjCcNw5hkGMakrKys4707JwQ6s05ecw387GdCGL37rkgAB4OC6vk6fTlthoe9sf74dA83mjQOcXSu1y+ngDAOprMGmQgZNGEjgocwEjoSEhKYLwkNGQcaEjoyMTMZK4R9PLRkTYh+ERaKYiWKBQ0bBjbGsI05vIWDIB78jORTvLTipQUP7TgIMZZtpNKKBYMoNgwkWvGwk2H4ceMiyJ08xCh20EoaAZzmb4vfd6CRgh8XISzEsJr7akUnjVbGUsIjzOdeFvII85nEevKoxo3KXgpoI5WVnMOrXE4lA7mJYqxhFU0TnlU0Kiqt/vpX4R0UFYnj7UxfUV8v+Js6s7T2Gnpxik9nGuo777yTlStXctZZZ3HppZcyevRoAL75zW9y+umnM2bMGJ588snEdz0eD7/+9a8ZP34806ZNo66uDoC//vWvjB07lvHjx3P22WcDMGfOHKqrq5kwYQIffvghmzdvZtq0aYwbN47LLrssQT0xc+ZM5s2bx6RJk1i2bBkzZ87ktttuY9KkSYwaNYoNGzZw+eWXM2zYMH7zm98k9uXPf/4zU6ZMYcKECfzsZz8jZja9PPvsswwfPpwpU6awevXqHs9BQ0MDs2fPZsyYMfzkJz9h4MCBieE5hzv2OF555RWuueaaQx57aWlpYt/GjRvHrl27umzD7/dz3nnncdppp1FYWMg///lPAPbt28eoUaP46U9/ypgxY5gzZw7BYPBzX+PuOFaqtRro3+l9vrmsGpjZbfnKY7RPJzXi+QCHQ1if778vLFObTZQ9hkKi+ic3JmrxVcQNpuIhnZYulTLxev34Oms5g1msYDDlRLATw0YrKQykEkxLXDf/U1FIpxmwY2BBRwheKwYS4MdhKhEBA7BgEMZJBBth7MxgjVnLYyWCDSvgw4WbEFk00JdabGjoWIkRRaghAyvQlwNEsNOKYuYINNpJwY0/8ZtxSEAMi6kELRiAkxCT+IhzWJ3ofxjIXp7jGjYwiSBu/sq3kYkSwE0K7YRxkoaPvtRQLg0jFhOhtv79hRem68ITmz+/I3k8bJjIJUSj4hrddx9861u9dDMc6XCII8TixYvZtm1bgjxu5cqVfPzxx2zbti3BQPrMM8+QkZFBMBhk8uTJfOtb3yIzMxNVVZk2bRoPPPAAd911F0899RS/+c1vWLRoEW+++Sb9+vVLDI157bXXuPjiixO/M27cOB577DHOOeccFi5cyL333stSk8UwEokk5gz861//wm63s3HjRpYtW8Y3vvENNm3aREZGBkOGDOG2226jvr6e//u//2P16tXIssyNN97Iiy++yOzZs7n77rvZtGkTaWlpzJo1i4kTJx50Du69917OPfdcfvnLX/Lf//6Xp59+OvHZoY79UOjp2J944gluvfVWvv/97xOJRBJKKg6n08mrr75KamoqjY2NTJs2jUsvvRQQ1Nsvv/wyTz31FN/97nf529/+xg9+8IPPdY2741gpgteAmyRJ+gsiWdxqGEatJElvAg9KkhTnoZ0D/PIY7dNJDZ9PhIAqK4XQqTQDbB5PBxmbFx9hZDQzxq3iQUGwk7kI4EYlgIIPb2KdCHYkdNYxlfvNYq4l3M4M1hDFio6MjWiC0kEkgiXshJDQAQkDCcmM31uRCOJCNxO7UWxYiRHDgpUYcadUw04rKfTHTytpVJNnVhU18X98h9PZSBrtGGZQKP6qI4d2PKTSTtTsKpaJmGJeIP5f3C+xm/xGEgYxotzH3XzKWLYxlgyaGE8JMaw00QcdCzdSzEQ2k0ar6d0YNJPBz1nMo8Y8tlGYaNiTJEFXUVsL06YJCov6erj/ftGrkZoqwkgLFogw0pfmNDpGPNTdaagfffRRXn31VQAqKyvZtWsXmZmZ2O12Lr74YkDQMr/99tsAzJgxg2uuuYbvfve7Cdrmzvgsqucrrriiy/pxoVhYWMiYMWPo21eEFwsKCqisrGTVqlVs2rSJyZMnAxAMBsnOzmbdunXMnDmTeFThiiuu6HHGwqpVqxLHd8EFF3Shyj7UsR8KPR379OnTeeCBB6iqqkp4M51hGAa/+tWv+OCDD7BYLFRXVye8q8GDBydouXuL+rq3ykdfRlj2fSRJqkJUAskAhmE8AbyBKB3djSgfvdb8rFmSpPuADeamFhmGcbikcxImIhFhCLpc4qXrYI+quJp9DKGSa3kOGdE9+yazOZ+3SaeFFNqwEmURC1BRWGby7xRTxAIWMY6tGIg4uJMQeymgFS+tpOImAEAMGxpWU5BaiWIjiowXHwa6GS6KomFFRieACxchqsknlTaa8GInygGyGcluZKLY8GMxcw8OwvTlADJRrMQI4sLAQhQLVtPvMLDRhgcPKlk00EQGFnRiWHEQwk7koHMW9zichBNJ5hg2dAxOZyPD2U4MG7kc4AB9E30GE9iChKixdRHAQCKCjIoIs8Ub0gyjg5Tv44+Fgp46tYOcz2QrxuMR/QkVFb2gCI4RD3VnuueVK1fyzjvvsHbtWtxuNzNnzkzQOcuynKB77kzL/MQTT7Bu3Tpef/11Tj/99AT75xf5feigfrZYLIn/4++j0SiGYXD11Vfz29/+tsv3/vGPf3yu3+2Owx17Z9rrzvTWPR37VVddxdSpU3n99de58MIL+eMf/8i5556b+M6LL75IQ0MDmzZtQpZlBg0alNhm5+O1Wq0nTmjIMIwrP+NzAyg6xGfPAM/0xn58VVBSIgbA1NaSIH4bGRXJXjdBJrGB9UxmP4NR8HM+b7OYn5NPFXfyEAOpMCtnNDJo5kf8mb0UEMTFBiZxgFwkSHTdvsBVXMJrhLBjJ0oYGxYMtlBIKn40s3dAKIAwLaTRhoEVAzdBbGho2PDgByQ2MQUXQcZRYnb92vHgx0M7PtJxo+IgTAwb73MW3+HvlDIGDyo2NByE0ZAJ46KWvqTRRgwbdUg4CGFgxYeXLBpxEsaCThQrraSQht/0SoTCshAjhwbcBMmikQAus18iTDb1nMFqcqjDQdjMKwgPox/VpNOMgcQEPqaOXGrJIxATAisWg337BOtqZqZQDs3N0LevMNptNrG8uvpLNqB1bh+PewRfMlP9WTTUra2tpKen43a72b59Ox999NFnbnPPnj1MnTqVqVOn8p///IfKykq8nfaxM9XzWWed9aWpns877zy+8Y1vcNttt5GdnU1zczPt7e1MnTqVW2+9laamJlJTU/nrX/96EDsqCCv+//2//8fPf/5z3nrrrUS+4nDHnpOTQ1lZGSNGjODVV18lJSXlkMfe2tpKQUEBt9xyCxUVFZSUlHRRBK2trWRnZyPLMitWrGD//v1f+FwcCU7d9PspClUV/PyrVplTvHSVvtRwC8vwkU4ANzEsjKWUGvphAMPZzkPcBRiczYfUkUMq7djQmEUN5/AeYZxMZT1BXIxiOxuYjIzGNNbyQ16ilVQ8qFSTRRA3teQSwoWXViIoVJPHUFRqGMiHnMM01mJFZzVncC4rcRMggJsq8hjNp+xkGDFsHCCXbBoI4MZBmN+wiFm8j4rHTPoqDKKcZjJ5m/OYwzuo2DCwsIXxjKaMf3MxVnRCOBnGTuxoVDCAs/kADRuptLGG6ZzFKsI4yaYJKzouQuhAFJkoMu0opKASxk429czhTdpIJYoVxfRW4mEmFyHOYBUWYDofEcPCVgq5j4WUUohhCK8tGBTJ5LQ0QfoXCAi205/8BH73u46O75tvFrMWPjeOAg/1Z9FQX3DBBTzxxBOMGjWKESNGHHJCWGfceeed7Nq1C8MwOO+88xg/fvxBwq03qZ5Hjx7N/fffz5w5c9B1HVmWKS4uZtq0adxzzz1Mnz4dr9d7yMlncarsF154genTp5Obm0tKSsphj33x4sVcfPHFZGVlMWnSJPzmkIiejv13v/sdL7zwArIsk5uby69+9asuv//973+fSy65hMLCQiZNmnTQ3OfeRpKG+iSCqoqqlJtvFv+PMQ4u+Wwh3azACbOXgcxgDR78+PGwlqnM4CMchGghA91MnL7Huai4OY1PiGAnig0nIbYwnigyfjzMYDUWdOxE2M1gRrCLnQxjLKUJdk8vLVSTjxWdLOrRsVJHNhYzxBPCTRQZJ0Hu4GGu5vku7KDbGcEN/JFFLOwgrsOPBz/PMJebeYzprEXFzXqm0EA2l/N3VnIOdfRFwY+XFjNJ7UnQU9uIUcYIpiAGFudRgwUDGxEwq6A0bNjQ0bCh4qGFNKwY/Jc5XMo/yTP7DyBe+WQhjIt6sqkjFxDVV1sYz/0sEN6BmYy324WxHouJHO4TT8D//I/o9t61q0MZPP00nHPOF6OhTvJb9C7C4TBWqxWbzcbatWu54YYbemXy2rFEkob6FERJiZgk9t57IszgMjpKPpvJYCRlTGcNb3AR2xnOGaxhJu+jIdNOKmHsTGUDzaTTjypkNHQkDpg1/NnUY0VnEMJKa8PDG1zIHN7GRzobmMzZvE8+VfSnggPkUmO+689+dCwMYR8qbgrYi4MQ7aQSxEkB+6imL//lAlJox0aU9zmXCgZxK0sT8wKWMY9GsimmiCKKEyRzccrr+SxhKbcQwE0D2diJUEIhNqLkU4mGzDLmASKsVUF/xrMFCYMzWEsGjYni13ZSMIA0k/wOwEIMJzHCOFjFWUznI9wEcBJBR8KCQQwLEgYB3PhMniMN0UnmoJkZrE7kX17mStYxnVBUIRAQ8rm6WpT3rlghksqdJyX+8IdC0aemfoEbJMlD3auoqKjgu9/9LrquY7fbeeqpp473Lh1VJBXBSYD6enj4YeH1y7KwHg9V8jmBjxnBTpyEcBEiYjZl6VixYLCd4WTQTAteVDyUUIiEwVi24cdDGaNIoRUHEdYxlVkI+ucWRNVEE5kEcNGGNxF68dJCDBsbmcRItmMlRhgnARwMpAKZMKm0MYQ91JPDMuYRQKGUQubx6EFNXFVphfy8fQlpho9mo2N5LgewEeNM1iQS2vexkL0UHLSNO1hCX2r4NfcRReY0PkbFxRD2YWCg4Gc/A3EQwkkg8SAYQCuptJHGDoaTywE0bMSwIhHFZuYbShhHIzkUsAcnQWQiZFNPNf3w42EyGziT1axmBkv1eZSGCtE0EcL/9a872GBBJJjtdpFAfuABePDBY3VnJXEoDBs2jE8++eR478YxQ1IRnOBYtw4eekiMk3Q4OobHdy75VPGgorDOTMKquGkmAy+tuAmiouAyOXcayeYGirmI/6IjEcLFX/k2KbQziH2k00IEmTJGEcWesM4Hso88aqgnmxwa0LGSRw2xRGuZwXg281++zmzexjDLRSUChHHhJw07GgtZRCMdpTJBSSFgKEgS2GXB2ZOTAz//vcLddyt4whBs6PCAaiwD2a0PI4MmZKLspYAAykHsoYLzyE0MmTbSkIBGcrGhIxMlk0YcRPCRiheJAG5saCgE8NLKaWwkj1qTI6mZA2TTRDZu/NiI8iP+TAp+HmE+U1lvdlDo7GQYE9ksqojMprkE1bU51S0+3jM+/12SRPI4GBTVRs3NoKoGitK9EyKJJI4Mnzfkn1QEJxC6h3lXrIDrrhMCor5eVAeFw2LdOPVBPIRiQ2Mt0zift4ghE8DDXgYzhHKchGikDw8xnxeYSwCFf/PNhBUN8DP+mOgEltGIYsOHlxr6sZBFLOUWKumPnxSCuBjIfhRUWkinkgHIaAxkP/nUUCaNQTHamc5aIjhpdvcnFLUzLLKbfu5WWsLZCZ6jtLSOOQlWq1ACI0aIWPrMmUIxvPwypAd8OKIaDYYHA2iR+5IbrSRT8hHQDw6JOBzgC3uRbDJuSww9IobXtJPKOqaQQTO/5ZcMZSfP8FOzisjBbvJIoZ2+1NBMJnYiGEjkcwCFIHXk8iljiWJnLwVU0p9K+qMhM4NVjGY7GjaiWLEQo50UMro18Om6EPyy3MESGwwKhRAMwp49TjIymhg5MhObLakMkvh8MAyDpqYmnE7nEX8nqQhOAKiqoDJ++WXxXpZFs9G990JNTUflSVxoxFFKIXewhCv5M7fze85gDX1opJU0grhoxUsledjQWc8UxlPKKsoppbBLV3HHXAHRsdtBDydgRyOIwmrOZDIbMLDgIx0VF1UMIIwLmQj1ZPMH+Rbq8k7D27Sb59Vv4bNmEjNcEIsQL7N2ODoUmqKImPjEiZCfLyzlcFjMTXC7xbqZmeALedEkmTSbn6jDw6A+flqrZVp1b4/n1DCEt/GUvYi7lGIO+PpTEN1BmTECKzoP8mtKKaScobzHuYykDA07BrCboQxiHyFc5FNFFBmwUE8OOhZayMCH12QmjdJIJiGcrOYszuVdFNrIR6WNNL7Of/iU0V2ornVdHGNcGcYJAL1eGDgQ/vd/89H1KiKRBmw2oSAtJw0ZTBInApxOJ/n5+Ue8flIRHGfEk8CrVwuhd8YZwjq+996OOLJh9EyIBmL5bSZbaAAPYZMkTjOZfyzA+5yT6CmIj44cRwlXIjSP3eQU0rBhJ4Jmdg/Hrdi4EJPQWclMPLTjIoiHdoZQjoMIVnTqcsbT5DmNaecoWIJDKXllIkOjOzGMCLJVp9xdiDUvj2xTCE6cKCiyq6sFW2pKihD+8erHb38b/vhHcZz9hitsyyzi2/XFhP0tWGWZdecVMSmiEAqJOczvvisUp8UittXSAp9EC3kgYwkuxYc/LJOXpbFqm5eApEBMeFZ3cy/zWEoqbRjAq3yDhdxPCq1IYFJL+Ilhw4bGS1xJAIUxbGUSG4hhQUNmN0PNPMmn5NCAh0Ai59AdnT13p1MohtRUsf+7d8t88MFgsrOFcigsFHxSyfkGSRwtJBXBcUScHcBm6+gQ3rABpk8Hu6biifpokLwMYE9iPkDnKhqAAVRgI0rATBo3kY2DCHfyEI1kcR1/Yj+CGkDFwxD2sIxbmcAnhHGwljMI4eBiPqGcQTSRhRs/I9mR8BSGsIcsextj9S04bDpl8jhub78XA7iVpaSYVT97p86jwKIQiYDdpbDyzIU4ti8l1qYSdSpsO3ce5w9VKC0VXs9Yc4RRnLng5puFYtizR/D01NUJ2gZNE17Ru/WFrJOW4Hb4uO9RL7OtCgdegPXrxWvECKFU4h2+gwcLIjh3lkJDg8IwczZzug/yXGIsZywmPKvn+SELuJ+B7KOQrTSTTl9qcRIkio3X+TqNZGEjyjqm40blWp5jPZOZzEYGsp/B7GUTExnGHlpJS1zn0ZRRwG62cXDjEoh+A8PooAmJ087U1wslUVbWdRJaEkn0NpKK4Dgizg6QkyPcfzATidtKuL1mOW5Zwx+DFNqoYCAqHry0cBcPMZ8lNJJNI4LjJIU22knFjR8NOzsYQSbNGGBW9QjqhRHsYA3TCeEiiIvJbGAt02klFRsxUmklhpXtjMCOhhuVW23LidndZGYp2KMBRrV8ipsAGy1Tud14lHTJR5vFy3eyFXKsYiKapoHXW4i677c8dmcFsX4DsPfLJuKHPn3EsXZuhnW5hBKADjK9ykphJVssHYydAwcqDJyk8NxfxfvsbDFcfs0aoUBycoRiNZs6OftsITxPO00MjvH7Rf3+/v3C8woGYTIf8QTXk009GjIHyEUhwFrO4E3mcC7vEUMGpETFUx7VyGjU0I8wJexlMDIaflLMMxs0A20GGnayqTvkfRBPGnfjHcMwRHFAWprwFHqZNSKJJBJIKoLjiM4zBCZPNmcGqyrT9i7HnufhgN+DRa1lHFvZzTCyqWMyG0iljSXM51W+yRzepoq+nMZmWklDxcO/uJC/8R1kIij40bEkPIYK8qknhxhC88hoZNJAEBerOJMwTqzEcBCmFS/5io+hWUEGtJXiSHNRWZeGW27iLvfj/DQ6lnZdoc6ikJ4uwlh33dWJP6ekBGX5cm5zaGxbLfPOiCL8OYXMmyc+7qkZtrpaKBG3WwjGeDI5N1cohDPPFDmD7dvFNvr3F8rkoosE/fP3vw//+IfwthRFjOp8+WWhBECsO2AAPPIIfPQR3H2Hym3BYiwxQXwXRaavpYEDuphv/B6z+TvfSeRS4soxXrWVQZM5Nc0BSBwgx+RCkkzSPR0rIW7mMdpIYyNTP9c9YhhCeX36KTQ2diSYk31jSfQmkorgOCLODrB0qRBc48fDt6b5sN+vsafdg6pClEwMIJs6JrAFCzpBnARwcj8L+JiJpKJSQx5OwtzNAu7lPnTAg0o6PiR03mEc1fTnTFajoLKByZzLu+RQj4sgexlIFg0ELKlEkXncKAK3gtIPbJqObIQwZA+SFgGHA7skMbWfj/KwwmmnCSt8yZJOSqATK2ZGrodpA/yc1lyMtGgJSraQYEuWHNwMG1eOcQ6lOHWOpon3KSliWXz9uFcRiYjvnnuueMW3C/DKKwdT8QwdKs53VsQHv5KIht1YtRZigKRrZo+GksjJFPQQniumiFtZitOcsbyWM/DQTggHEgYOs2nPwMoYPuU5ruUanmMjn49LIhYTHtEddwhFOWKE8HySc5GT6C0kaxGOE1RV0Avs3dtRDSTL8HG5l4oDMsEmP8GQSOSWMYo+NJJFPf2pxE6YM1hDGj4msIUIdhrIQcXNNbyAnRAZ+LCZvKB2NGbzHrNYQR3ZZNCMGxUD+JAz+SeXspXxBCyprJz6C14/dwkF3yhk2DCIyAq/j95MqqIjtzVhJ0Jt+hjSct20GF4kSVjvXTwBOIgV057uwWPXUDRfYhVFgX79ulq2ceUYDgtrPxCAQYNE2Gj4cJE38Pth3jzx8vtFCMnv7/AqOm83vr2e1gO4fK6XCy53kzu7kJSCPiiSilPS2M6IRBio8+CeKvrjx0MRxeylgHk8yk08ziYmYTfHYh6gL/sYRCspRHCgYaOeHAzg5/yOPhzZZBo3qhiOY6hEo0IJuN3iOBwO4VH1whyaJJJIegTHEvE+gcpKYQ1v2SIsvawswV0faFB5+hkffZnLXJ5J0EbHJ3Kl0Uo1fQniYQD7SKMVNwFCDMVCDB0LQZxYMLATxmkOnBfDYGL0p5I+NPJbfk4GPqbxEflUk8cBttgnk5sJ7j5u2qwK48cL4VtZCevWTWHxgGe5dP/j5I6RCNa7eGd4EWMyFK68UiS3DwpTfAlWzMLCDm+hcygEDvYgevIqDre9g9ZTFNx3FOEuLqaB0/moLsI7fb/Ps+Xn0q73PLin83CfGvqxgq+xjun0pQaA7/ISd7IENwGs6OxnIGn4yKEeOxGWMJ+HuCuR8IeDq8Lio0PtpgfyjK0IP4V4PCLHoevieGpqxNCbJJL4MkiSzh0jxIdIBYOiW1jXhUAqLxcx8InWEn4cWY4UMx98riWEk1/wWxrMmP7F/JMMWsEc1xjEjhc/EjGi2GnBi4adF7mCO/kfXASwETOHuIgSxzpy+IjphJGZwBbcmQp6DFKsKnUDJvGXaY/y+kqF2bPF/r3+utj/iy4CVBW92cfti7xoduWz49RbtwqztZcmZ/UWeuRnU1Uad/s4/wovhluhvFwIXBBC+hHmH0SEt5BF2NHw4aWAPdzCMgawn8lsoJUUQKIPLQlyOxU3B8jjHb6GgzALWUQarYxgO5fxD4DEtZ/Ls/jxEJQ8ePCT4/FTPHgJEVnwFlmt4rTOmCE8oxPgtCZxEiBJOncc0XmIVNzCbWwUD3NbmxA0V7McnylovLSwgPsI4mICW2gjlU+YQBvpJss/+EjHRoyPmM5FvEEzXtrwso0x9KeWH/Ecy7iNdJpxoNFuUh6I70UBg41M5pv29QRDEg7CbB1zJUq2wogRguagrk6EaGbNEhU22BUq/QqaXYRePhOHNcWPDw451VFR6DNe4VcPiOlhqalCEUgSBAyF5d2I8N5iNotYmOjGzqeCPA4wgP14UHGapHsxQMdBDKtJTmegotCfCp5hLsPYSTb11JHNCs5DReFmHsfAQh25WCXwZNjpZ/MxTKnhg9phgmvKK66LohyVgWRJfMWQVATHAD6f8AQCAREOamkRkZJ4p23n0EMeVUxjLf2ppJY8c8A7TGQz2xnO6XyMhI6TEDsYwXi2YWAhgpNPmEAN+eRTycdM4Qr+j7u5mzPM2QAHyGYL44hhw0szoymjoQEUh0Zt7iiq+0/H7xeJyEWLhCBcvLhrYvZzzzw5gVgxj2Sq47e+Jbq6KypEZdKvfy2URnWokD9kLMEe8OFMlfn+joW0m4q7HxVMYQMV5OMwmUqFJ2bgRGMPg4lhQ0XBQYRsDjCKMjRstJNihplamcpH/Jevm0ynuvA8dJWpjWtwEGaObzG13nmU2QqZOFGU3NrtYv+SpaVJfBkkFcExQGWloJCorxcPrtcrPIF43Xi8FHEIuzift0w65AiaOUnLRgwFFQMrV/M8KbTxI55nCuvRsFFFPkGcCbIzDTnBE3QFf+NsVvBDXkTDTggXzzCXO3gYqwRYrcQkiXDMRlUVGGZnb3a2eM2b16szT44rjnSqY/zYo9GORr+sLBg+XCE1VeF7Z1Vz4GcaByJiQ0EUbETpT7XpbQEY2IghYbCdUdSRy3TW4CSMQoB9DCaXAwTNGQ1WookO7ygyf+Myvs9LiWFB7zGLYEjhJ5FiblWX8NprCnl54h4aNepLDSRLIolem1l8AbAMsAJ/MgxjcbfPfw/MMt+6gWzDMLzmZzFgq/lZhWEYl/bGPp0oUFVhcUajIhcQDotlDofwEEDQHDzDtfyZH2IlShgHBhLZNFBHDps4DQeRRBMZQAUDuY8FlFNAOi1MZgNefPSjiof4eYKGIoDCO7aLWWPMIlUXychUw4dKKm/ZLyI7NURatpNzRtWx8BYfqaOULkLxBIzufGF8nvy1qsJzz4mZw6Wl4rqVlopl2YqXCl0mBT/teLAQMycpW8wxmBoGVhrJ4hNOo4UM7ETYyCRe5kq2Mo7f8kv6UYmLAM14yaMWO2GyaSCKlZ/wNIVsxUGQNkR3XDseQu0tKFYf7bpCdbXwKuP79oUmnCWRBL2gCCRJsgLFwGygCtggSdJrhmF8Gl/HMIzbOq1/MzCx0yaChmFM+LL7caKipkaEg9LShHCJRDqSkJ3RQgaljGYYu1FRsBJjMOUoqEjAQ9xFI9mJ6pJW0vDhxU6EenLYzRCmsIEoFubyDEFciaqUrCzw+xVaURg4AGp3Q0yTsRPB0ScVp9WPO1UmbZQXehD0J1B050vh80x1jHsPgweLfEgoJPI6/fpBba3Cy5lFXNFYjDfWgkyE9UwiAx8ptJFOCyGcfMzpPMivDpqX4EZlE+OZw39JpwUZjRa87GUwBga15DGD1bSTipdWQGIyG1jNDFRNplbzopmzKfLzhZHxu9/BH/7QrYQ3iSSOEL3hEUwBdhuGUQ4gSdJfgG8Anx5i/SuBu3vhd08KbN8ukq6yLLpE29u7Eo4BjKWEW1jGSLYjoeNBR8dCPdncwcO8z7ldSgrjTU1vMpvzeZvh7OAsVtFIJkPZyzbc3EQxP7cuwXArnHeeSJLG68/zhik8u6+Im6Ri+kZbGD1GRp53Esd8PgeO1MPp7j1EIqKGP768JqOQ4pQltO734ddkFrGQsJkUdhAilfYuHlzcQxtLCfdwD1/jbRyEsRBFx4KTCAOoxEGIerJxEqKNVFpJw07EDBs18xB3EUDBEhOewI4dgo8oEhH8THfd1bWCKDnBMokjQW80lPUDKju9rzKXHQRJkgYCg4H3Oi12SpK0UZKkjyRJ+uahfkSSpOvM9TY2NDT0wm4ffagqPPNMx/+d8wJxxJuVfKSzijPRTQbQbRRyNc/zHy7p0tQUxmEOUYlwEW+wmJ+jYaeGvtSQj4ad8Wwl29pIHjVkZ0NBjsqs4dX0TVVpbzf5jb5WSO6LSzj99UVkPrfkK1V/2FMjW0/rHKoRLTsb7rsPApJCo6MfPpsYr+kgTBqtWNETHlxn9KGeX/JbRrMNBxEs6NjMXIKTEGHs9KGJmaygH1VM4GMyacRClP0MYAGL2EsBeVTj1FVCIaEAAgGhnDIyujaZlZQI5fDLX8L114uy5SSS6AnHOln8PeAVwzA6i8OBhmFUS5JUALwnSdJWwzD2dP+iYRhPAk+C6CM4Nrv75VBTI2K3/fqJsILPd/A6fakhDR9Wokxks0kFHebPXNWFiqAvNQxgHwWUk0UjINFKCm8zGxUPQdzYiSATYRD7yJBaWehYzJ7UC5nx77eR0fjlaTKhuUVERhSSlweKotBjLCgJ4PDew7e+JYjs7rhDKNb//reQO7QlXUJACippJkfROLYwl6eZwnoyacZmegIgpj/YiGIxCSlks7xXQsJKzKQBCfE/3E4UG+2kCpoLQ7DQ6roIDymKCHmVlQk+pXjfyqefCu/h2mtFjiOZS0iiO3pDEVQD/Tu9zzeX9YTvAUWdFxiGUW3+LZckaSUif3CQIjgZUVYmKoVkWTyo3b2BsZRwK8s4nY/JoIkq8lHxYMHgB7zEBqbSSDZjKWE+j3AWq3ARQMNhlhhGuZR/EsLNNsYwjhIGsh+rTaJiyCwyLQrf9i8gdOZsHLm52CN++HcxzEoWnR8pDpcfGTwY7rlHWOHTp8OGDQqNMUHDPY4Srmc52dQxijIchPHjIYLDHO8p2vziFo2OBS+tGEjmgBwLOxlCf6qpJB87UUZTRggHb3ARdiLMYymL+QV1Rh42m8KWLYKB9bHHOjqPa2tFpZrHI4yRxx6DJ55IXv4kuqI3QkMbgGGSJA2WJMmOEPavdV9JkqSRQDqwttOydEmSHOb/fYAZHDq3cFJAVQUnTH09/POfIowQZ5CM0w2DCBPcycP48fAR05AwyKcaLy1Y0ZjKOpZxK5NYx40sR0M2LUhLpxJFC3ZzUEoIF/ukofjI4A3HZbS48pk4yYpMlBSvVTSEeTwdRedJ9AriXsNLLwnv71//gkmjVG6URBhvAJWEsZNKOwHc6Eg0kIWOFQMLKi7a8VBHNmEc1NCXNtLQkOlPFRZi9OUAuRwgiwYcJnWIgsoZrOZBfkWxcT0Zu9ezapW4x9xuESbavl14BHa7CCE5nYLBNXn5k+iOL+0RGIYRlSTpJuBNRPnoM4ZhlEqStAjYaBhGXCl8D/iL0ZXTYhTwR0mSdIRSWty52uhkQ+eu1UhECP9Bg2DfPuERxCt++lHFTTzOVNaZXcMT2c9AFFRshPHSjgWDsWxjAffRQiY+BCto2GS2bCMVOxGiyKxjOhuk6fQ1arjXvRh3nlfQNVtighY07op8oY6wJD4Lnb2GtjbwV/lQ7BohzY1Vj9FOGlCNiwBRbKxlGvsYQAwrYVy0kcp/uJALeYMACmfzPg6z3wAMYljYRwH5VJJFAxZiTGcNEjpD2Y0NjaeNa1iY/ixVfaayYQPMmQMjR4pkcmOjUAJjxoieiOTlT6I7eiVHYBjGG8Ab3ZYt7Pb+nh6+twY4JbKUqipGTtpsojM3Poe4rk54BPGKHxcBJrORj5lAG6lm1/An7GEwU1lPGq0EcVNFHgBj2MZGJmPg5QA59KUWN0EchGkhnaUmQ6YEVDqH8XzGPO6yFJPa1gIuWWQ1335bZDxP9o6wEw09lOS0tYkGQd0qY4vGMCQr6UYTVnQGUAXotOKhkVyCOHES5hnmsp3RXMzrZsjPIIoVFTc2NGzoyGg00QeFdoawC5c5OS2IC400svQmLq95nKUpY4nZFJqaRG5q/nx4+mnhCbhcycufRM9Idhb3EtasEXOHXS7xPj9flIr6/XShMQ7gJoaVkezkEyYwmQ3kUc1wdtKOGydhWkljIBW4UbGiU2WmXHYwAgs6leTTRBa/57ZEQtligb59Ya+9EOPhJcin+ToE1AUXJGsIexuHIC0aMQJcfRSeai5ibrSY6lhfzjRLe2PYsBNiHKXUU4+GHR0LzzKXzYxHAqaxhlzqiGBHwsBJGIkQXhoI4iGME7CwjwHkcQANOzIRgoYDXZdoLvcRzVEIBuHOO0XoavLk5OVP4vBIKoJegKrCCy8IYRyNdszajaMzl5BMhDAOHITIoY7+7MdLKxHstNKPFPzkU42BhI4FFYV02inHxQMsMOvKtURlisUivBAQXbBuN0w9t1uG81TpCDtRcBjSouxshYcfhl//upBHQksYrpcxMPV/2NeeyYCKVfhRSKONdFqJYaGcIeRRw0h28E++SQAnl/FP3KgJ5liAbJoIotJADgXsxWWGjUAijIOtjCEas6EHAmQ6VTpXgyUvfxKfhaQi6AWsWSOGp+u6GDQjSR3DZqCDS0jBj4qHbYxhGms5mw/QsZgjEu0MphwJPVFTEkVOWI0OIgRxd6lNt1oFS2YoJJRQJAK/+lXyoT/q+AzSog7iOoUBmaPI/l0qafsiqLUANiTNZBtEQsGPYVJT5FPJWEqxE8aCYY67tBBFIoKMiwjp+Ihgx4+b3QzDjwcJgxTakJC4jwVEdin8IzKPRYsKee45cT8kG8uSOBySE8q+JFQV/vIX0bGbkiKiBMFg13UCKBRThAc/+VQSw8YfuIEWMtjJcGLYAN2sH5fMJKI9UWcuoxHGjosAbrqOpMrLE5O78vLEHN6vUF/Y8UPntmPoMQmfnS3I4DS7QtP3iqgoj+KSgihyiE9Sz8FqNpFZMGg2qULGsQUQg28iyIBBBNnsEQkDOho2JAzSaUUH896RmMhmRrONEexgYnQjNzQtYvcWlZqajsayhQvF361bSSKJLkgqgi+JmhqhDCZPFjmB9naxPDFm0BTcpRRyB0t4me9hAFNYjxcfHtrZx0Bks6EIJCrph0qKOWYyTDW5uAnyCxbzCPOZYN2KzSY8gooK4RH89reirj2JY4DPmn9JV+E77+lClo94lNfmPE6paxKGbtBKKu2k4KENF0EUVAaxHzsRqslnF8NR8aAh4yCMjRh2ouRQRzqNBHEwnD3Uk80BckmjFS+t5sgchWHBrWRFa2hqgocfFoZK//7CeUmOuEyiO5KhoS+BkhJRQ75xY4cnYLPByGjJQYPO4wRw3+Zv+Einmv6swsdZrKGJTKroRytp7GEwBVSgEsRHKgu5l9nSClqMdPzmdKwbKaZ4kOARys+HBx8Ug9iTOIY4TNtx9xRCSwu8vUkhZ/bX8BeMY+a/5vPf0DcIRO18nX8Tw8a7nMsc3iKGjY+YylTW0UgfyhjBBLaQSTMRJGSzoySVVrYyDh/pZNCEgQUJAxtRDCRiMcjNEQZCaanYxcmTRUVbT9TbSXy1kfQIviBUVVRmbtokYvO7dkFVFdijPQ86j/cQyGgYwGi20p8amsikhn5sYwz7GcRYtlNNXz7hNH7M0+xiJDYjKhLNNog5PKQrGn1dPiZMEFbe0KHH+2wcPcQb9E5IC/YQpEXdUwjp6SSmvrXUaUQtdmxZ6VilGGGcRLGhY+V9ZiKj0Y8qZDR2MoIodsSYSw8xbERwEMVKCWNpJhMFP+2k0EgGVmK4UVFQKbUUsrEmj127BNutqoqqtupqcb/K8jE/W19NdLuBT9T7OekRfEHU1AhPIJ6Ei/dsHW7QuQ8vA9jL5fwNN0F0JOrJIoMmUmjjDS6ikgFk0Myf+DFX8RdcBJjERjIzQRo8GM3nRzFk+o3xYjvF6sK7JzQPOVbyBEd35tKWFvF30SJwRL0Yt8vsWe0nLDmRDNFuHsKJjoV1TMGOxluMwEc6fajnHN5Hw0YbqVjRkIlSzjCWcxNzeQY3QXYxnB1IBFBQUViuz6MtppBuFedy3z5RULB/P5x+ughZnSzn86RFtxt4x+wifv92IcGgKCy5+eYTh/cp6RF8QQQC4gE3jENXCMlEyKE2sfx0NjCVjbgIYiOKTCRBH+AgTArtxLBiJcZPeBo/HvZRwGbbZEa2b6BP+15SJT/DlxZx7yMKS04h0tDuCc116zrCKydbbLtzCmHLFtHP5/eLmQFVLQpPO4vIVfzkGHXsZDg7GU4OdXjw8zw/IoAbH+kANJLNJk4niIsU2nEQ5hMm8AI/4lPG8CzXIKHTTAYNZPMnfsI8HmVztJDqati2TQh/wxDKadAg0fTmcJw85/OkROf4YP/+RBweGn69lNS6XewpUfnkE7jmmhOHETbpEXxBxLnpexoy81e+zY0UM4YyDGArhYxmGzfzGDGsNNKHXOrMqVZWrETJo5azeB8rOg7CbGck5QxBAiosg5F1jbfar6BMmcT/ZGUz9UiGxx8L9EJdYk9l+Y8/Lrwst1uEMg41VvJERWGh8ADmz4fZs0V4yO8XpG8xuZDX05YQUH20Wbw0NpHwGAG+wyuJUmMFP81ksIozSaMdJwEiOPgRz3MVL5NCGxUMTKz7HV5hHdMP2p9wWOSvZFmcV6s1Oeu4N3HQY9AtPhhpUSmoWc25dQuYbvfyWv8iNoYLefxxGDv2+F+DpCI4QnS/0Hl5MGyY6B+II04j4SbIaMooYSy7GY6dCDfzOFGsRLFhQyOCjJ0wMjphZFwESKONJvqwhXGcxmb2UoBqS6dfZC+Fls24gjauUl7jzUeKGPtc4XG/eY4odnMEiiL+zEiSCLmlpQl+nB07OmYGn4w8OZomCN/ShXGPxwMNDcKbbNcVfE6FcBgCQMiiYBjCci+miCKKSaclsa1a+hHAx2W8igWdGvqxg2GMpozdDAMggp00fPSlhj3mss6Ih4by8sQ5l6ST63yeqOjxMSgQkYH2Sj/IdlI2rkGzOqiwFZBqj3BpZTG78pYgScoJoYyTiuAI0NOFLigQn1mt4mG3RbrSSOhYGMFO9jMIFQ869Wg4WMdkpvMRVpOMeB/9acXLIPbjx8MKZhLAg5sgGTSTjY9Jtg3U5k/GnT8YR8zPWVuLaa1ZgjLsON49h+muTdzVn6UoTCXhlb1UVir84x9CEEYi4m9urmBxTU2FDRvg2WeP/wPzedDTjGSXC+bOhRtuEN5OOCzuoXjoJhaD0pgoNfbiw0WAX7CYCHamsD5BO5FrhhTbUcigCSsxzmANNqL8gsUsZV6iUi0OXRf7UFcHq1aJSrPy8lMnvHg8cKjH4NprFf6voojJG4pJ0X1MMMKEpsxCK7HTHLaTp7cwaaiPkFtJKOPj2fSXVASfgZ4u9NKlcMUVoou4Tx+xrHOSuB9VZNOAjShzeItPmEgQN+9zFgt4gFbSiGJFR6KNdECilr6AhBUdBT+NUg4PeRYx2lNBnv1RIn0HY7eCGvPgNpPPx3WozGd0136mouikJKSojKW0iFisMDF1yzAEY2Z6ung/dqzgbzqZcKgZyYWFQqk9/rigJKmqEnMEWlvFMfv9ENCVxGQ6DZkMmrBg4CKIgUQAN24CSBj0o4IzWYuOhQP0xUqUIoq5gyWJEZkgLlcsJn4jzom1dCk8+ujJpWBPJPT0GNTXi/P6aX0hm0csoU+khvD+xbhqFWbNgj0lfty6jJ7qpciczvLOO/Dyy+L/41EYkVQEn4HuFzpehrdzp2jmAjPWaiaJvbQwgc000Icc6pGJMIUNXM9yruIvfMwECtlGCAd9OUA5g9jBKPKoZgobyKSRIG6esBaRNjSbijaF/EFuyhv8tAY9uHQ/owpl3Hne43VKBHoydzt31/b0hDQ0iGk9mZmiwN3thpwc2ioi/Ki9mG3WJQQNBUkCl6HSvt2HmuHFmqpgtZ6cYYxDtRtMnSqUm88nFMHSpYKqxG7vICqM5w2KKeJWluIiiIZMBAdORPv6boYgYaGOXBrIwkqMsZRSymi8+LoogkhE/K2qEqWs1dVibsHatfC1rx3Ls3LqoKcKMVUV5zoWE53l9a5hPJc6j+9VFeMMteCxy0SuK+LicQplZaLhb/16kcA/4wxxj3R3ro82korgMyDL4qLW1wsX/oMPhIvd0CAsq3gncZxG4i4eog8NKARoJJModvYxKBHuGclOsybcipMwE9hCDCttpHEtz1Er9UNK9xK2KeREIWpXSP9NEbNeKCaitmBXjvGg+UP5q4cyd+PrdH9C9u4VJRI1NWJiSksLusOJlp4D485Gimq422sYCAxlO5fzD9Ah1iTzhK+IWb8+AXIiXxCHIn2LL7vvPtGOcOGF8NZbMFo/uCFxHo9yNitYwh3oWJHRAJ2BVCBhEMNqEhqK6iILRiL5DF0VSyCm0N4uQm42m7BEp09PegVfBJ0fgz17RF4rK0tUi8XlRHY2bG0vpK7/Ei4/18fG3V7eWiROdjAo7KKUFLGt+CyJY53ITyqCwyAevaipgY8/Fg+Nz9dRcdEdpRSygEW8xRyayMBPGm78DGU3jWQioeMgBEA+lTgII6GTQx0xbLhdBsOn92PzZoiaIZIHHoDMmYUweQnysQ4gflaM/3BDfTs/IQ0NxD74ED0G1vUbsISCYpRi1EPM14ivYhXu2FB+y88ZwzayqaeBPqzjDFTZw3y5mDf+uYSLL1bIVk4t9rTOjpPHA7OmqJxevhwVT6KTPB7m+S8X00gWt/F7TuNjgijsZggzeR8bGpm00EwaURw8xk0JbyBexNC90z0UEt3G8f04BU7ncUHnCrGZM4V1n5cnxoRGItCwT2Wwx8ek0TKBgPg8EhEOsWEIZdHSIjwCWYampmM/PyqpCA6BeIjb4RCx24EDhcaPRsUrji6WFgpR7GxjLAOoJJVWYljZbnaIPsbN/C8/Io9yYtiIYcGCxGjKyKaZJ7VreTL6HP0umsKFF8K55wprAjj2XMJHkgzuvF/xlsnOAtpUFLv+38d4X1mJM9KGO9qOji5Gs8fCyBYLbkNF1kMMpIZ2UuhDI/lUk8nrVGsD2KsNYud6H7+9ag+/SF1OTvpJ1mF2GHR3nNIMH05Jo844uCExgMJGprKQ+1jEAqrIZxYrqSKffKppIgMJuJ4/8CljyaOaCHKiiEHtpFjuZAk5+QpOZ7J6qDcQrxBzOkVIKDtbGIxfyynhrJLluFvrGPraDsrlEQwI5bBcKqIsWJhoRNV10fSXmyvky7x5x/ZxTyqCQyBuqbnd4sLa7YLcrTPGUsItLMNLGxo2fs9tfMoY6smh0hxFaCWGgzA+vNTQjzt4mKXMI4KDXOqIYkFCQs5MxW20883Kxxj+3BNkDz7O5tlnJYM74zCeg4rCEy+mcnfIh0XXTOUnCJZjhkRjLIutFGIgBriHceAkjGBhtYARY4S0g9bGCJPXL+ffNg/nX+4h33MIxXSSoXuETZK8WFwyqUE/qiRyQhpylzBPLXmoKORyAJkIKh4q6M9qziSNNuxoPMJ8k8Q8goKfOnKBDsUyJNNHWFaOi9A5FREPIYdCQgHU14OvWmXs9uVURR3MlCsJWtz0jVZSFhvAdRQzP7qEeMFHLCYqyNLS4NvfPvb2Ta90FkuSdIEkSTskSdotSdIvevj8GkmSGiRJ2my+ftLps6slSdplvq7ujf3pDcQtpNZWoa3b2jpoJEB4Ar/hPs7iQ2aygvP5L3/lcubwBs8wFwdh0mjFQZhiihJu+vucy/vMZC3TqaEvFiCGTDCgE7U4kSwWYk2+3j2YuLVeX38w0cmhyE+OgGo58f3DtADv3g2f7HCjWlKxYKBhM9WAZPLpDOUh7qCNVDN0FiZkUjBb0NGRKDcGkButQg9rNAQ8rFwJEbunI5B6kiMeYVu0CH6+SOHjqUX0TfEzyNhLX6mO5y1zkdM6JHUBe0iljWl8xCD20Yd61jGNMA4i2LiSlxNcV81kMJIdeM2eBAU/MUmmPuLlpptExdBJ7lQdd5SUiI54vx/ee6+DFVhWfVhiGjGs6NEYfsODS47hlPVEv0ccsizkzK5dcNVV8OKLx/YYvrRHIEmSFSgGZgNVwAZJkl7rYQj9/xmGcVO372YAdwOTELNYNpnfbeE4Y88eIfw3bhTNTdGoiOd1DKCv5HQ2kUI7BuAkRBptPMdcVjGDxfyScoYmQkadQ0hPch038zj76U8+1bTgxmrE+CQ6hjSbi9QB3t47kLi1XlcnMlkjRggKyqIicUCHygF8VjI4jsN4DiV7FBYvhrLWPD4xJjCND4khoZrUaBuYQhHLaSSbIG4WsIiJfIINnWr6UsZoBrOfAvbxM/5AaqQNFx4qK9OpLPMzJOcYB1KPIjpH2MLDC/kkdg2nrSnGkCR+YjzDkxEX6ylMjD0N4CaAQitpZNNAHlXU0o+XuZKreJkIdlJoQ0VhOyPIoBkPwrt4Si7CnaWwbh1ce+3xPvKTG53tIEkSgry2VhiNPryEDRmJGJphxRrxE4qEmcYKZKL8nMUsM/s94hVdDodQCPfcIzrSE6Hho4zeCA1NAXYbhlEOIEnSX4BvAN0VQU84H3jbMIxm87tvAxcAL/fCfn1hxC9uXl5HyHvfPiikhBtYTjZ1FFJCX2qxI66gxYx7y0SYzkf8kZ9xNf9LDf26JOtSaAMghJsW+jCPJXyNFUhhC4bFRc7tRSjZveSnd050VFaKOFdlJQwYIOoVQRTqHyoHcLhkcByHKCNVZS/Ll4sbeUqfPcSqZMIxBxk0E0GmnVRe4srExLVSClnCfG5lKZk0MpAKxlJKG6l8yjjGUEoqbQxlNzu1UZRvzaHvL4twn2IxDUWBH39PZfc3n6PBmkPI6iHT6eenrcWUs4gBVJBCGxPYTCZNYI40dRNkIYsIoPAz/sjpbDSpqXV2Mpz5LOkYcRpRUOqEbVBWJgbonGKn8ZghbgfZ7bBypajEikSE4RiKKTzNtdzM41TTl+HswkGYNlJZyVmoKAf1ezQ2iqIUh0PYbSeTIugHVHZ6XwVM7WG9b0mSdDawE7jNMIzKQ3y3X08/IknSdcB1AAMGDOiF3T40WmtUnE0+oh4vuq7gdoM1pHIDywnjYACV+FGwEkOEMMRkWQkDHSthHADczOPMZ3AiWRfBzulsBOANLsJOhOmsZ4FzCSlOjWbdy+rZvfhEdk90pKWJWJfV2hEK6t9f/D1UDuCzktSH8Bx8moKmQf8MlR9K95Fi2YmLEDoWdGwEcHElf+FtLkh4TNfyHDXks4uRVFLJLFawkcmcxiYCKBhY2MRpOI0I/xi+iHRLNqPUU0+I5Xt8BPpoONweGhpAjXjoF9vDEuajIzGF9WRRTztpgDBCCignl1rK6ZmTPIBCY6eegkBACK4FC0QhxCmQdz8uiNtBTU3iEVNVUQUEIoc4l2cxsNCGl19xP9/lFfZSgIYdmUgiRFRLXkfRSVShvl7wUnm9x+a6HKtk8b+Alw3DCEuS9DPgf4FzP88GDMN4EngSYNKkScZnrP7FUVKC9dfLmP2+StCisNmYR0VaISkxH3aTI8hJEBWFIC50LHhpxQAMjIRmF59JDKAi0XGcQhuGmZZxEqKdVNJpwWXTaHb1S9xQvTZpLH6XxlnG/H7xNxbrkJ6Hagj7POjBc/CqYnPWuhoGtm6l3W7HEY4QxYaMRhQb49ia4MXpTt9tJUofGpnFu6TRThX9iCJTTw651FGySeN3vxMW2Lx5p5YQSx3gRbLLZNj9eAZ7qC1rYaS0g7eM2fhIJ41mLmQ/Ueyi+ooYmTTxG+7nb3yLEG7e4CKchAjhJIc6+lJDEHciVGkYIpRRv1dlbLqP3/7GywNLleSUu8+JuB30yCPCxvL5xD0Za+ugnKkjFwU/F/MfVBQUVLxUchqbkdH4HXcRxUY7qYny3jKjkJISkTeKz50+muiNZHE10L/T+3xzWQKGYTQZhhE23/4JOP1Iv3tMoapo99xHZM1Gxth2MCa4kdvVRfiqVVolLx7amMVKcqmjgHIkYuhYaEchgAvDbOppJp0SxhHETQUDErTUIZzmcHqdEE4UM2ZbF/YmGkq+sLPTU9I3fpeGw8LyDwTE33BYSM958w47bvFzoduQlvhPqwEwAiG8ag0yYdwEkQmRTzV2OsqwBAlfBC8t5FHFJfwbA0ijDRsR8qniEyZgJ0IEmWrVy86dIoezaNGpRaesZCvk3leEJeDHdqCSVK2ZCucIgvZ0sqljADWEkLERwUYEHSuNZDKK7SxiIZNZRx7VtJOKnQgptPELFnMvC3mE+YxBDC0eHinhpzvmM/b/LeS8N+Zz0zlb+dvfjvPBn4QwDBHOyc8XDaYVFZCiHzyXBOAjpjKHN/kGr9GXGrYxmgLKGUUZAdyEcVBEMWk2FZdLzJeuqTncr/cOesMj2AAMkyRpMEKIfw+4qvMKkiT1NQyj1nx7KVBm/v8m8KAkSSY/I3OAX/bCPn0x1NRAyVbC1gwkh51QMMIEtjKtXw1b6vNAhRgWGuhDFvVYMYhiUEM/LERJxU8QBxZ03ARYwh00kp1gkxRVMsMByKEuof19mkKsFv7why8YEzxc41dna12WxTqd4/2flQP4EigshIIH07B8YEFrMJB0CdCRTPvDwEIraYkcioKfSWxAQUXCYDfDiWIlnRYkdDz4iWHjGa7FFfbh0sGSoiQelmEHE26etBj+rUL6nbWEuh0+HnlU5px3F5Lmb2EyG4hhoZJB2IiSSy0HyMGKQTspuLCxiyFMYQMWIGI+4i2kd+kjWMgibmQ57Xioi3no4/JzbaCYB3+9hLPOUo5ZbPpkRzwNF42K5vl4j1HnuSTx8w4wjXWsZgbTWIeKwjB24yRMJk3MYgUhnFTQn74uH3a7QjB4bI7jSysCwzCikiTdhBDqVuAZwzBKJUlaBGw0DOM14BZJki4FokAzcI353WZJku5DKBOARfHE8fGCxQLRGLQ1gRERO1xbA7awj3ZSEy63iwDn8xZvMocoMjNYRQQXK5mJTASZKHsRFKXxwfXxcrFW0rCjEZAFlUSqDGefLboSPzeOpPHrcHH+o9yoptg1QuPH41u1C0mLYCWKhkwtuexiOGm0dnGhm8lgFiuooj8R7MSwYmChlDEUU4RDijHXeBZHVMOyW+bNIUU0cwrFhTpByVYoyFa4wQt/aipi6gcPkUobbaTyAefgx8NlvMo2xjKKHQDEsLKb4QRx8xg300oav2DxQRPzOocsJQDFg8vagjvio6IiqQiOFD6fcLS3bIEDBzqWxyln4nTiGjIvmRVddeQQwkkMKxYMsqlHw0YL6TgJMpIduNNk2tpg9GhRtHK00Ss5AsMw3gDe6LZsYaf/f8khLH3DMJ4BnumN/fjSyMtDH1OI472dePQgMXS26IXsi+ShA5oZvmgnFSsxQjiJ4DB5XkT7PkAzmeRQ14X0q4A9icqhKDKPU0RttB+yJLhJsrO/YCXk52n8Og7YWumldnsONbG+nMYqYliwovMBZ2JFjGns7ELXk0MEOzsYzhhK6UstMmEcBLmLhxhq7GE9k6myDCZN93NpVTGRaUtISzv+x3q0UFgIc39fyD1FS3B8Mp+6SAb10XQU/HzMRCLYcRJEQmcDk8mgCQ2Z7YwCOMgy1ZCpYAAxScZj+AlaPKRIfoJRmYDd+8XDk19BeL0iNNTeLso+OyNuAB48dEillFGcxmZcBPGRQoAU0+O1spMRxEIaMYdI6R0LqvDkqMrOUBSaixZSkTMJrWAEldmTeNC6EL8hhMxf+TZeWhI8QYv4NRk0k8sBFPyk0crZfMCFvE4KbYmLH6/9jjf5BC0ebpaKyVZUUZFkhZ/97AvK7SNt/DoOUFVY+pTCH21FpCo6FfIQ7ETYxRCs6BRTRC15CUEFYCfCVgoJ4k6EiGLIKKiMpRTQGUspVj1CW8yDpGl48bFwoYinnoooKRGNX6X12fyP7S7SXGHyqcSDn/tYyE38gZt4nHIKOJNVzOR9UmljMOUJy9SDP/GdYopoJJvHjCLSZT/9qURr8bMkVMTVV0O21kODYRI9QlHgJrM7qrsiAOEZ1NCPAIJW/C1mM5u3mc46bGj8D/N4l9m8w9dYwSzWMIN6KYegw8ull4qKrmMxUjRJMdENnumF/O2sR/Hi418feiltUhgb6+gDAHiJK/GTwk95EhchUmnBQQg3IdJopZHMLtvsXhHTqnvwSi2cP9VH6iiF1laRZ/1CONLGr+MAn0/cwOVKIU/mLEFv9rF1u4xF1xLVK8BBLvR9LERC5wxWsZfB9KfCPLftqCg0EsVBCIsRIRCVceR4cXtOCcaJgxCP/KWnw3nnwbvvFnJLxRKcnfitANYxnat4mfc5h2YyUVC5i4eYz5KDLNP4d3Y7CvnzOJEjaop56R/Zw/An56Nt15BdpwaX07HA2LHw0ENw/fWC3ts4RE2jG5ULeYM1TCeAGwML49jGk1zHXJ5FRiMmyTxhKaK2TUyvy8w8Ng5+UhF0g6LAT+cpPPigwp4DoHSy5uOu9VW8jJdmhlCOBAymHCchWkjHgoGORAh3IjTUOXEk6Kj96FaZnfVepozpmH/8hXEkjV/HAfFd0XVoiykE7QqtDg5KgPUkqMayBQkJA3ATwgBz3nMGWTSRRy1+0njGWUTbJwoXX3xqzuDtzk46fTr8X4VCc7ehRGJQEdTRl2zqmMwGUmljCfN5iLsopbDLbAIQxWMrNyh4vQpeWeU77cvZEfPQP+BhTNapweV0tBGv06iuFk1gDsfBnGRxTGMtM1hNCBcxrGxgMjIaNeQn7n+/ReQNjaC47sfKwU+GhnpAYSH84hdiaEe23YejWxlYKm2Mo4QACiEcyERNXhwLIZzkUk8qPiJmziDunqcg3PBUyc/fcotoCik0N/eSAd+tfPNEgKKICtXhw0Xb/a5dQvj0hM4utCDzexQLMQazz6wz0gljRyWFDzmLR5jPPH0JG0KFhMPHh7r3WKBz5C8SESMdOnNexdF5MNJkNmAAbaTSTAZFFOPm0LEFnw8iDT70sEZbzMM770CV79ThcjpaUFX40zIV64FqtqxRCQTEtbLbu67nRmUIu/ghL5jZLhcR7ExnDQYkjJ8a+tEWU9B1sZ3GRnHdr722w7s+Wkh6BN1QXy9au2VZZOzXvuMl3C3ZFsWGjjXxHWGt2kymUcH2mE4TD/JLljGPT6VCPqWQ+cYS+lh9TJnjZdgwhcxmYXAdcYXG8Rxq+gVRWCgMy6IiYT3F+Vh6iqdCRz7FRzpvcgFn8QEDqKSKXDYymQaycRBmO6MIoCAbwhoLBuHOO0+a03LE6Bz58/k6eOxVtatC6DwYKV5ZtIHJ+Egnn8qDppV1R5wXx234CQY9rH/PT84sGdnrPRlvu2MC/9oSvvnhcpoOaEwICA6nLXohktSxTrw0Og0fE9nMFsYxhHKsxHAS5mWuPOi6xGKiFHrBAuFdPPvsoUeC9BaSiqATXnlFCJOGho7h6bY0hWcb53ITj2HQgIaNv/It0vDRn0qTOtmOBNSTRX8qCOHCSzuT2MgCFvFj4znCNgXdpqD3UYg6hGV8111HqATq6wWt4RtviLvhJOPi1zSREHe7RXijubmjDb874vmUCHYs6GxgEqm0YSPKFNazhXHcY3LqyLLo4nS5xFCQk+R0fG7EI381NWKa2UcfCZ6gtrau65VSyHyWsIT5NJOBj/RElZAP70GzM+KIL3+GufxEegaH1kKgXqbmsiJa9yiHnU30lYWqkvHCMmIxGxWRHGxShJ9qxdwWW4JqntvORSLNZDCKMkawg7eZQwptyERZx/TEuolroyvs3Am/+Y2YbzBw4OFHgvQGkorARH29ECZVVR3Wanm50OjX8gw6Ehk04SLAA/wGFwEsGGxnJHsYAkjYCdOfKqroR5tZYlrIVnKpoTw2jMGDxUQoi0V0wx6REnjlFXFH1NQIaTprFhQUnFTx2865glhMxFEPBR9eUmjjdDaag9mraUehjTSchBlNGS5zXq/TKeg42tuFkjmVoSjCSrzzTnHvfPKJ8IK6T8prJJuHuIsiismnEg2ZZ7iWaazhe/wFCbpMKYtbrG6z/PRp4yc0pQ2lWffy9z4Kzx3BbKKvJNasQV63mimGiz6alU2WyVhiGmn4Eoqge5HIWs5gJisYxD5COHmMmxOh0M4T5J6yFbHPUcj27cKDjjdKHs3K8GSOwMQbbwhZ2zlk4Ubldh5BwU8L6QxkHxPZDOh4UFFoZzDlLOVWfsQL/JVvYyCRRRND2IMblbiXmJIiKj/2f6qSGaom2noEAb/6ekF0ruuiZTEchv/8R5jTJ1H8tnOuoL5eNN5YrcLCPBysxJDQ8dKGjoVmcwLXbfweNyrt7SL3UFh4bJpuTgQUFgrumWefhW98Ay67TLCKdw5HxJPvi/kF/+IiiljO49zMVNbjJIANjVtZSh/quZHlOAkymlIm8AlP8DPGaB/j9YpbrHuLynG77Q41N+N4QFXhL38BhwNPlgtZsTM5ugYdugwQ6lwkAmJI06eMIooVHYm5PMMk1nUpLffj4Xq9GK+s4nSKR7+pSWzvaCaOkx4B4rq+/vrBy6/kRb7Ba+jmVK0IVlJpJ41WDCRi2Ggjxk95mgUM5ALeooFsUsxQRj5VfMA5HCAPpwzDgiVcUrWcnHaNrMUyzPsMP7uiQgSFVVU86VareL9mjWhFPokyo3EB9uabou66ubnnuc9eOjq4PbTzdf7DACoZzD6cBAnjYBJRLuJfvM4l1NUpfP3rXy0LVVHgtNOEbfDBB+LW6F6yWMAebmEZM1iNYXqrfahnGLvwo9BGKufzBpk0MZTdBHEBkEc5i0PzKJdmMjo2D1ku7BVewi+Fz5qdfawR14RnnEFw5QaMYAyZMC91i/d37y6O5xKryUfFg5cW7uIhwji6TpDTW8hz+2i3KBQWiutcWXl0K8OTigBxXd1u6NtXnHCAPtRzO/+DDubcJw0vEeLPm0gOa6TQTjqNPMIdjGMrEWRayDC7jSMUcyMBSSFdV7m4cjmqxcOwWR7ktMP42fHsXGamiCNpmqCQjt+AhgFXXnnSST9FgYkThUAxjJ4TxnEryk4EPynoCMb9FFoBCQtRsoFFLGQOb/OUPI/XXy/kiitOutPxpaFpHYRncVJZNyp9qeFWlmFgEDNp0QsoR8dKDCtRbGTQzELux4KOFx/7GUQe1USRCUgKIwttZL6wlHnf/AXL/5FHZYtyfFpUjnR29rGEWcoVsSu8Lc2hiSYkoqw34/2dUUohC805EhFkbuVRVDzkUcUU1if4szRk9jM4MUFud6OXCSNE9eLYsUc/WZ9UBIgT7HKJGu2aGvFADaDCHDpjwWKOmgdRISQhaJIj2PHjYTi7eZvZtLEfAxHS+JjTkICylOnYQnD6EB+5LRpDZ3rM5rFDBPy6Wz/XXiu6VYJBoa0mThQUpdMPvulOVHSuOolGxWGEwx3CqzM6W1Fp+JCAZlLJwocOyOiE0AnhQsfG9bFi3rcswedTvlKKwOcT5c2DBgn645YWGBXrqFCZxkeEcJFFAwYSGlZks8QZSHi065nI+bxFAXuIYaOSfPSYzKebQmRaVzGytZUlaX1ovrIIz/TCY3+OT0QKFbOUK/BgMa5WDcOQ+SPXkYYPA7p4BZ3j/zaiZNCEgp/zeA8JAwOJdUxOkAQGcfGUXIQtTSElRYQAj4UDlFQEdJTo3XOPSGRqGihaO9nUJxKTkjk/V8NOABcKKiEcRJEpYySteCllFIWU4kHFQYSHuIt2XSE3F+57zMvIp2Rkrx84hJ/dk/Wzfz+8/DI89ZTYudTUE6Zz+EjQXa+NHi0EV3w0X0+Ix7jP4T2msJ502tGBKDKgYUfDSowmKZOJWXXkOn14vSfH+egteL1CoWZlCWoNe7SjQqUdDym0o6BSwQAGUIGDKH7c1NKXME4Gsp8AbvYzmFe5jPN4L+Ht7jMGMOvAv9FkA3l3OfJ4hZxXimF6x7D1Y3qgPUzAO95h0a1qAX9onM8aH9hjzYnOYBDMA/FqoPg1UVA5nY148eGlBQvgx0M9WeRSz2Ym8Cg3s51RBDWFVL8IAsRHgB9tByipCEwUFopqjHfegTSbyo+0P9OEl3wCWDGQgAgSUSxmc46BioelFHEB73IxrxFDxkqUHeZowEaycasqUwp9FBR4ked9BhXEoayfwkJ4/vmTrpi7u15raYGHHz5052V3XMLrbGY8/aghag67j2HDgk4po0lxRNCtMhde5U1EzU6SU/OloShw1lnw0kvCy8ruVKGSQhsNZJFFI3YiVNAfFYU2PBSwDwUVH15KKDQNG4WPmMIrfItv8C/OZA0YBnXuAvpb7VhLS4UGPx5W+AlIoRJYV0LjNcv5Wr3GLBmgjX0MREFlOms4g9WsYwr/4ULcBGkmg5msJICCjRhhbPTBRzV5BPCQQSMxrIneGAlRur55M8yZ0zVBf7REQFIRdILXCxMmwN5VPhRUWsnAQwA3QTPPL2ymWnLRzQay+7kHFRcONBrISnQOBlEYL4kZx4OqNIz5MtxVdHgqiMNZP0eZLvpooPM817Y2EQ5qbhYhIUnq4G7vCfHSu3KGUEk+6bTgIGwSeFiYwGa2hQ0Wty3kwK0KY8aI6pnjnUc8VlBV+O9/RQlyKAQ+raNCJYSTMA5qyOV9ZqFjwUGYhSwijVYA0hFW7AQ2MYodbGcEc3iXV63fJdUIUmDsxoEdyWEX9bmGcfys8BOJQkVV0R8XVn693UNmpJaxbGUvg5jMBgIoOAgxhY1M5yN0LDgpxEoMixleDqLQhISdCE6asKInSklBPBsejwibxjvmq6pED8nRypcny0c7wesVcddWyWtq7ygxbDSTQSsplDMIH+no2EihjVzqcBEghQDlDCaCnbeZTTup5FLDz4zltBseWlP6Y88wfTw4NBVE3Prpralhxxler1AAr78OK1YIwRUOd/QTHA7xfoLZvI2NKB78OAkTxcGbzGEFs2gxUvnYV0BDg+gGdziODVPjiQCfr0NgQEduxYOfHOrYyXC2Mwo3ARyEE4yjexjGHoaxkam8zPcYQxkG0J8qnAS5JPYqTXoqW6VxWGIR6soaCaoxUep1PO/DE4VCxefDYdGIOjxEo1AVzBQWPLXIaDgJkEUTbaQQQGErYylkK+k0M5TdWNFwEcKKzjbGsJUx3Mnv+JQxiZ/QdRE+DQbF66KL4MknxbXu378jXNSb93nSI+iEPXuEQGmLKfyeedxDM+dSg42oOUwmQhpt2AliYDWTyRI22vHgJ4yLFNoTcwlkNAKSh4kTwZ7ugcrDJLniGdWCghPH+ulFxG9um014Ap+lCOKwopOCHz8KNjT2MIQC9lJLP1wESZd8ROxi2Leun5rEcz0hniMYOlTct5p2MHmfG5UBVFDBAAIo5FGd6Cp2o3IHj5BOMxp20mjFTphNTOYFfsiVllfYYR2DhM7qQTdz++ApaNWn1C35xeD10hqQsQT9RCIeCEcooZBU2hhoFouAmEkeRTan7NnJoZY8aojgxADKGcJLXMXl/IPL+QeX8HqiyQ+Ep3f11YJb6sUXRZho1qyuYdbevM+TisCEqooB1LW1wtIqNQq5mj9zNiu4lWVMZT0xrDSTQj4qkunmxZCwIJFLDQ3kYiPKMuZRSx4xSSbL5UdRPiPJdaLVSfcS4oO8L7pIKNjKSqEALJbPVgTxfoIPmcF5vIOfFAZSgRuVHBpQeBMJGMouyqR+AAnSr5OoveILI+48Ll0qQmK6LqzHgKEc1K2aguCi6DwcPYST4exEQ04YLrkcQCbCWqaz3TOd0wp8RCWZ5l0atTeq2NKUo397nuDERioKyynia65icge2UF4p87z9Tr7V+EfeMmYznB30p4p8qniVy7ATIZU28qkmhAsJg/VMwU6E7/H/qCOnywjRO1hCUFJITYXVb6kMTPMh5XspK1NYs0Y8S5FI79/nSUVgwufrSMjEG3QCKHzALH7Ii9SSSyPZKPjJow4bBjoWrBjEsNBKBgtZxOtckoj1Pesq4la5mHR/C1gOkeQ6EeukewnxlIeqinmu8Z44t1tYNIdDBJls6hjJp/Q3R3xqWOlHFSCRSTPNeHnCciM3+J+lvM9UolHRXvFVQWGhGFizdi0sXgzvvy+8rc7U6RHsnM5GAN7gIuxEKKKY5dyAjoV6ssmmHgs6FnRe4PuCVbcNpJY9zG1fTqBVo/9WmbJziyhXCo/e7VlSAsuWiRsm3o5+ghlEPh/sTy3kzdlLsLT5qCr0Uv2OD4DdDKOOXDJoZDKbSMGPBYOoWaobxImOlclsoIxRaDgOGiHqxYfDq0BJCXPal6PYNTJyZGxjinixpJDycvFc9XbEuFcUgSRJFwDLEDOL/2QYxuJun98O/AQxArgBmGsYxn7zsxgQny1VYRjGpb2xT4dDT0ZHfOSc39+10cmLD82kP7YSMzswLYCOgRjFHsbBaqZ3UQJuVBr1DOTfLsJ1qXawhRPfiUDgxKuT7iXErdaHHhLnNTVV/D1cbNONyjTW8ANeYCxb6csBNGy4CGEhCkg00Ica8olYFdL1Jm7icf6QN5a2NoWXXxb0TKeIU/WZUBT42tdEGek3vylyMukBH/ZQRwWRYaYCnYRoJ5V0WgjipoL+nM7HZiGEzsdM4ANmiaY0vYZL9i6j2paO5vAw2Otn8oZiWuYsoUVTev/2rK+HX/1KlEvbbOIhXLRItKOfQM9BPO/1j40KoZBCQwNYguA22riQjRhYkNDZyhgWcB8j2M7D3AkYDKE8MbTqz3yfS3j9oBGiPrxYW1V+oC0n6vRQL3tob/Qzq6yYmilLuH2BQl7eCVg1JEmSFSgGZgNVwAZJkl4zDOPTTqt9AkwyDCMgSdINwEPAFeZnQcMwJnzZ/ThSHC4KY7OJ2t04twfEucJdbGMMYyklhVYMDNpIwW7WDetIvMxVCSUwlhLm2ZYjRzUmvybDmUVdR5B13gkQd9YJVifdW4gXfNx6q6h3Hz5ccA35/QeXkY6lhFtNWgQdC1Gs+ElBQaWBbJyEcOOnD43IxDgQyyFqc5CbJ4HPx+52hZkzRejpFHGqjgiq2tFruHkzNLZ5iXSqIJLM2dAhnHhpwU4EDRuteGkmnT40oWNhIJVcwj84hw/x4mM8m3k/OgtV8nDA72GIvYVYkw9ZVnr39iwpgd/+Fj78UDAJ9u8vOjy3bhUdnnHWtRMInTmALBYSnGJxxLDRShqX8Q/COAig0IqXFNrZwCTe51wqGNRlMl8xRSKXo1cTC2s48z2EW8EX9RANtnDLj3wMG3Z0bujeqBqaAuw2DKPcMIwI8BfgG51XMAxjhWEYAfPtR0B+L/zu50bnKEz37PvatVBaKhRBZ8SrMUK4+JQxlDGaGvpRxihKKKSMERwgj52MTAyguJVlhGQPtbb+lOz1oC3tlOLvvhPp6WJ5S8spUSnUE7Kz4cc/FmELm00cst0unvk44pS9GjbCOAjhIJ1WRC+3eDkIEcKFjRhptDCcXVRHswhb3DRGvdTWCrbu1asFTfNJwsn3pVBSIlhzFy8WYbcBAyBsO7iCaCfDGUUZs3kbxZx17CSMnxTKKeBTxhLCxb3cQwwLDWQRxcY01mCNRajZ5edAs0xj1Nu7t2f8eXC7hQFktXa095+AiOe9Zs4Utf4jR4qoQZvJj7WCWbzBRYRwczobsaGxljOwE8FBBCs6L/AjAiiJ5P7dLOIOc6SoxQIhh5eYJBNs9NOvHxRk+5kyQ2bUdO9RO67eCA31Ayo7va8Cph5m/R8D/+n03ilJ0kZE2GixYRj/6OlLkiRdB1wHMGDAgC+0o4fq16qpMRVCvYoz5MPdja+9czVGBJnHKWI4O0030GAz48mgmfksSQygeD84CyXTQ9ThIaK2IMd96ZqaDn6A+E6kpgpSkfjMylNICcQxfTrMmCHCb+vXi3xB52c93jdgIJFHDQYSVmKouEilHRdBItgxEDTKhjm1bBSl3NJyL3uCCg6HOK3BYMdwoVMZPTXsbdkibqF9BwpYwnwAasnDjcoS5vM2s/GRjpcWprIODRuNZCMTIYoVDyHOYhUxrNiIkkYrBfou2qyZ/D23iAd/qxz5IKUjQfyhzMkRr8ZGYTG0tZ2QtLLxvJfF0tEf02J08GO1k8pA9jKJDdjQmMBm1jOZt5hDBk1dZhAAiaH2ccRZeV/Vv833Qy+jtLRQOFHGfcfRNQ6PabJYkqQfAJOAczotHmgYRrUkSQXAe5IkbTUMY0/37xqG8STwJMCkSZMOMR768DhUv1YgAK0flrCwbTlWQ+vC1w4cNNDjPhZyK0tRUFFREsOnOw+gmMYadmdchEIEu2KGeuLJsM2boawMzjhDXFxZ5qgE/k4gKApcd53IF6iqCAt1ZsyM0/dOYgPV5JHLAXQs+EnhEe5gBms5nY3kUYsPL1FsOIgQwU5ZfTrtiFPs94uHacSIntlNTyV0N2ysViFDp7hKuFRejqFpGMDLXEkFA4lgx4fwQH2ks50RjGQHGTQRxsGnjOIC3qSdFCR0smjEhoaBwUuOa9nfVEhr6+eYqHckiD+UkYhg1F21SmjyKVPgjjtOuGcinvdatEg0RzY3Q0Tv4MfKpoFJbGA9k9nPYCLITGEDGzAI4mYp8wAOKuX14qPd4mWcaw8/iSzHLWv06QPjF19J+tenH/Xz0BuKoBro3+l9vrmsCyRJ+hrwa+AcwzASk2sNw6g2/5ZLkrQSmAgcpAh6A4fqVg82qlzRvJw2w3NQKVcBe7oMjSimiL0U8Ci3kEobOxmB3SzC6zyA4jxpBX1D5Ywcb1JLgDDf0tNFQfCaNaLLasYMUR1xgt3wvY2SEkGg5XB0NEJ1zsUEUPgbl3EO76Oa81u3MgaQeIXv8Seu5zJe4VFuQcLAgkE1ebgIksMBasmjpUVhxgwhqMLhUybNckh0N2xCIVEx9L3m5dTpHuwm5cGZJuWB6HfvSE7W0I8/MZfreAo/Ch5UIsgMZQ8yUTRs1NCXJjK5KvQsCxrGsmOH0rsh+84PpaYJBXDllcKFPEGfiYIC4cSff75Qvs891xE1GEkZN/Mo+xkMwH4GYwEeM3mECtjDI8xPyJO3mM0c3saOhssBrmAbTcpA6q0epp7uJ/2dV+DrR59gsjcUwQZgmCRJgxEK4HvAVZ1XkCRpIvBH4ALDMOo7LU8HAoZhhCVJ6gPMQCSSjxp66lZ/61kfNkM7qJSrgN3cySM0k0EduSj4WcAiHIQYQxkxLGxhPI9wR6K9X8WD7lTY12cGp//fL8gcZ1r61dUd5pvHIwqCy8tFSOgETIb1JjqHMHJzRUjo1VeFEItb7ZNZxw95ER2wobGeybTixYM/YTm9yrf5Jv9gFGWAhAsVGzrX8ScCuHgyWMSGDYWcc85XQrd2kaE7dohXYbYPvUZDjdmZYfLbGFgI4hINeLQkkpM7GMZifm02RkI1uVjRaSOFFPwYSKTiRyUVl97M4HQfr76qMGtWL5/bE4lCoht6qjCM555SUmDnzo57OIAiSONwo+Angp0MmtCwsZ1RQAcJXXwewf0s4G1mU08u/WO1TJW28o51GP+/vfMOc6O89v/nlTRqo9Vqe3XvZTEYF0zvCSGE3JvkXnx/CcEOSQgLgWBCTHMSEwJJ2BvamjRKbm4uJCGNJCRUU40bzRX3st5db5V2V30kvb8/3pG2YIMTG9u7O9/n2UfSaKR9ZzTznvec8z3fU1UFFRN80HJ0GISHbQiklCkhxDXAMyj66CNSyo1CiKXAWinlU8CPAB/wO6FaKWVpolOAnwohMqjE9d0D2EYfCQbK9hh6gJTQ0GXvailAJ9/ldqaziS4CrGE2QQqYw2r8dJNCI4PgJN7hG9zLQ1zF/+NxCgjitmtU3H09xfP6TPADl2/JpNp2nMVAPwoMDGFUVfV21WpogNms5FEWksaGgRM7KU7nNV7nNO7j+lwMNYrOr/k8d3IrXsIUEuQ1TmWXqeN+VaaeP1XWsXjxEV61HseoqYHLLoMvf1mdzx0dAVI2jUI6sOeKHu10UoRGirtZTAwvDpI8zcVE8NJBEUW0cxLr6CSfUtrRSAGSdorxi26SaFRMCQAf0bx0HGppHYxhGAionlG/+U1/KnTf3s838iNOYD0SWE8NY9hJkEK8xIjiRSOZy8OksSMEtKWKSEnwJTqYOrUCZ/LoMQiPSI5ASvk08PSAbUv6PD//IJ9bARxTtvfKlfDob3V22mv5ckpRuYppZQbriOEhQBcJnMxlJdsZR6FZkh/HbfYobsCBQQoHD3AtbY4qauYEmDtnwEV9HKooHi0MtIHptFpNTZ4MyWCEa8L1fSarJB5ibGc8P2AxzVTm4qkAF/IcOxjLabyBkyRn8yoRfOxiLOWyidSW7TgcM47p8R5NRCLw8MMqFNbeDum0zj3JWq7jXtxmH+IsayWbkkmiUcO7aCQReBnHDuykcROjkJSZI0jjJ4KfbtzEudd2I93bdM6qHPohN/jgOs9IBN57r7dxoJT9+w6A6lfyGqcRxYvERi31PM5lzGINaWwkcPMek0iZ4pVCgO5M8m68BrtM0fpmA8UpjaIlR2eOGNaVxatWwRVXqNhqq1bDktRSLuJplrAUP904MeigkEqasJOhnP14iKORwE08x8/OJom/yk+5z76YvXsD3H33AQojj2MX+KPEgWzgrbfCnXfCSH8IGVZFeRpJDJzk0U0cd46JlY2n/o7Pkkc3c1lDHDcOUthJcSH/IIULGxkmtv4nj15yJ597/DPDoqAsFFJGoLVVxavdbtiUquG6zP2cyXK+wK/RiVJEO3ZS3Me1jGE3OxlDCW2U0EqEPFLYSaDhIYnT7AbXSDlbmcyd3MZu2wScLapH8nC4bD+oH86rr6rnWSMwsJJ7BHuZyVsEzR7baew0UsGVPMxqZjOdjbhIMJO3uYNbOUe8ij/TQCqpcZdjCXMuLGOydy9/to3ku2NLj0oHiGFrCCIRJeva0qIMwfi4KmY6i5cpIEgKO6BojXYytFNExJSY1c0G4A5SdJPHSk7BSZLTeJ0ybqHE5mZV/Frq6+e8v6jpOHSBjwYG2sBQCJ59Foo9Aez/62VTZBpT2UgePdjJ8HOuZIHJxMqG6+bzODoR7KSIohMhg59udGJ04WQ7Kh502cbbufVrZ/C/z5QO+VMdCCgPK0uVTaXU5DSWHXyKv5I0aY2FdFJKK5U0kzElkMN4qaAFNwmieGijjHxCNFGVo0NG7AW4ivMJSHWfjBjxgcMZMjgYw1DT4OmnFX00y3rLN6nPOhHO5iVcJKiimQROWqjCS5gpbGEts9jJOJqowk2cItp5lbP5i/y0qa0V4NSSHSzcvQRNGnTFNMJv1KKf/9GvaIatDHVTk0r0OBzglb3FTBFF+MSGRCNJgE48xMhgRyPFfioBQRwXaWys5WRCFHAWL2EnxYjEdir2v81//ePzzF33U8Kvvzs8dJEPAX2VhLPtQVMund+V1pJxeXiPqbzDiVzBo+xkfD8mVgQfAvgfvoAAdHoAaKGENA62MokIPpLCg5s44Te3sH37MTvUowZdh2uvVd6Aw6E8Ao/sXaHuZiwRPJzMm6TM5UsSJ1U00U4pQQLsYQTNVBDDSytl5vmNUE0jhZk2bgstoia2irw8xZsfDpfzwRThs4nhrKcAivosgXmsIGW2sYrhophOimnBTpr3mEQauykl4SSDjRjeHBGixV6F3Q6XR5aR1Hy0e0ZguHwUPn50dNWHrUcAyqoXF0MspCx6C2UYaOynnGr2oWEQQ6eFUqL4GMleALrw00glOmHGsYux7KaYdtLYiKIT7slQKXbx+ZXXYP+sF+bOgf/+7+EhfnOI6KtDtNlRw+7qOrr3hmg1ernVEiijmU6KTFkEjWe5iLu4iVu4CydxXGYHKDtpdMKMlntwYHBF6hek3g7AjKF/zgsLVUOltWuVR1DUp1sZqEYowqzOlthwYIApmthCBQZ28unGgWHWvwrKaKEbP0V0UJ5s4YHkAr6Weoy77ppDUZEyPnPmHMuj/ugx0IsFtYDMKsI4nYrzEUXnceZzLi9STSMCiTA76tnJ4CSJA4M/cCmf5O851tYjLCBACKcGVRN1CqIhHO0GLREfbjfMPtWHlhwkrKHBispKxQV++21wpnorA9cwm9N5lQg6aWy8wPmk0JjNGmK48NNDGxVkcPAKZ3MGr/AWMzmBDZSzn3L246cbZAaby4XN7YK33lI9Gh96aFiGhQ6G7I1WWwuvv67TbPSem7HswE93P+bFPdxIBU3MZTX7GJHjuneRRxGdlNNCGgfLHRcS9ZYwZXk9fG5oCw5lQ5zBIFRUKJZyiN5uZRF82EgTIoCLJF3kUUobSZxopNjANKayGQcG+YQQCJwYCDK4iRGSATptRRTKdq6zPcD1q3+CXqpzxRWqLmTuB2kIDAFkI7lZBlFLC7z5pipC7StOuZ4TSOBiH3lE8TGJzehEsZGmmv2MYi9j2clGprGMWlI4uJYHARtO3cNf7bVs18dS5NA4aW4YX5lPsYbkIGINDTZEIqpr1saNKr6a1RO6nnuppAknSbYwiRE0oGHQRDWvcxoltCCx0UMePeRRzn4EmO53Hp/mT3jNHz9jc2Kz2UjZHNiMFLaszvUQnpT+Fezfryax1tbebVndob2MYjsTKKSDUlqpZRlFtHM6r7Gb0XRQgmbGv2/kHr7Mw+x1TUToOuedB17H0FBx/SA0NSlttvx8aGtTh9oe6610HcsOJrOFnYxmJI3sZAyrmcsrnM4ZvMZcVmPgIIaOhzgeYnSZdQQCSRmtJKSXuHSTMGzku0Lo+TrhMDz4IEyfPnRPb2trr1TJz3+uwkENDUrptadHeQMipiijHqJsZgojacBPNxI7exkBCAyTnxUmj3Hs5FruYxLbcHkcRFJuthrTuHhPPX87p44Rn6+l8Ll6VT9wFJmFw84QZFUeXnhB/ZDZhI9AYsdgPFuJ4WUH42mikjmswYlBGjv3cgMxPNzOUs7iZWxkcJBiJHtopYwXOJe5rKHM1o6WiZFKgGwLYSNNtEsSGA68u38C2dXsvn2KgZFFBU0ECNFJIQZOOiniYzxLDDcgcBNnBPvowY+dNBop2iihmQo0u6SgBAq0/hzs47zfyWEjlVIrVE1T53KXHMsyvsbN3M1bnMRUswByDDv5HrfxGmfxCudwB7fTRgln8gppHNjJkEYjhhsvMZwk0EWMtfIk4oaHsCOAJ9NbIT5U7eyTT8JNN6nqdymVETj1VJUj8PtVTmZcTFFGvcTQSOIkwTbGE0ZnLqvx0UMhQVzEyeDAZvY9n8F6ErhpjBdToCf5eNVGkhOmMfeGEGUza+DjR59ZOKwMQSSijEAioRKVWdcuuwKN4yGMnxgeZrOGZ7mQ7XTiJEEEnYU8wiMsoAc/r3MaMbyMYQcX8zTtFGHg5E7P96hwd3Bz6GacmQTYbHR7y9nV4GZKZGjeNP8q+q5mdV21spzOOr7OfczgHSazmTc4FY0kBQRpZRJJnJTSgo8wlTQSIEQEnat5iD9xKZ9MPoe9Kcjr+2H87fMpbYKGThXGGGIN4AAV4qypUbz2LGNotnsdV6WX4UqGmMlbOMz8CQg0knyTH/EWs2imkhABMtgw0AjjpYgOCuhEYmM1J1Mp2lmXmU5ceHhI1JLx6KTTMG2auof6rW2GiLVtbYXbblOrfr9fHdb+/YrlJoS6jkRMzRk+uqlhAwE6qKCVBC7SONhDNcV04CKBnQxduKmkiU4KMHAQxYtdJglGnOQ1drMnluGJnweQXqit1ampObrnb1gZghUrlESxy6VifS6X0rfKKl+2UEbapI1qGIxmJxPYxrN8jBAF6IS5lgfJJ0Sl2ay6kiY6KGQ55xLDw6zYKzyT/ARNshyHQ+DyaTSPOY1YOEP33hB66eC9QT5KOBzgt0e4Or2MEAW8xDnMYwXn8QJbmEAXedhJYcdOC6VoGHiIARDBy0m8TSGdXJt6gJPkdv7TeIKt33mc1mVP8qCspeCMGsaMGVIN4AB1DEuWqJaVjY3QvD3C15PLiLt9tNoLycTeoYo9dFBMBhsgmchWKmhiBxNyIaQmKhjHDhopw0eMTgKU0MlN8vtsYAbtjkoMp84p45Xx8XgGRC2GULvVvXtVtMBuV4vG7m5lYCOR3sVjJSEqaWQeKxFI8gmRMplArRQzmr00UUkCF1Xsw0eUOJLdnESYPKJ4mc5GvPRgxDP8VLuW0dU6yeSxuT6HjSGIROCJJ9Tkn6Uxbtliureyf7L4XF6gjFZ89GAjRQGdRNCJ4ENjD9PZaNK+vOZF0E03fmLCx1i5lQXph4njIZrJw5WAsr2r2V08C//IwLE+DccVsqvZDRvUjZef6WW7RPCxhtmcw3J89FBAJ0V04iBNHCdd+BDY2MYEHKSppoFR7OFBriETttFEJWFHEd2dSS5L13P/W3XYbDrFxUOvwX22ZWUoBK72EInFBiv3+WjdCm9zEuPYiYsESZzspxwXOc3HfmJpN/Df7KecNHbKaOEUVvI5nuRjPM9DqVq6KmsoLobbbx8gljvE2q2OHKkYQR0d6tCycul9k8NJNKayGRtpDJwIJA6zdjuBBwFIbETwsZlplNLCZqbwFX5OGS3UUs9GpmKXksfc19DomEN5XHkgx6JB4bAxBFmhqNmzlR6+zaaSPk1NvcniWurxECWDjWe5gAheLuGvXMzf2MNo9lLFVLbgwGAEDXRSiEQQxI+NDCPlLuawFkGGFE78dJFJORHJBJU3zLe8gQHIrmbvusvkajsCZNIaekYJds1mDRkENWwijQMvYcJ4MXDyFidzFq9iI00lTdjI4CLJCbxDGW3sYjSRlJ93wrNJZgz2vxdiyz4dmw1OPnnoySTk6hQDARilcU5lmGDQR1tjKfuoJIGbJC5AMbCa6dW4yoqldePPhYlO4F2ieNjFWNwkqRX1/MRVh9Op4/UOmKQ+qAx3sBmCSIRSI8R3vhngyuv0fpN/X5zAuzgw0IkiUT230mYWwG7qB73DCUxgBy7ipHHwfW6hnVLaKc31N8mrDtAW1ZFmZfixalA4bArKAgGlHb5ihbLshqEsv82mcgRBs/n8A3ydNcxlOxOoYSP7qEZiQyfMWbzGm5xEK2XspZo4Ll7gHFK4KGc/s00d8m4RIOX2ktGc7K+eScEnT2Ps//vopWQHI2pq4LvfVarDabfO/RnVWWssO3ETQ5o3V4Q8U+zbzX7K2ctouvBTTAceYvgIE8GLkxQSG4V0kgFOTb2MzBgEZQCHuezZunUIFkVFIio2BFBbizsVRg824CLBIup4ndPYxBTWMos7WIKXCDNZSzGKrpVdDGXPvYsEb3AqBk568GHPGIwvDiHlARr+9C3DhcHbbtVs92bcsoRzn17ElXPXM3q0Clva+syUXiJcxhOECLCVCYTJM1uCSpJoeInxfW6iiwI2MY13OIkreIxNTKeSRrxEiJpS6w2dOqmUmo82bDh2DQqHjUewYYPq3hQKqR+1sFA91sh1fLVPv4FHWEgUT069MWFOPG9xEqfyBs1UEaKQ2azBQwQDFzeXPkqwx05t+n5anGPJZPyclF5DwBGhYmoS7803Db6V0VFEZaUyyjt2wPZkDd9M1FFOE9/ldmawnhQadnOCF2TIYKOITtI4kGRMjSI7+6imgmZ6yEMjwTh2YiNNEWMZmd7J1u4adF0tCJ5+WulMDQmY8XkjZpDIaNiureWlT9Zx229C7DcrV5/j47nmSh/j7/yWz+EiSQInt3Anf+YzuTBRBU18i7uJmCo3OmFSQuO1DQFmFSkvrl8KYCgIKprhrbaYj1UbfdiiYeY21bNuUh2NjTpC9IaGKmhCJ8LbnMhM3mY/5XiI8Sif53RWYOBiEtv5GV+hiWpCBN7XhyDb+MrhUCr0iYQiTSxdeoQb/xwihOzbJmqQYNasWXLt2rWHvH8kAlddpYrHCgpUMUg0CrZYhOsaFtGV6dWz8RHmERbwFX7GebxIHt20UWIW6ET4K5fkWv1lRdHaKaXYE+EB29eZc5oDR0kR7nSEAtmJdn/dsfllBxmefx6uuUatjHbtUsm503mJX/AVbKTIp4eo2bZyBacwhj1sZRwjaaSAdirZTyNV5BGmlULK6KCJctJovMKZ+AhzN4vZTyVJTWf0aPjVr4ZAQVQkAosW5SYwRzyMKxWmrqKOf7yqv6/1bzGtvMEp5NFDBjs20vSQxzxW0o66Tr1EmMsb/BePA2pef0r8G8myEcw7z0vYX0lnQn9/CmAws4YaGzFuWcIzG0fkKoZjWxu4XS6lIVNF1Oy4Ph2lSXYuL5BHj5mEF3QQoIom/ISR2AiaHeC+xCNE0bmHRf10s3yEuZE6tHydkSNVf6pkUhmCqqqP7jCFEG9KKWcN3D4sPIKsF+B2q8SP16smmxOKQowdYfBGgw8yvQ1pmqjmFu7iYRYymj2kcCDIsJ1x+AgTIIgNyQNck7t5KmM78Li6yby4HocH9hbXEPrREiZaRuCQkO1pnEio36igYR3/lXki105xNbPppIif8yWi+PgGdUxiG3Hc7GWsKecLq5jFRLYTRieJmzXMxmUKAi7ldroI8FRZLftcNUOjICoUwogZrNrow+kEu8eHaAqyb0OITOb9BzaRLRTRQQ/+nCEopp1TeY3n+Vi/jnwSWMlcPpX5O3XpWor2BTF+X0BT9Rx+O2kJoVDN0BFUDARIZDQc8TB2j49gQxifR8OVFyDfXDh6iXAD9+AkSRwXOhFK2Y/ERjUNaKRyculV7KOUFu7jOn7Bl96nm1VAkAAh3EU6F16ohiDlsYumDYscQVbgbNo0ZXXb2tRkM/rEAHmFGrOnhLHbMAWhNEIEcGLQShl/4RKWcw5PczHtFLOOaXjM2PVCHmUa65UMrVjGjuQonsz8OxtLziKt+3nw6bFDLxb9EUHXlWx3JKJ6FFwtlGja25zM37mITopYRB2vcTbvMYUMDlwkMHDiJkYMH2uYxXe4gwt5llc5k9c5jSAFzGMFCVzsYiwx4WNhrJ58RyRXEDWo0WcCSyahaWuYlqDGrmAAm61/bBugGz8S0EggyOAijps4X+B/uJevcxt3kMBFF/kkcLGI/2Zaeh0ltKJh4Iu0UNb4FhduvpeANoQubl3Hdm0trlQYe1MDrlSY35bU0tSlU1io8gTz+TWX8hQX8Qxj2EM7ASR2GqkkjUqc+OnBZ9ZspHAQwct/8TgSNb/YBPhFGGnXiLsCjBmjomnHKjeQxbDwCPqGMKdNU0yhcBhWb9SJUcsXI/VUySAJM3aX7YiVpZT24OdkVnEGr/Ep/kIKOy9zFlHcXM+9/IDFuIRBu82HlLCtp4I5vga0SIhQSB+0i6SjjbFjVe7mkjNC+F8yaIyoFVSIAgoIMZK9RNGJovMA1/AYC6hknynh6+ME1mEjzV7G8ENuopZ6ymjBSYKXOAcDJ4Z0IhNBThwdIuXVB10+833ITmCX1xPdGcSnaTxeVotM6djiape+zBcPcSJ4KaEDTJJjE+VsYSqFdDCLtYQIIAAbafLoxkcEG2AnjS2TIdCzjxOm7kU3QnBU1PKPDra7a/jphDp2vxNijxHAE1X3bnMzFKVbuYH/NgkLTpwkGEsDEbzE8eaa/riII1FzRyeFBCmgkCCPM5/P8SRFqBzK70pqKfHp/Pzniqp6rKNpw8IQQK/A2Ysvwje/qcJEbW3wZn4Nm+x1EAixMxjo1xYxSymdxjucx0tAxuQKCy7hr+xgLBkcTOA9Mg4NbypM0unDK8NEDA1DDwz+ieYoIrs6L58cIPOaho8wYXyMYhezWMO13E8ML4+wgCaquZ46fsZXsZPGTw9d2PgWd/NF/vd9ic8oOjYBHhmmO67x+sYAt31+8EYy+sI7pwb5ozruvT6EoQeI23VGjFDeVWtrr3Sylwjf4m6SuIniwUEaSYbnUbEJCRTQSTd5dFGIn0789JiUSAOkIIPAZgd/264D0IcGL7JyJ1v36lCo49HUts5OZUhPlHuxk2Evo6ikiThu/HSTND3STgoJ0IkO2MlgN0kNF/AcW5nIKuaxinkU20J0ZQLIHp1lP4AxY471kSsckdCQEOLjQogtQojtQojFB3jfJYT4jfn+KiHE6D7v3Wxu3yKE+NiRGM8H4be/VW5edbVagbrdMHqajmNUVc4IZLGLsTzHeUxnEw7SaEhzpSSxISmigxQan+FP/N6/kPK8MGO1BlxGmBcm1fLl6y1v4J9BloW4v0fnMa+iMo5hF3NMWu5uxuImxmMs4PvcwgL+Bwk0U46Bhp8ezud5LuN/cxS9HUzgPq5HJ0y1bCBgC/OH8lpmnqHz3HNDh0Y691ydCWdXccI8nYsuglmzVMy5LxfkbF7gfJ6nnP24SJq5LxuFdHAhz3IOL+dkk0tppppmwug4SJnfIJHCRlx4MCZM6bUwQwBZuRNdV4SSkhKVF3A41Ip9LyNJmcvALvJNmXRBCojiIYONPYzlT3yK3YyiBx8Gzn7/I4rOPllF2q080bKyY3GkB8ZhewRCCDtQD1wA7APWCCGeGtCE/ktAUEo5XghxGfAD4D+FEFOBy4BpQCXwvBBiopRyANfhyKBv0jiZVHmCpiYVo+vqAp+I4JehHN3rOu7jbJYToLvf92TvLTsZNmknojuhzVnF306vo8wV4uL/F+BT51pG4F/BZz+revCujNSw0l7HhPRmruF+9jAGjSTT2UgaG+0U4aeLAkL4iJDBjk43Lgx+zA1cwt+4jTvZSE3OOwgQIuUJUJKvM7Vg8NY8HQjZHEt9vZJPcThgxgwlmdzUpLyBL/I/Zl8HJ9LsUiYRnMybRPARw0MTFWTM5ioNjCCDjdcYxYU8RyfFZJxeWspP4MRiP9oQdndTpu1zOMAej5BPFw9wNTdwLyPZSwY7e6nCTw+T2EIHxWxiMq2UM51NNFHJa5xOkELKaCFAiCiqQC0eVzpG9fWKJHE8XH9HIjQ0B9gupdwJIIR4ArgU6GsILgW+Yz5/EnhQCCHM7U9IKRPALiHEdvP73jgC43of+iaN162DPXvUdo8HRnWt44ssw26yJfx0A5IAXWYjj/4wsNFIFT1aIT4tQcwVIGbT+c8b9CHfsOOjQF+pGlC/UUeHztbtU4hlvCrRRgYXCbNjtJs8unGQykl/Z91bL3HOZjnf41ZupI5mKnO5BXscfDF47jmYOHHw1Tx9EPo2UolG4e67FT32j39UeloAMdxopBAI7KRJY8dOmozZbS+FxgU8i0ASNFlXrZThxgCHRsbpw+/0YLt2kNUJfAiycifZYsNIRLELqzvXcVPqjlxfjH1mQ6oGqhlFA0mcakHIVGbyDjsZZXZ/K2I2a9nANOJ4cmwiULI2VVWwebMy0hMmHLPDzuFIhIaqgIY+r/eZ2w64j5QyBXQBRYf4WQCEEF8RQqwVQqxta2v7lwaaTRp7PDB+vEpMfvzjUOiKsCC+jLD0sY8RpHAwg3eZxDYMHHSTT8ZsVZ9BEMVDHJ1G1zj87gR/rKjFVahTXQ2PPDJ0wg1HC32lakaMUGUXoRDMnKluxt/xWQIEzQbsaTYwDY0kF/E0LpI4yGCHXKPwNDbcJDiXF/kh3+QeFjGN9YCK9waDSmxwKCKro1VZqcJsBQUqtBEiQDf5tFBGBJ04LgQZktjxEqeMFk5lBUmcvM5prGYur3MarZThI0wTlVyZeoi78r6P/2d1eOcMTkG5gyErdzJunFIa3bULIq0Rvpa6j4lsNRO/hZTQgc/0AgJ0UUAQOyl2MI63OZEUTl7kbHrIw0WcOazhERbkuu5V0UiFP4LT+eFjOpoYNMliKeXPgJ+BKij7V78nu2ravl2tmAIB8GdCOIVB2OT5dlKE3Vx97mME1TTQQx6CNOs5gQZG8jOuoitvAjFXgDyvzuzZ6qZraBg64YajhYFSNQUFMGkSlDSv43vxZWB6ZP/D5dRzDTfyI+bza6rYTxqBgQNnzmuTpNFwE0cgGc92usinlnpupI4YSivH7VYLgqH6W2UXPUuWKA2bKDr3cr3Z9e1dXMRxEmcPY0mhUU0DVTRSSivf5xYAaqmnmgYMNJZRS8hRijYaps4+tsd2pDCw/q2sTCWHOzvV+/mE8NOFgxQSlRv00Y2XBIK0yblSi4/zeIEOCilnPzF0JIK3OAmBjSaqmc46almmur/1aDzVVYvjpBoqKw86vKOKI2EIGoERfV5Xm9sOtM8+IYQDyAc6DvGzRxw7dqiukfE4vPQSVBUEiKdVa78wPpwkeZcaprIZFwmaqGI7Y4ni5U5up91RifDpXHqx0i6aM0etYgerxMqxRl+pmqx45YjCCN9xLuPvxT627/fhJczneJIlLCWGBwPNFPmym7ITApvZk1cjSQZBDzox3ExnI5uYRoAQMXT271fSwpWVQ/u3ytJxzzsP/vEP2JSuYYF8jGrRRLXcRT3XEEMniZPdjKaYdu5iMRtRq/3v+upwhEN0iQCeYp0CFNPueAlnHA4GhiLnzoW//x1WrerND1Sxj+lsoIImxrKTGBoBIqQQdFJKgE40JGls+OjBTxfd5BPDA8AM1rGWWSTRuJplxGw+gg4fY0rDfN1RT8mNdejHySrkSISG1gAThBBjhBBOVPL3qQH7PAV80Xz+WeBFqbQtngIuM1lFY4AJwOojMKaDom8YYsYMuOAC8FfovHZCLXkiTDUN+AjzHZbyRX7JO5zIeqbTSTF1fJMdTCBm0znnHBg9WsWye3pM9cxjXBQyWJFdvYbD6jwGgzBnYoiNbxuIPB8OB6YEuMFI9uIiSZh8DDQEaTTS2M0Uvo0UKWwY2AEb1TThJ4ggQ4gAHhmhLN2IiEbYvFnRiQeG8rL6bYM9xJel4558Mlx4oUp8xoTOVjmBlZzGu8zAQwQ/XbiJ8xYz2cn43Of1Up399ioiZpKzouL9BWqDEX3nAKdTTf6LFiljGTdrL7xEWMCjvMnJSOwIJLpZI+AwpecdgCSDlygBQpTTQjtFOEniIYabBI8zH49NVR/0SNWUfuYZPk6fazC9OnQMz0J/HLZHIKVMCSGuAZ4B7MAjUsqNQoilwFop5VPAw8CvzGRwJ8pYYO73W1RiOQXUflSMoSwOFIYIhSA0qobv7KzD1hMyew2o2fxrTM+JdUVRMsZnngknnKAmrrIypQ9iGMe+KGQwIxuyW7FCaQDVPRzg5g6NosowrbqPdJeq+t7LSCLopLHRQDVj2QVABugiD4nAR5SdjMZPBCdJSojxc67sJ5/g8WosC9Zy89fH8rG5IRZ8I8D0ufpQ6q+S87R27VIG1uVSq123G6JxnTtYwvXci06EiBk6igkdpDIaxcXQ3q4mxyzVsaaG4yac8a8iOwc4nSoiYLOpY8x6AtDbrEopDY8kgYt8OhlFAxJMAUS1AOkgjzge3CQ5gfX8ii/gJo5GilXMgwykUHUxFRU+dm8MM2bW8RU6OCI5Ainl08DTA7Yt6fM8DnzuIJ+9E7jzSIzjUHCgMITHAwsXwuff0mkM6/2411m2SRaTJ6ubateu3i5NlpzQkcPvf6/OK7rOU55aLt5dT1EsSASNB6mlnVLu5XpuZykzeYs4LlzEMXChkcFG2gwZOWijBIFkN6NoppJF1BHGRxQfgViYb4qlpEJ+yt+BzgUaHctqWfZEzVDpr4Kuq+v6iisUUyUrpxyPq9cbZQ3XcT+FIkTSG0B6dfISUKpHEF0hupsD5OfrnHQSlJf3UlQH47noi+wc0NGhvPn29v5GAFTjGSdJ89rSEGSI46WNUkpoI2lScN3ETM0myU7GUEUjY9hNO8X8H/MBNYc87Kplkaee8a4gPQmNzvm1lB1HJ3LQJIuPFA6mmFtTAz/+sbpxHA51o3R18T71xu3bVbHJRRfBJZcM/pvieEJ2pVZWphKc25w13GSvw+cOsS8VICzVyd5IDQt5jLFs5w5u42M8A2CW+6mk3lpmEkfHMBuyA/2Ev8IpJ5NZz+uRs3B6K3Amw6QfqEfodfjK1f8ZzP1VsqiqUsVlxcWKDfP736trWqhTRVTqxNDRBVQXwdTUOq5zLiPuMEjbNJZPqaWjsob5848fzvu/goGJ4dpa+NGPVM2Fzabu+awxmI5qSq8T5mTepIlyKtnPNsahkeI1TqWHfBwk+Tf+xH7K6KIANzGaqeB/+H9cxDP8F4/zOZ6knlrezdTw5zPqmFIRoj0VYM684+tEDoGI3z+PbBhi6VL1mHX9L7oIzj9fXSxZfZbsDQNqchJCXVRPP/2+r7VwmMiu1JJJ1Umupwe60zpGqarG7IsoOhuYwduchJ0MHuL4CJNB8B4TOYU1nM1LnMNLPMMFNFNpSomr5imFdJABOjJF7NwJYXzkuQzyZWjQ91fpi0BAUXBtNlU3cfrp6hrOXstutzrGoiLobo7wpeQyosJHyDcCT7GPz7XVU+aL8OSTx/pI/nWY/Wa4+WYlR79qlUqkf/nL6jobMUKFzYRQuYGrUYKH65nBc1xAM1V8gr9Ry0+4gsfoogA7aZK4+Q5LcJChjBZ0oixlCRfwIiEK2McIwvi4VtRT5I6wZpPOnlTVcak4MOw8giwOpJir67B4MVx+uVr122xqhRqL9ZbqZ1tcJpODe6V4PKKvt2YYaiU7dqxqWvPSS7B7d3/+fzGt/Ce/JUSANDYcpLGRxk2S5zifBG7spPkYz/EcH89pRxUQBFTLRpFOEupyYouFaSjT+Pz3Azz46ODtrzIQ2XN6772wb58iOHz726p6OxhUhuDMM2HUKEjsDDFbGthG+njtNcDnw94VpMgeosXQB+X1nk0M9/QoCYl0GubPV0QRv1+RAiZPViyytjbIj4T6eY5ZwcNiOniPKTRRlWOgZfOGj/N5RrKXvYzEicH5vNBPcrqIIGMLQ1SepLN48fHJuBq2huBgqKpSdNDiYnVxvPoq7NypDEC2WMduV88H80rxeEXf6thAQJ37pUvV6tww1Kota5RHooTA9jCaSpowsOElSSNVuT4RANU0ECDUT2oiRIAx7KSWekppQyQzLHjlWm5s0vv9/8E28R0IA3tP/fu/q8XOjTeqMFyW+mwvChBAQ9rC2O0qSZK2a3SkA4PWMwqF1GS/cqV6bberqustW+DTn1bG8LVnIrjjIWwECBHIeY6RAwgeZjuL9c0bZvsQg/Io+n5eJ0xaaHTbAkz2H7+J9mEZGuqLgVTBvq50dbWqPD7vPDjrLOUJpFLKxR4KSbPjFVmDq+vKI/D7Fc23vLz/pNZXCGwH42ihlGYqaGBkLgTUt8cEkOsVG0VnIzU8yhW5OoTPpx7hjv9YzxNP9P7/wY7sirigQK18CwqUx1VaCt/5jgqBZqnPX75eR7u+FmcizKkjGrBFw/xlRC2dCX3QekaaBu+9p64bXVePyaQyCD09oG1ex52JRXwvczMPZq5iKhtyvZsHCh6G8VFLPV7ezyv2EqHSLIHKfr6aBvwizB8qazGcOvPnH7/ncFh7BAejCg5MJv/oR2pCampSn6usPH5/0KGGLBfe61WTlculupiBWondyh3cye3k000aGz/iRtZzIgt5hAKCuf6wAJU09qMGK674Y6bsglq9fTlVz63X1zFunM7ZZ5uDGMQtGAfSpfsmwAd6X+rQ1MbCUIiTtQDjDH0wHnYOXV0q7BUMqp9RCHVPp9PQsz/CRbuXYU/HmMImXCR4jAVcxUPUsYgy9iOR7EFpRWc7i1XQRAxv7lrKJpf79iO+kToq3CH0qgATTtQ5LV8l249XDFtD0LeoZCBV8MA3yPEZ2xvqyCaQo1F1ExuG8tayyfw/8xle5wzO5QUu4h+cyipm81auZ8EHNQ7PcsUHthD0pUL8+MdKNkTfMbgLCw5El+4b5jlgd0lzo87gbjuzbh3cd5/KjXg8KtRrs6nrqKQEtq0JcWGqi6lsJIGTMD6KaeEXfJmVzMPAgYdYvzBPHt0s5m5ANZ95hIUs5JFcP2IfYWqp51u2OtqcVWQysGkTPPro8W1Mh21o6EArJcPoXYH2DU9YOHbIJjuzz2025db3RRSds3mZNkpyTI2FPJoLB32d+wBJC2X93Pu+8WDoDSPtjwdYswZ+/bMI0bo+ang+n1otDKKS44FV28Ol+r1vSOz009VCwmZT3vwnP6lCYyPEPmbxJqPZzTQ2M5HNVNOMjRQRPDhJmCGffYxnC1U04iBNsC8jiAfwEO2lJePDiUGRPYTdrjyS0aNVmPl4xrD1CD5spWTh+EFNDdx/PyxfDjfcoGK8zc3KIMTjEJAHXtkHCDGZzZzG68TxkMbOGmajYRAgRBNV/ZhEWW8h5dJpaYEf3RqiwGEw7eM+pk4FfD6MtiDtm0P4pxx/FMCD4WAe7lBGVorb61XeQGWlum7mzVOhxdXLIyze/zM2MokR7CGDDQ8J4jgppY3/4HfYSeElxjbG4cJgJ2MYSUMulBjBh6QNG5l+XkMSjR57AJ9PjWH79uO/mduwNQQHKywbDjfJYISuq5VcSYmiQq5YoVZbNhvEUwGMRH+mhoFGEo35PE4CFzE82EhzFi+zmlk5b2EgkyiKDgmVP3CmosRS8OrflTRAKhRmwyqNxyIBHPmKMDBYokQHDAENYezbB2vXqsWCYaiFg5SqoC6RgFNjb3Aqr5PGQRw3abM6WAIuosTw4CGKjRST2UKQAkaY19Q8VvA0F+MkSRQPj7CAhTxKIUGSaDyEmkiyFdyTJh3/zdyGrSGA4blSGuyYOxd+8Qv49a/hhz9UlaEhQ3/fyv4RFjKSvbiJsY4ZzGY1JbTjwKCIsYxhJxupwUuEACGSaLnmLVlNIpdh4BXduI1u1vzBT0JqPOatZecOJcK2dCk89ph13RxviERUTH72bJUnaGxURiCdNiVlZITLeJwUDgw0EjixI9lHOY2Ucy6v4CKOm3hO1VYgKaGNZ7iAmbzNWHYSIpDLN21iOoUihCgI0NytU+FVc8r06Yr1drxHGoa1IYDht1IaKnjrLbj4YlVk9te/9l/ZV9HAQh6hkkbO4FVC+MkjQjtFRPGxk3HUUs+jLGABj1JGC5PYwntMopNC/HSzl1G04EOXYQoI8seyxSzfUkl1uU6+T4UZ1q8fGpLMQw3Z/N+YMWoSNgz1e+3erVboARmihFZcJKmkGZvZzqiBalopJUgexXQiALvpJXiIEcNLDA+vcxo/YHGu8x2oPFVc6ARQKq1OZ68RGAyRhmFvCCwMPmRv9PJyNRFnawuyN+Vt3EECF+PYgURQSQsANtL8njMJUcBodnIND9JJISNoIIKXkTTQSQEn8i4tlJPESQQfhQR5e4uXjrhOareKN3s8x+bYLXw4+ub/XC6VR+rq6r1OxrGNM3iNNHaSaHRRhAAW8wO68XMxf8cGucYzAHZSRHEhENzL9ezg/dY/W6xWUqK6691wA0yZcvwbAbAMgYVBiOyNHgzCxo39i8yylNAkGmW0EsFHCg0bKWxIYnjM/seqiU22Z283+fjpwkOMElq5gOcI48v1nG2MBHC4FAWxu1vd3LNnH7+VosMZ2fzft78NL7/c23EMVO7nSh6mjUJ8xLCTooggKziFTooZzU6cJIjiwYZEI4ENSRKN9czgp3w117hnIGw2yMtTz+32wWMEYBjTRy0MXmRv9M5OterrKwyYpYR6iQJgJ00KB01UYUNSyX58hHmAa4jiwUUcO2ny6EaQ4STeppVionhxkTB7zi4kLHUSCVW/kMko4zNQusHC0cNARYDWVpUcbm3tfX/z2gjuzka8RHLXSIAQdtLE0NlHJbsZTQcFRPGRRMNNDIkggk7KbG4kgWf4OJuYxkIeOWBlcVb6JJlUr6+9dvAYAbA8AguDFNlE/5e/rDyDVErdhNGMShxfx710k4efbtooASQrmMdSbmMn44miM5WNLOF7aBjk00UEDx7iNFLNu9Rg4EKnh2aqsNuVAXA41A0/apTi5Vs5gqOPgYoAEyYoEb1USv0+t90Grzy4jhualiGyRYRSJXWr2MdJvIWbOPmEsJEBBNU08HO+hIGbMB78RM3MgY1GRrCVyRg4c7TkvlpDDoe6NpxOOOUU+O53lV7ZYIJlCCwMWpSWwi23qKRtMKhuyHBYJY6v537m8gaX8ytKaWU0u4jj5moeop5aaniXH7MI1WxQ0EUecdy0UYKNDJ/kaVooxYakgkYa01WAoh4KoRoTFRQc2+MfjhjYZnLfPrjjjl5NqmAQFl8b4fauZXSlfYRNOnEt9SxhKYu4BxsZ8ujBS4wUdpqopIZ1uEnQTAU+YkCKLgoJEuAVzsTA+T7dqiykVInh730Pzj13cHkCWViGwMKgxty58MQTqqlQayu89lqve76FKXyb73AHS9jKREIUoBPmRu4xOeR2Uxagi0qa6SGPIAUmjVQ1IlzLSSzkETYxLbcKlFIJlqVSKjxheQRHD1miQCSipMm7utTzZFL9/tu3Q4kRQmAQHlBgOJEtzOBdesijBz+j2YXPLABzYpBBUE4LQfJx4WAFp+MiQRoH1TTkCg6z14HdrmS8L7pIGaHBagTgMA2BEKIQ+A0wGtgN/IeUMjhgnxOBhwA/kAbulFL+xnzvMeAsoMvc/Qop5TuHMyYLww9z5qjagj/8QcmGT2cdtaYImEYSnTA7GQeoSWEC23CQIokTN1H89CCQ5NEDSNzEaWAkz3IhUXxU0/A+oTFQbJS774apU3vDFFbv6o8WWd2p1atVcjYUUvUB27apcy8l/aRD+hYYlrGfMlopIJQjCQjAQQonSbI8IY0UEkE7JXiJcjeLc7993KaTn6cMj9erJv+pU1WYcDD2a8jicD2CxcALUsq7hRCLzdffGrBPFLhcSrlNCFEJvCmEeEZKGTLf/6aUchD3P7JwvODZZ2FUcYSvt/aGBQIEmcWbNDAy5xGECBDHTQwPY9iNjQwCyAA+ImSwYSMNCMpopoDOfkJj2SIiKeGNN+BLX1Lewa5diilSVjbotOkGBbK5gWAQ9u5V2zRN8fazlcOgaMT11HI991LNPiLo/JSvcDX1dFCIj7BpBDIk0SihlRR2JAKNFD7C7GYMGWwYaLl6gbw8GFGo5E5++cv+vRwGuzzN4bKGLgV+aT7/JfDpgTtIKbdKKbeZz5uAVqDkMP+vBQv9EAqpFeL44hCFeQZptw/NAXFXAVuYRCGdVNOAjzD3cCO3cCcO0hjYAUnCDBMZaETx4CDFv/FHzmY5M3gXOyn2MYIELm7ihxSj6Cmp7gjv/K2Rt16N0NGhtO+TSSWDMVCbbiDTxcKhI5sbKHRFOHtCI1WBSK5bXVtbb5vJShopppUy9mPHyElG/Du/40xeIYWGnQxd5NFKOY9yOQ4kCdwIBK2UkMDFLkbhItEvFBSJKKZafj5861sqPLhr19AQ8jtcj6BMStlsPt8PlH3QzkKIOYAT2NFn851CiCXAC8BiKWXiIJ/9CvAVgJEjRx7msC0MNQQCqsirfHKAnm0a7nSYrrSqDN5PGUtYihMjF9rZSA1vM5Nf8gVO4h28xHAQxcBOJ0WksfEyZ2GgcTYvcQLrSKFxIu/gp5s6FvFHPs2FPIcmDYyIxv85almzS3kKhgEvvgiXXKLGd7DeFxY+HJEIbN4MhY3ruLRxGem4wciQxg/TtWzqrsEwehvOl9HCZDbjJk4X+bRSzDxWm5RPQTc6DYzCQZq3mEE+EfZRTRqHKTsdZzkz+A5L+1UOgzI2fr8y8oWF6nUmAwsWDP7f8kM9AiHE80KIDQf4u7TvflJKSW8h3oG+pwL4FbBASmmqyXMzMBmYDRTy/rBS3+//mZRylpRyVkmJ5VBY6I9sbUHKpfObolryRJgxWgMFzjD11NJOaa4zWRbtlNJBKUlcdOPHwEESF2nsbGIqBk7mmhpFo9nNmbyMREkNp4E7uZUErpwk8ee763GnI7S3q5XjN76hEpp9mS6DVM36mGHdOvj61+HeOyNMfWkZ63f5eLttBG1RH1dl1PnONpxPY2MsOzBwkEcYJ1HO4yU8RMyiMAd5RKmkEQcp/sKl+OkGoJImRpnaVI/wJXYwod+1kpenJn+/X7HUHA7FVCorU7pGg/23/FCPQEp5/sHeE0K0CCEqpJTN5kTfepD9/MDfgFullCv7fHfWm0gIIR4FbvynRm/BQh9kawu+9rUa7n2nDlt3iLAjQENah+T79w8QIkgBf+TfmcsqbKTRibCEb3MeL3E6r5HAyX7KzIRxM2lsZLAzi7eooJkCgoQoUMwUGURPhQjFdDweFbK48krFaDpYl7DBHE74qJBtCKdpihq6dSsUJ0Kk4wYt+JT8eMrHCILkyxAZoJQWxrGDavaRxoGTKGPpxkaG7ArVTgYDBz3k8SYns4q5fJulRPCymSnk0YWLJOs54X1jcrmUB5BOqxBkUZHaPlR+y8MNDT0FfBG423z888AdhBBO4I/A/wxMCvcxIgKVX9hwmOOxMMxRWqrit5dfrtOa1tHM3tN796qEbl9k2SVhfKxmDqfyOgZOzuMlGqjms/weQQY3MQycuEhSTSN7GUEMLykczGQtXeTnEoshAsRivR3UWlrgrrtg/Hg1YWQyivUCgzu5eLg4WPfPviG0aBTWrFEx+ff2B4ilNJyEMYSPAi2MYWh0ygBeIkxmCwKJhziQwUXSFBVRkNhMoyBI4OLHfIMUTt5jEiPN3FEKJzsZh5P+mtGapupHCgth2jRFG00mVR3DUEgUw+EbgruB3wohvgTsAf4DQAgxC7hKSnmlue1MoEgIcYX5uSxN9NdCiBIUb+sd4KrDHI8FC8yZo1gdd9yh3PiODjWZZCfiLPqyS1TzGhcvcypJnMzncUL4zaSjxEacBC68RBjHTsL42MloJrKdi/kbcdzcyh1E0fHKCEXJEB2ZAGF0Vq5UYwiHeyUxZs5UjKN58wb3SvKfRSSiekk88YR6rWkqxl5drZ4vW6ZW316vMgbZXsM9cZ1fM5+vcz9pw46Bi4fs1xBN6wQIsZ3xzOMN4rjxECODDYmdNgIUE8RGhgyC9Uzlan7KWubgJUIrZTQwMkcndZHIFYzZbGoc550HixcrL6CyEnbuHHp9TIQchIIps2bNkmvXrj3Ww7BwnKO1Fa67TvH9t25VCUfoTfJlMZ13+T630kA1QQqpooFP82cEGXRi5qpSkEYgERg4SaKhEyWCl2f4OG2U4iLBo1zBAh57X39km01NFiNGKJpjS4uaWM44459rcHOwlfRgwLp1cM898PrraoLNtpBcs0YJ+GnJCN17QzRFA0TQSacVLbSnBz6ReJI7WIJOD/l08zYnsYXJ1FPLLsbyEFcxkzfpJh8XMcawiwQaAbM2BOAN5rCDSVzP/cpgE2EubzCfxxH0pwaDMgRVVWrSnzmz/zkfrL+DEOJNKeWs9223DIGFoYrGRjXJbjADjjt39lYdZzGddXybb3Muy8lgo4VSNNIU0U4aO16iuEkgyZBtlSyBJHYENvYwijA+/sFFVNOIIJNrZagTxkeYG6nLJR6LPRHyZYi4O0CgSue005Rhqqv78AllMDOPIhG44gqlFtvSopKtBQXKICST8MWT1jH3rWXs2Wbg9ms8WVrLi201RKOQF2vlBXk2MVxU0GJqxmb4LZ/DTYK7WUwFjfyEq9FIUkQHGgm8xEkBYQI0UkUSFxuZyq3cRSEdXG0WHQL8H/NZxbzc72SzqTDjjBnKGMDgO+cHwsEMgaU+amHIYvlyVWS2Y4dqSpLJqBtcCNPtJ8LXuY9x7GQPozDQqGA/JbTyCmcCggROMAvOADKmTBkI7KQoJMhIGhjPNoQZfujbOznbHxmU0VkaW8TN8SXc3rWIMeH1pFIqbNTU9MHHcqjMo+O1VqGpSYXp8vLUhJr1inp6IKBFOHPjMtJuH+2eEfRIHx/bUY89HkFKGOPYi0YSzEK/BB5sZCijhdN4naXczn/xBD8wtaMkEEenCz8ZnEighzxcfSSlr2YZYXzsYwRBCvgc/WtahVB0ZI9HGayhzvayDIGFIYnWVvj+91XVabZxuJTKAGQxMi+EnwgSG10UsI2JNFFBB0Xsp5xXOAMbkgwOUtiJ4SaDwA44SZFAfbEgQw3rTfVKjTKac9IW2QRyluIYxsd+yshIyaf33MuTv4zw97+rBPf69Qc/nqzGTpZ55HSqbX0NyLp1sGgR3HwzXHUVrFp1JM+owuEamnhcMW96elS+JB6HWeND2NMG3RkfDgekXD5IGtjDIWIx0IwwxXQwit3kEUanB4lgMpuJ42IXYwnj43xeYgM17KeCBqqRCFM6JMxUNuElwgNcgxMDDUMZageknP0NNihD8OUvqwRxX7aXYajzPtRgic5ZGJLIsoSy3cSamiAWgxNPVHHprVuhxx4g49VxxDJoUsWMDJxsYTIe4kxjE/uoxk2MIjrIo4ckbjIYaKRwYxAnw+ucRpACnBj46eYE1iOB9dRwB0uIolNJIxoGOhHO5iXspHET4+T0G7wUPZ+1a1Wh0v33HzhE1LfrVjbhmkgoraPrr1ec9mXL1DFu2qTeW7BA9VQeKIn8r8a3DxSaGju21xhVVh78+yorlSbPyy+Ty5fk5SnVzpZEgG17NHoyYWIpH/HOMD7TgBbTypU8zOucylxWk8JGHmHWMpNCgrzKqRg4MXBioxE/ISrZh4skLgwgQ5g8WihnE1PZxHTzd9bII0xM+nAkew22EMoIVFaq4/V61Tn3+YYOQ+hAsDwCC0MSI0f2ylLn56sbu6xMsYlefhn+7//gjI/rvH3m9exxTaSATgrpZCsT+TZL+R638TYn8gbzANCJYjcF6QSSBBrd+NnDKEayFxBcxhPsZRR/4N95mbPowc8uxgKKqiqBeawgiZMkTiSCy/kVRbKVdEMjq5dH2L69/3FkV+CgJt7WVnjuObWqPuccFbaor1eTcTSqYvBOp0pE22zwwAO9q/dIBJ5/XhVoLVmivIcP8kIGjmNgaGrpUvjCF1T19CWXqBzAwb5P1+Hqq9Xn0mn1B8ojSLl03jylFr89TLmhqJz11DKN9Szja5zCG5TTwl+5mN8wnz9yKd/ih7zOaUTMmP4odjGLN5nENnRi2EkjUYa9lVL+wiU5ZdkoOj8RtQREkHHp9yggmJOSsNnUdeP1qvM4f766hhoahoaUxMFgeQQWhiRKSxV99PbbVWtJh0OtnseMUe9/8pNwzpwI3XsLeeGVej61qAsPUWJ4aUb1n4yiM5dVBOgihR0bKVIma6iZCgrpwk4GJwme5iI+wdO5DEILFVTTkJt4oug8znxO53U8xCimg3aKOINXeJiFtFIGu+Cu8+bz6R/M47Iv6axaBQ8+qCZ0jwcuuEAlVjOZ3nBXtqAJVOgrkVDbYjH1uXQaupoi7Nkd4oFfBVi+WsflUiwdKZUXctddH66aeqDQ1LvvKk59fr7yvt57r9eryX4m+52RiOrlq2mKHtrZqbbt3auqdXW9hp/31OFLhwgRYBobeIwrsJGhgBAJnNSwgdc5jQw23mEm9xHgOu5lJLuZxZtIBDpRUtiJ4yGFAwEkcJNHd79eAlJKMpArNssinVbHdMIJ6pzPm6f+BiND6J+BZQgsDFl85jOKnrl3r/IQSkt7wyIF+9ahP7oM3TA4v1PjD1zABTzXj/b5f8znHJbjI0IKO93kk083LmKMZi+NVLKFiXTjZz/lzGYtaewkcOV6HfdtYrKKeWxhAmfwKik0CgjiJsEYdpmfX8MZna+z6qrT+Pm711P3bA0Oh9K8nzRJGbXTTlOTsRCKdnnaaWpyrayEa65R4aB9+5ROv98P3a+tI3X9Mjp3GFxm02iTtWyjhj//WX2mqwsWLlTe0gexYjRNGaFgUHkhHR29FNyGBvU8259hxQr4/e+V4QDVM+L11xVra98+Zaz6IhTKxt11UkAFTXyHb1NKC2ns2EhSRTOdFFDNPn7At4iim2Re8BKnkE72MhKdCG5ieImxmxEU04lGEo0U93J9jjb6NZbRRQGNjCCPMNdQzyLqiAmdGTPUMfZd/Q9VA5CFZQgsDGmUlqo/6I1xi2iE+WuXMWW2j5IxPhIdQb4nbudZeQEtlPfraLWWk7mADqJ4yacbieIQZbBRwX5msYar+AlX8jBvcSKT2YqbKKfxGt8ypav7woY0q1wlOhFspKigmTN5mQ5KQNqIpRzYl9XTrddRPErHboft70bQQyHWvREgYeg0N6tV+bZtcNNNaqKaO1cd31e+ooxAqivC/OQynnndh17qo9IX5nM76/mWvQ4hdIRQSdvdu9UKOJlUYaa+VNZIRBW+Pf64Co28+aYySnl5yrtau1aNw+FQq+nt29UY8vKUIXjnHfjNb3r7+aZSiq0VIJRrCJMVAswKxxXRwem8hpO4SdlV6/Y4GgZ2FvIIAAt5hCAFRPAyjxVU0pTrLSCQVLGPVczjLm7pRw0NEMKFQZvwYQNiNh+FMki1J8SoU3Xq6z843zEUYRkCC8MCfWPcFd4QLrvBqo0+TtTg7XV2psiU2cKwmzhuNDMFeQ/f5GTepJBONAwz1OAkRCFOEmgYXM1DTGUz3fjZzUhmsI4yWvgR3+IyfssdLGEjNQQI0U0ezZRTZnbCKiSIgxTFdBCkkBR22imiIt2CFgmxbZvOXM86rkwuI50wcMc1/jKiluXOGlpbVZHcVVep1evHP65WstOmqWT4GH+IQLNBMOWjuxmCQR8lRhB6QiS8OqlUb7gmHu9t9ZjVzVm3Du67T63mXS449VQYXxGhdWsIzR0gEtHp6eml45aUKA/jmWeUUch6DH2lPWazkmuox0+ICexgG+PoJsDP+RL/xROE8SHBPLcqkZBNZBbTyQzWsYq5XMsDZBC0UE4SJy2UMJ6dpoyEDQNBO6XsozpnBPoaIENo+AgTxkeeCONwa8w8N8Atdw7PjnOWIbAwLNA3xh1PBrC5NGzRMCtX+oh3p3HbU5ydXk4KDUHGbG0ZoIkq5vM4N3IPp7CSMpoBQT5dCFOSIIlGBB07KS7geVwkyGAjjx5O5k1u5EfU8pDZOP3dXFc0kDhIYzM7ZZXQxoucSyEdpIFYWqM6vY0vJO6jQ/qQNi/2rjRnhOr5k6xDaMpbaGqCG26AH/1IxbdTKWX4CkYFiBgaRMPEUz4c8TA9aARlgFRKsXi2bFHnxTBUIjqZVIahtVV9nxDkwlPBl9dxuXMZjbsMCso07onVYrerOJLXq+L+qVTvxD+wVnU2q3iUhUgEpbQSIo9TWUkrpfyClbzHFN5mJjrhXLOgvhBIytnPybzJJqaSxJXrQraZqYxjJykcGObvkUcEnSgBQoxlR66AzEDjH/ICLnE+R4U9yClnatiuqeXfz9GHlRfQF5YhsDAs0Jd+6fPpvDytlpPeqMeVDNIloVkfhz/WSsp4/2fXMpeFPMYF/J1fssCsRpWksOMhwRTew0uUYtrJI0wG6CYfL1H8dHMGr3AZ/8uFPM9mJjGB7UhAI00SB9niNJ0g5/E8Bk52M5plfBU7aU6U7xJBJ5lREtlNVDCJzbxnTGHnTjVzCdGrfZNN3r6zTefB1AKu4UH8qVbiNi8PUAs+HSMGTz8N48ap8NCf/6weTzhB5QwSCUVDtcUi6EaILqfGxYll7C9y0ZnxEm5J82/helY56nJyELGYMhip1PuNgJcI1/AgkCFtGttKWojgoRs/eXQxmffYhcrmS7OCI2sM1NeppvMj2YuLJEv4NmfzKgUESeOgnRJcJEngIoMNjQgpM0NwHfdh4KCFMpwk+ZTzOX6Yt5Riv8HsHwQYM2OYWgATliGwMCyQ7VeQEwvz1HD2z+t4/KEQ61ZGuaLlblpss4E4CdxU2Foo10LsSalJLorOGubxEmczhl1opCimDYnd7I+rEsqGucbPo4cEbgCKaOfHfAMXBhF02immk0LKaTG57gqlhAiTopkKJvIeeUTYTznl7CeCl01Mp4h2zuQVvskPCVJIvextmxmJKIMQCqnHqZl1fIGfIYjjwMHPMwtZJ2qwRXqTu+vXq6KprLe0YYN6nkjA1NS63CraFk5SThMFkS5GkUYKO7vlCLzJEEH0nHRHPN57zrOhmBABAoSoZi9j2INAomGYzSJ92MgQx8tOKiikEzdx4rhRE3+0D7NHFYilsbOa2ZzNqyxhKSfwLp/nVyRw4iWClxQZbIQI8GOuZwbvcjqvE8NDGjvvOGbjtBnYUgb5U6uoGH9ULsHjGpYhsDBskO1X0EsF1Em7df7xnxESGQ1NJOnR/HgzYZJSUQ09HpPrniIXKtrFWDzEOI3XANDMAjOw0UQ5+fTgohsHBgKJgQOdOGnsOEmSTxcuFHUmhc1UN1VTXQw3hXSSRw89+EngJoIHnRjV7KWC/STRmMx7vM1J1FKf0zLyyAgBqSZeJNzGHUxkK8Ic42Lu4nL5v5BWzByAZirp6FCr4e5uFeu328ErI3w1s4wQPiL4KKaVT/IWuxijvB0ZZjJbSKD1m/BBJWOraOgnvvcHPs2JvEsSB15iQAbNPH4nSbYxnh783Mxd5NOFjRST2MJIGnARx4bERpoUDlopoQd/7lxexhPE8fAC5zOXVehEeJOTuYdvsolp3MfXMWwuMg4PQsDprGC9cxbO0gBLlgyvpPDBYBkCC8MKut7/xq+uhlln6exP1nLm+nqkEaShWeMRby3F+ToTJ6qWk+k0RGWvbLXfbHqyirm0UcLF/BVBmnWcSA0bcJCmjWIkmCJoKZJouEiSxk4MD17CCFTsW4L5HPO5MgwJXKRwYmBQSCcAdpO7NJ2NbGTqAWPgf+FialhvSl60YiNDBU1cziOczSvUsB4BrDOrn7OKm5mM+tMJ4SFGBC8aSRK46SIPOyn8dJHGzjbGcS4vcD7PI4A8s9tXHC+zWcUmptBINRIb3+QeNAzcpgFM4CZjHouPHk7kXbYwkdHsZhPTWEYtl/MrGhjFeLbhIYJOjAZGECaPeazgTWYxifdMCXG12l/FXHyEWcId7GAC49yNaCnYXX4qU8JrsMk07kyC7bPn85M79fdVXQ9XWIbAwrBGttdxZ0kNL4+pI90RojkW4LrP6fzud7B6tVKfTCSUSJpISHOKluxiNHl046ebPMLk00UFz9JJAffwDcayi9NYgYcYBhpp7CQRpLGzglM4mTfRieA1iZEZU1RNkCGBy2QVdeIijpuEyaGxE8FDCZ10mrIWhbRzA3XE8eRi4JfzS/LoNo2HYtxnsLGIOqLkEaQQgIls5Xru5TpTmjmLKhqYxRoyQBoHm5lMFB+vcToJ3JTSwsm8yXf5NjE8rGE2E9kKwCamUkkTY9hNGJ02isg39YGS5nmwkyGOhwhe3mMSVTQxmt08zmW8y4kEKcDAwT0soo0SbuYu4riYydvoRHCS4Pf8G5/hjyRwEcMDwBzW8CazaLVVUlUBp8wOcH5aw1+h48q7EIIdJKMpvn7fPPTSo3aZHfewJCYsDGtkcwfhMOxs0WkSVVz9TZ1LLlEFXCeeCJdeqgzGjPERbvQuQyPFGHYzkgZmmM3sQwTYzFS2M54IeYxkHzdxD7fxPfZTSRwnGikSOImg4yDDViZjR9KDTsKUndBI0UM+d3ALb3AaDjNn0EgFEg0B+Ijiowcf3bhI8AO+xaU8xVm8zIU8ywj2MpN3zHh7AidxPMRwk6CUdrxEcrF2iQ3dDO1k4SXCAh5jK+Moo42RNPAxnuPXXIafHippYA5r2MyUXNX0HFbnCrxm8G7OsGUQjGEX5bQgzM5hTpLYSLON8UhsVNFkFt8pCYjJbKaFMkKmKuh+KrCT5iTeAcCBwSamsI1JALzBqThJ4iGGiwR/8c2ncoLOrFnw1Rt0Cm5TPaydwRacmsB3y/XopVY8qC8sj8DCsMf7cwdqe2Wler1rl6qYrciEcBpRpjk3Yc8YlBLEkYpQRjtNVNBJMQB2usxVq8HfuIQLec7UvdHwEGUuq82WiEkqaMZHD93ks44ZtFCGhsFktrOMr5FPkH1U85/8jh58+IgQx4WdNBuooYERnMGrGGalcg8+zuMF2inCwGmWYElSuWlaUkUjeXSTwU6IfCLo/SqgA4TIo4sx7GE3o0ihUUozX+IxtjKeiWzHgcEYduMkYa7GRS4nIpAkceIiQR5hHGZsP4wvtz2FwwyZGfjopod8U1XUhoETN3F68FNAkHy6cmPLYMdAkMZBF/k5quizXEgRHbjsKRpHzGPieFVL8fOfw6+9NVyzoI7p1aGhrRNxGLAMgQULvD93kN22cCFcfrmKm4cdAXSvxNEdo9gWxOmCeMqDRoIS2ghRQBo7gkxuco2icy/XU0s9TnNS3swUkjg5h+WEyUMicJBmElsYw24A8glRQSNj2c0EtueMQAKX6SFU0YPf/H+SvYxiNLvx04ODFJuZSjGdhHBSQJAUTmxk6KSQAF1mX14DJ15+ylcHhIX2MZu1lNBODA8R3FTRTBwXs+mihVJK6CHb5M1HNxopNjGFfLqZyyq8xEiZx5Xt7ubCwEsMG2k6KOJlzsFDlIt5miRuUjjowo8gTRx3TsYboAc/T3NxjlFURgtODOqpzZ3bghKNh93XM2a6zoYNSk9pzBjl7T34qE5d3fCtE/gwHFZoSAhRKIR4TgixzXwsOMh+aSHEO+bfU322jxFCrBJCbBdC/MZsdG/BwnGDggIllfyxj0GgSuc3JdfgtiXxiBjpDLQ7ythPBT34KaIjp2B6n6lrA7CRGm6kjm+zlEXUkcLBxfyVKhoZxW6TPuminP2ksZHAiZ9uqmnkVU4njZ0S2rFj0EkBNjLmBK2bjJo0NjI0MIKVzKWZCpqopIVSMwTkIIabBkZgoJHBnmu7qYxYS+54VVjoUVYzmxQO3IQZy24EEhcGggwBuuikEAdpNFJspIZreJCv8VNaKKODQjOx3FsHEEHHQwRJhjQ2PMQ5nVfZyyhWMI9OCvASwUYGnSiT2ZxTIW2mEgMNJ8kcWygrILfFUcMtWh13OJbyl7PrWPK7Gm66CWbN6hUYHMp9BI4UDjdHsBh4QUo5AXjBfH0gxKSUJ5p/n+qz/QfAj6WU44Eg8KXDHI8FC0cM69YpxdING1Rx1ckng+/cufz2gl/gGVGCpyJAxqbxtjab5bbz+Q/xey7hLyzksRwLJ4soOk1U5YxDGgcSYUoiCHYwBhsZNFJ4iNFGMWkc9ODnGT6OaqHjI58Q5eynhnVsZTzn8BL5hBjDLjooJI6XW7gTOxmazdh6CD92MnRQSDEdZJAYuHCSpIQO6ljELFbjJcJkNuMhyg4m8lc+YZa62UljJ4xu5hwSxHHxGqezirlcx30s53zmsJJTWYGfMCk0YnhydRV+wjhJkcSFBHQijGE3c1jJWHZSwX5SaDzPBfyVS4jgYwlL2UgNURRbK48w1fTKVGfPZcymUzC9ilvu1Jk7F6ZM6e0jAEO7j8CRwuGGhi4Fzjaf/xJ4CfjWoXxQCCGAc4H/6vP57wAPHeaYLFg4bGS1iQoKlO7/ihXw2mtK7fPiH56FI/a/JH7wAG0pG7ZuD/dHanknpZrUy4Haxn0QIEQcL8s5myI6mMJmM+Tj5kXOoY1SesjjAp5DkCGOm/FsxUfYXJUniaAToIureYi/8UkSuHERx08PS1hKO6W8zhnUsYj/YxJ59DCTtyijhTBefETx0EMGkQtN3c5SWilDI8Us1iIRdFJEE+WU00ozZRQSwlBKPeynFDcJfshNRNH5BH/hHm4kQBceIoDASZIMdjrxE6SAMexEI4XEbj5KZrOW5zmXsewhhoeTeJtnuRAfYTN8ZfYPPquGB3fVkWoPkfEH2NOu43PC6NGq7iGRUBXVcIDiQW3o9hE4UjhcQ1AmpWw2n+8Hyg6yn1sIsRZIAXdLKf8EFAEhKWVWkmofUHWY47Fg4YigrzaRzwcXX6xklBcvzoqSzYGHfsKzi0Kk8wKMb9PZ8YwqPrPbVU4hW23bF1lapgoBudnEVKRJ6yyjhVrqKSTIViYCUE0jNWwgRD4VtGJgz8XJCwiRxk4Pfnrwm6t1NXk6MUjipIsAc1lNN/m5gjadKDGTR+QgRQIXk9hKI1XsYwQZFA3zbWYgELzKqVTTTCeCJA7WM40w+UhgAlu5kXs4m+UU0kkKG5pJgQVIIdDIkMBDCjc2MqTNtHIKB+0U0sQIRrEPADtpCuno1zvAbld9p3t6dIRTpzwArp5emWuHQ4WBsq/h4AQACwfGhxoCIcTzQPkB3rq17wsppRRCHGQdxCgpZaMQYizwohBiPfShAhwChBBfAb4CMHLkyH/moxYs/NPor02kJvVAQDGJstBLdf7fTUq22O+Hs85Ssss9Pb0GIduJC3ppmauZzXQ24iLBTN7mCh6jnVLaKeVG6vpV6U5mM7fTyRQ2mwygFGkctFFCBfvxEiVIEQGCOEmSNCt9PUQBKKQDu1mBYOBkNXO4gOcoIIgHSQslNDCSSWylkyIA9jAGG3A/12Ijw0IeoYsCk+CaYBfjiOAjQJAf8U0EGcrZjxODNDYM7DjMaukwfkIUsIHp+OkhjzASgYGDCLpJMbWxhtnMYwVuErneAXh1yv1K0bSpSU3msZiSuk6nlTTGvHmqDiSReH/o50AEAAsHxocaAinl+Qd7TwjRIoSokFI2CyEqgNaDfEej+bhTCPEScBLweyAghHCYXkE10PgB4/gZ8DOAWbNmHczgWLBwRHCo4YWBK8+NG+GWW1Tj+OwKNTuBFcoQLmmwlzE0UYWbOEW009THEc7y8rPYy0gmsIMe8uikwFTmlGSwsQpVFlvDu0xmC+8xiQepBRTLJo9uHKTxEEOQ4Q1OJYmTFczjL1zM5fyacexkMu+hYTCSPexgAjphonh4z6wT2MQ0AoTwEGUxdxNBtSmzkaGYdgycpHBgJ4ONNE4zIdyNH5AU04qNNKuZQxInJ7AeB0kcpLmTxcxjDRoGa5nF48xnoz6PjriOU6rVfkGBOr+plAr/OJ2qLWdXl/ptbDYr9HO4ONzQ0FPAF4G7zcc/D9zBZBJFpZQJIUQxcBrwQ9ODWA58FnjiYJ+3YOFY4VDDC31XnnPmqH7IV14Jb7+tOnllvYKMP4AHjUoZprnHh8ORJG54+3H4B8KJwXtMYiQNtFOEAGK4WMcMvs8ttFBGHYt4jguIoPMJ/gbA01xMkAKKaeX7LOZcXqSM/TmDcT4vEcXDO8xgPNvx0c3FPM2rnE4TVf2SsVnj5CViCuyFSeKkmDZTI0nSQx5OOpBms84weWTFMnrIQ+LgcT7Lx3iO3YwyxzGFeazhERbSRBUhAiTsOiKhQmvxOLS1qRV/IKCE9LJieW638tQWLFCemGUEDg+HawjuBn4rhPgSsAf4DwAhxCzgKinllcAU4KdCiAyKpXS3lHKT+flvAU8IIb4HvA08fJjjsWDhiOJfCS+UlsKtt6pJStN6PYq4Xeet2bXMWl1Pvi9IJKnxkKeWaOzg/yBEgFbKaGAkaey5pPAi6minlEoaSeIkRAF5dCNNIqDbrCaey2rcJEmYxWXPcQEhCiijmRo2EkYnjoce8kniJokzl3AeiCx753aWcgLrcRNDkMZPNykcRPBiI0MGG01UoJEmghc7GTop4GM8x918iztYwt+5iJDp4SzkEW4020TaUJO9y6UenU6VfL/1VtW/2e1W7yUSylDMmmUZgSOBwzIEUsoO4LwDbF8LXGk+XwEDuHS9++0ELNknC0MOc+fCY4/BAw8oj6C7W01qrXk1/LC0jjNqQngrA0zs0BHbVP/hgRr+0Dv51lKfE5T7ITflJuoQgdwqPY47l6RNY2MeK0jgYidjKaSDCWxnPScA0EmRKSDXTQQfGklT+0fPJZwPhF2MpRs/r3EaM3mLMDqVNJktOGE55/AUl3AeL3Iqb1BAkHaKmMtq9jKCYjpyhgsggo8CggQIEZU6Uqrz4PWqjmu6rvI0l16q+irffrt67XDAHXf0tiG1cHiwKostWPiIMGcO/OQnvaElUM/37dN59FGdHjMR/YMfwBe+oBq7HwjZgrRsErlvDmGgoehlG+3DTYLlnIOBk06KkKjkcQsVVNKIQFJIBwUE2U8Fa5hlav4EDnpMAUIIoIt8BNBBKWkcrOVk8ujhVu5iBxN4gQt4lo/RSRE9+PGiZKuV9IVqExnBh5cw0q7RIwO5oqbSUjj3XMXOCodVDiAQgM98Bs44A/buhZEjLSNwJGEZAgsWPkIMDC3pulIznT69f+7hmmvgttt62zwK0fvn8UA43D+J3BcDDQWofgMqsas+4yTJempMwbxdzGINr3AmBhqnsgI7Bikc/XIDB0LWA7GTJo0dL2EMnITxY+CiGUWrSuFkA9MYSUNOtvo9JpHCyU9ELV+T9RQQxObS2PWJWuaX6EQiauK/8kr461+hoeH9SfrSUssAfBQQ8kD+6HGOWbNmybVr1x7rYViwcMTQ2qqaw7e0qFBSQsn2o+tQXq6E7/o2gT8UTGN9v5BSPbXsYiyT2cy13M9uxgKgkWQsO7nd1PD/MJwg1vMNVz3F6RbGGCr53EoZ9dTmKqq9RLiHRSRwmbLTqr/zEk8dF31WR4YjyGAIe1GAktE6Pp8yAuGwStCDVQPwUUAI8aaUctbA7ZZHYMHCMUYkoqimS5cqr6C9XYVD8vKUXEJTk+LMt7erBGoWmta/P7DD0d9YbLbVcGPm/SGl95hCDG+u8buTJCECudX8h6Gzqob7PHUYbSHiGY10zKDV6B+ywqvzpF7Lf7TX45AGKaHxkKglUKVTXQ3JpE44rLNgATz66IEpupYBOHqwPAILFo4h1q1TUhaGoSbCyy5ThWh+P1RUqO3t7XDXXYoxs2qVMgygVsvd3epzbreSygZlRCoqVMK1pUWxaxKJ/snoA3kLA/WRsuhrYOx2uOgi2LNHhW6qqlSBVzKpwlher9nq0nyMd0TIlyFEQYCRU3QKC9WxZSf9mhplCK3V/9HBwTwCyxBYsHCMEInAokW9MhZ9QyN9J8S++zmdsG2bqlHIZFQVc3m5Ci2FQmofm039lZerePrq1epL8mWIoAwQlurLvUQoFCG6RICezIFn4KxRisWUMbHbVVHXpElKiK+yUhmJ5mb1P6urYdo0ePddFeoqLITOTlUAdv/96risSf/YwQoNWbBwnKGvnhGox2BQbR+YYM5WORsGFBXBL34BDz+sjMH69WqSttnUxOxyKV2kSESxa2782Dri/72MdNwgltK4J1rLOllDTOq0ajpCgE/r1UeSUj2329VE7vGo7dmVvJSqgvqmm5RH43Qqg5QdWyajQlpZJRifT3kPhmHJPhyvsAyBBQvHCAP1jD5ILvlAVc5FRco4TJ+uwj/jxyvPIJGA4mIldfGJsyIUfG8Zy0t8pN0+ClJhfhiq55pEHRF0urvV902apCbwrKNdVKQauzid8LnPwfXXqzAQKGmH3bth5UooKYH585XmD6jxaRosWXJox2Xh+IBlCCxYOEb4Z+WSB66m+xqHfftU0rW4WIViNA1efRXeeyHETWGDGaf6WLMGujM+irQgj98bIm+yTjSq4vlZMb0XX1QSGZqmttfWqkIut1uFhzweFQbSNJioShZ48kllCPqOz5KBHlywcgQWLBxjHKlkaSSiEsl3362E2nw+SAYjfPy5RZxygQ90H4mOMO5UGO3+uoP+swON5/e/V1W98bgyNBdeCFOnqvcaGhTjKesxHOnjsnDkYOUILFg4TnGk4ua6rlbx0Jt3cBboPD+plpmd9fjCQZyaBtd/8PL8QOPJVvVu2aIawmeLuj4o7GPlAwYPLENgwcIQwoHyDuGyGsTSOjBCueX5v7Jaz1b1BgJW2GeowQoNWbAwxLB+fS/DqC9fP4uBtQsD3z8UWGGfwQmrjsCChWGEg03Uh1q7YGFowsoRWLAwjHCw+Pyh1i5YGF6wffguFixYGCrom0MAi+NvQcEyBBYsDCNkaxfCYUX7DIetZK8FKzRkwcKww6H2YrYwfGAZAgsWhiEsjr+Fvjis0JAQolAI8ZwQYpv5WHCAfc4RQrzT5y8uhPi0+d5jQohdfd478XDGY8GCBQsW/nkcbo5gMfCClHIC8IL5uh+klMullCdKKU8EzgWiwLN9dvlm9n0p5TuHOR4LFixYsPBP4nANwaXAL83nvwQ+/SH7fxb4u5Qyepj/14IFCxYsHCEcriEok1I2m8/3A2Ufsv9lwOMDtt0phFgnhPixEMJ1sA8KIb4ihFgrhFjb1tZ2GEO2YMGCBQt98aGGQAjxvBBiwwH+Lu27n1QlygctUxZCVAA1wDN9Nt8MTAZmA4XAtw72eSnlz6SUs6SUs0pKSj5s2BYsWLBg4RDxoawhKeX5B3tPCNEihKiQUjabE33rB3zVfwB/lFIafb47600khBCPAjceyqDffPPNdiHEnkPZ9wihGGg/iv/vSMEa99GFNe6jC2vc/zxGHWjj4dJHnwK+CNxtPv75A/adj/IAcuhjRAQqv7DhUP6plPKougRCiLUH0uc43mGN++jCGvfRhTXuI4fDzRHcDVwghNgGnG++RggxSwjxi+xOQojRwAjg5QGf/7UQYj2wHmUlv3eY47FgwYIFC/8kDssjkFJ2AOcdYPta4Mo+r3cDVQfY79zD+f8WLFiwYOHwYWkNHRp+dqwH8C/CGvfRhTXuowtr3EcIg7IfgQULFixYOHKwPAILFixYGOawDIEFCxYsDHNYhuAAEEJ8TgixUQiREUIclOYlhPi4EGKLEGK7EOJ9OktHG4ciAmjul+4j9PfU0R5nn3F84PkTQriEEL8x319lss+OOQ5h3FcIIdr6nOMrD/Q9RxNCiEeEEK1CiANStIXC/eYxrRNCzDzaYzwQDmHcZwshuvqc6yVHe4wHghBihBBiuRBikzmXXHeAfY6fcy6ltP4G/AFTgEnAS8Csg+xjB3YAYwEn8C4w9RiP+4fAYvP5YuAHB9kvfByc4w89f8DVwE/M55cBvxkk474CePBYj3XAmM4EZgIbDvL+J4C/AwI4BVh1rMd8iOM+G/jrsR7nAcZVAcw0n+cBWw9wnRw359zyCA4AKeVmKeWWD9ltDrBdSrlTSpkEnkCJ8B1L/LMigMcSh3L++h7Pk8B5ZvHhscTx+Lt/KKSUrwCdH7DLpcD/SIWVQMBUCzimOIRxH5eQUjZLKd8yn/cAm3k/hf64OeeWIfjXUQU09Hm9jwPUShxlHKoIoNsU8FuZ7Q1xDHAo5y+3j5QyBXQBRUdldAfHof7unzHd/SeFECOOztAOC8fj9XyomCeEeFcI8XchxLRjPZiBMEOaJwGrBrx13JzzYduhTAjxPFB+gLdulVJ+kFTGMcUHjbvvCymlFEIcjBs8SkrZKIQYC7wohFgvpdxxpMc6jPEX4HEpZUII8VWUV2MVT340eAt1PYeFEJ8A/gRMOLZD6oUQwgf8HrheStl9rMdzMAxbQyA/QEzvENGIks3Iotrc9pHig8Z9qCKAUspG83GnEOIl1GrlaBuCQzl/2X32CSEcQD7QcXSGd1B86LilqrjP4heo3M3xjmNyPR8u+k6uUsqnhRDLhBDFUspjLkYnhNBQRuDXUso/HGCX4+acW6Ghfx1rgAlCiDFCCCcqmXnMGDgmsiKAcBARQCFEgTD7PgghioHTgE1HbYS9OJTz1/d4Pgu8KM0s2zHEh457QJz3U6j48PGOp4DLTSbLKUBXnzDjcQshRHk2bySEmIOa0471YgFzTA8Dm6WU/32Q3Y6fc36ss+vH4x/wb6h4XQJoAZ4xt1cCT/fZ7xMoNsAOVEjpWI+7CNUydBvwPFBobp8F/MJ8fipK5O9d8/FLx3C87zt/wFLgU+ZzN/A7YDuwGhh7rM/xIY77LmCjeY6XA5OPgzE/DjQDhnltfwm4CrjKfF8A9eYxrecgbLnjcNzX9DnXK4FTj/WYzXGdjurPsg54x/z7xPF6zi2JCQsWLFgY5rBCQxYsWLAwzGEZAgsWLFgY5rAMgQULFiwMc1iGwIIFCxaGOSxDYMGCBQvDHJYhsGDBgoVhDssQWLBgwcIwx/8HhiZxNgSBhjMAAAAASUVORK5CYII=",
       "text/plain": [
        "<Figure size 432x288 with 1 Axes>"
       ]
@@ -2055,15 +2066,50 @@
     }
    ],
    "source": [
-    "maf_rec = AutoModel.load_from_folder(os.path.join(pipeline.trainer.training_dir, 'final_model')).to(device).eval()\n",
+    "nf_rec = AutoModel.load_from_folder(os.path.join(pipeline.trainer.training_dir, 'final_model')).to(device).eval()\n",
     "\n",
     "z_sample = prior.sample((128*8,))\n",
     "\n",
-    "z = maf_rec.inverse(z_sample).out.detach().cpu()\n",
+    "z = nf_rec.inverse(z_sample).out.detach().cpu()\n",
     "plt.scatter(train_moons[:,0], train_moons[:,1], c='b', s=20, alpha=0.5, label='true distribution')\n",
     "plt.scatter(z[:,0], z[:,1], c='r', s=20, alpha=0.5, label='transformed gaussian')\n",
     "plt.legend()"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.legend.Legend at 0x7f46724f2b20>"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "z = nf_rec(train_moons.cuda()[:1000]).out.detach().cpu()\n",
+    "plt.scatter(z_sample.cpu()[:,0], z_sample.cpu()[:,1], c='b', s=20, alpha=0.5, label='prior distribution')\n",
+    "plt.scatter(z[:,0], z[:,1], c='r', s=20, alpha=0.5, label='transformed two moons')\n",
+    "plt.legend()"
+   ]
   }
  ],
  "metadata": {
diff --git a/examples/notebooks/models_training/vae_iaf_training.ipynb b/examples/notebooks/models_training/vae_iaf_training.ipynb
index 6c6f0c19..b53bf381 100644
--- a/examples/notebooks/models_training/vae_iaf_training.ipynb
+++ b/examples/notebooks/models_training/vae_iaf_training.ipynb
@@ -65,9 +65,10 @@
     "model_config = VAE_IAF_Config(\n",
     "    input_dim=(1, 28, 28),\n",
     "    latent_dim=16,\n",
-    "    n_made_blocks=2,\n",
+    "    n_blocks=2,\n",
     "    n_hidden_in_made=3,\n",
-    "    hidden_size=128\n",
+    "    hidden_size=128,\n",
+    "    context_dim=25\n",
     ")\n",
     "\n",
     "model = VAE_IAF(\n",
@@ -343,7 +344,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.8.12"
+   "version": "3.8.13"
   },
   "orig_nbformat": 4
  },
diff --git a/src/pythae/models/nn/benchmarks/celeba/convnets.py b/src/pythae/models/nn/benchmarks/celeba/convnets.py
index 650de4e1..63b5f477 100644
--- a/src/pythae/models/nn/benchmarks/celeba/convnets.py
+++ b/src/pythae/models/nn/benchmarks/celeba/convnets.py
@@ -235,6 +235,7 @@ def __init__(self, args: BaseAEConfig):
         self.input_dim = (3, 64, 64)
         self.latent_dim = args.latent_dim
         self.n_channels = 3
+        self.outputs_context = False
 
         layers = nn.ModuleList()
 
@@ -270,6 +271,10 @@ def __init__(self, args: BaseAEConfig):
         self.embedding = nn.Linear(1024 * 4 * 4, args.latent_dim)
         self.log_var = nn.Linear(1024 * 4 * 4, args.latent_dim)
 
+        if hasattr(args, "context_dim") and args.context_dim is not None:
+            self.outputs_context = True
+            self.context_layer = nn.Linear(1024 * 4 * 4, args.context_dim)
+
     def forward(self, x: torch.Tensor, output_layer_levels: List[int] = None):
         """Forward method
 
@@ -315,6 +320,8 @@ def forward(self, x: torch.Tensor, output_layer_levels: List[int] = None):
             if i + 1 == self.depth:
                 output["embedding"] = self.embedding(out.reshape(x.shape[0], -1))
                 output["log_covariance"] = self.log_var(out.reshape(x.shape[0], -1))
+                if self.outputs_context:
+                    output["context"] = self.context_layer(out.reshape(x.shape[0], -1))
 
         return output
 
diff --git a/src/pythae/models/nn/benchmarks/celeba/resnets.py b/src/pythae/models/nn/benchmarks/celeba/resnets.py
index a661853b..0d420c86 100644
--- a/src/pythae/models/nn/benchmarks/celeba/resnets.py
+++ b/src/pythae/models/nn/benchmarks/celeba/resnets.py
@@ -235,6 +235,7 @@ def __init__(self, args: BaseAEConfig):
         self.input_dim = (3, 64, 64)
         self.latent_dim = args.latent_dim
         self.n_channels = 3
+        self.outputs_context = False
 
         layers = nn.ModuleList()
 
@@ -259,6 +260,10 @@ def __init__(self, args: BaseAEConfig):
         self.embedding = nn.Linear(128 * 4 * 4, args.latent_dim)
         self.log_var = nn.Linear(128 * 4 * 4, args.latent_dim)
 
+        if hasattr(args, "context_dim") and args.context_dim is not None:
+            self.outputs_context = True
+            self.context_layer = nn.Linear(128 * 4 * 4, args.context_dim)
+
     def forward(self, x: torch.Tensor, output_layer_levels: List[int] = None):
         """Forward method
 
@@ -301,6 +306,8 @@ def forward(self, x: torch.Tensor, output_layer_levels: List[int] = None):
             if i + 1 == self.depth:
                 output["embedding"] = self.embedding(out.reshape(x.shape[0], -1))
                 output["log_covariance"] = self.log_var(out.reshape(x.shape[0], -1))
+                if self.outputs_context:
+                    output["context"] = self.context_layer(out.reshape(x.shape[0], -1))
 
         return output
 
diff --git a/src/pythae/models/nn/benchmarks/cifar/convnets.py b/src/pythae/models/nn/benchmarks/cifar/convnets.py
index 3a59d75d..fd8212c4 100644
--- a/src/pythae/models/nn/benchmarks/cifar/convnets.py
+++ b/src/pythae/models/nn/benchmarks/cifar/convnets.py
@@ -230,6 +230,7 @@ def __init__(self, args: BaseAEConfig):
         self.input_dim = (3, 32, 32)
         self.latent_dim = args.latent_dim
         self.n_channels = 3
+        self.outputs_context = False
 
         layers = nn.ModuleList()
 
@@ -265,6 +266,10 @@ def __init__(self, args: BaseAEConfig):
         self.embedding = nn.Linear(1024 * 2 * 2, args.latent_dim)
         self.log_var = nn.Linear(1024 * 2 * 2, args.latent_dim)
 
+        if hasattr(args, "context_dim") and args.context_dim is not None:
+            self.outputs_context = True
+            self.context_layer = nn.Linear(1024 * 2 * 2, args.context_dim)
+
     def forward(self, x: torch.Tensor, output_layer_levels: List[int] = None):
         """Forward method
 
@@ -310,6 +315,8 @@ def forward(self, x: torch.Tensor, output_layer_levels: List[int] = None):
             if i + 1 == self.depth:
                 output["embedding"] = self.embedding(out.reshape(x.shape[0], -1))
                 output["log_covariance"] = self.log_var(out.reshape(x.shape[0], -1))
+                if self.outputs_context:
+                    output["context"] = self.context_layer(out.reshape(x.shape[0], -1))
 
         return output
 
diff --git a/src/pythae/models/nn/benchmarks/cifar/resnets.py b/src/pythae/models/nn/benchmarks/cifar/resnets.py
index 84ecedaf..30acc6e1 100644
--- a/src/pythae/models/nn/benchmarks/cifar/resnets.py
+++ b/src/pythae/models/nn/benchmarks/cifar/resnets.py
@@ -228,6 +228,7 @@ def __init__(self, args: BaseAEConfig):
         self.input_dim = (3, 32, 32)
         self.latent_dim = args.latent_dim
         self.n_channels = 3
+        self.outputs_context = False
 
         layers = nn.ModuleList()
 
@@ -250,6 +251,10 @@ def __init__(self, args: BaseAEConfig):
         self.embedding = nn.Linear(128 * 8 * 8, args.latent_dim)
         self.log_var = nn.Linear(128 * 8 * 8, args.latent_dim)
 
+        if hasattr(args, "context_dim") and args.context_dim is not None:
+            self.outputs_context = True
+            self.context_layer = nn.Linear(128 * 8 * 8, args.context_dim)
+
     def forward(self, x: torch.Tensor, output_layer_levels: List[int] = None):
         """Forward method
 
@@ -292,6 +297,8 @@ def forward(self, x: torch.Tensor, output_layer_levels: List[int] = None):
             if i + 1 == self.depth:
                 output["embedding"] = self.embedding(out.reshape(x.shape[0], -1))
                 output["log_covariance"] = self.log_var(out.reshape(x.shape[0], -1))
+                if self.outputs_context:
+                    output["context"] = self.context_layer(out.reshape(x.shape[0], -1))
 
         return output
 
diff --git a/src/pythae/models/nn/benchmarks/mnist/convnets.py b/src/pythae/models/nn/benchmarks/mnist/convnets.py
index 560616bd..1c7e0e22 100644
--- a/src/pythae/models/nn/benchmarks/mnist/convnets.py
+++ b/src/pythae/models/nn/benchmarks/mnist/convnets.py
@@ -234,6 +234,7 @@ def __init__(self, args: BaseAEConfig):
         self.input_dim = (1, 28, 28)
         self.latent_dim = args.latent_dim
         self.n_channels = 1
+        self.outputs_context = False
 
         layers = nn.ModuleList()
 
@@ -269,6 +270,10 @@ def __init__(self, args: BaseAEConfig):
         self.embedding = nn.Linear(1024, args.latent_dim)
         self.log_var = nn.Linear(1024, args.latent_dim)
 
+        if hasattr(args, "context_dim") and args.context_dim is not None:
+            self.outputs_context = True
+            self.context_layer = nn.Linear(1024, args.context_dim)
+
     def forward(self, x: torch.Tensor, output_layer_levels: List[int] = None):
         """Forward method
 
@@ -313,6 +318,8 @@ def forward(self, x: torch.Tensor, output_layer_levels: List[int] = None):
             if i + 1 == self.depth:
                 output["embedding"] = self.embedding(out.reshape(x.shape[0], -1))
                 output["log_covariance"] = self.log_var(out.reshape(x.shape[0], -1))
+                if self.outputs_context:
+                    output["context"] = self.context_layer(out.reshape(x.shape[0], -1))
 
         return output
 
diff --git a/src/pythae/models/nn/benchmarks/mnist/resnets.py b/src/pythae/models/nn/benchmarks/mnist/resnets.py
index 7a937dde..223bad3e 100644
--- a/src/pythae/models/nn/benchmarks/mnist/resnets.py
+++ b/src/pythae/models/nn/benchmarks/mnist/resnets.py
@@ -229,6 +229,7 @@ def __init__(self, args: BaseAEConfig):
         self.input_dim = (1, 28, 28)
         self.latent_dim = args.latent_dim
         self.n_channels = 1
+        self.outputs_context = False
 
         layers = nn.ModuleList()
 
@@ -251,6 +252,10 @@ def __init__(self, args: BaseAEConfig):
         self.embedding = nn.Linear(128 * 4 * 4, args.latent_dim)
         self.log_var = nn.Linear(128 * 4 * 4, args.latent_dim)
 
+        if hasattr(args, "context_dim") and args.context_dim is not None:
+            self.outputs_context = True
+            self.context_layer = nn.Linear(128 * 4 * 4, args.context_dim)
+
     def forward(self, x: torch.Tensor, output_layer_levels: List[int] = None):
         """Forward method
 
@@ -293,6 +298,8 @@ def forward(self, x: torch.Tensor, output_layer_levels: List[int] = None):
             if i + 1 == self.depth:
                 output["embedding"] = self.embedding(out.reshape(x.shape[0], -1))
                 output["log_covariance"] = self.log_var(out.reshape(x.shape[0], -1))
+                if self.outputs_context:
+                    output["context"] = self.context_layer(out.reshape(x.shape[0], -1))
 
         return output
 
diff --git a/src/pythae/models/nn/default_architectures.py b/src/pythae/models/nn/default_architectures.py
index b410bb5e..58d7b67d 100644
--- a/src/pythae/models/nn/default_architectures.py
+++ b/src/pythae/models/nn/default_architectures.py
@@ -3,6 +3,7 @@
 import numpy as np
 import torch
 import torch.nn as nn
+from attr import has
 
 from pythae.models.nn import BaseDecoder, BaseDiscriminator, BaseEncoder, BaseMetric
 
@@ -70,10 +71,15 @@ def __init__(self, args: dict):
 
         self.layers = layers
         self.depth = len(layers)
+        self.outputs_context = False
 
         self.embedding = nn.Linear(512, self.latent_dim)
         self.log_var = nn.Linear(512, self.latent_dim)
 
+        if hasattr(args, "context_dim") and args.context_dim is not None:
+            self.outputs_context = True
+            self.context_layer = nn.Linear(512, args.context_dim)
+
     def forward(self, x, output_layer_levels: List[int] = None):
         output = ModelOutput()
 
@@ -105,6 +111,8 @@ def forward(self, x, output_layer_levels: List[int] = None):
             if i + 1 == self.depth:
                 output["embedding"] = self.embedding(out)
                 output["log_covariance"] = self.log_var(out)
+                if self.outputs_context:
+                    output["context"] = self.context_layer(out)
 
         return output
 
diff --git a/src/pythae/models/normalizing_flows/iaf/iaf_config.py b/src/pythae/models/normalizing_flows/iaf/iaf_config.py
index 4c58a455..9f646419 100644
--- a/src/pythae/models/normalizing_flows/iaf/iaf_config.py
+++ b/src/pythae/models/normalizing_flows/iaf/iaf_config.py
@@ -1,3 +1,5 @@
+from typing import Union
+
 from pydantic.dataclasses import dataclass
 
 from ..base import BaseNFConfig
@@ -5,19 +7,21 @@
 
 @dataclass
 class IAFConfig(BaseNFConfig):
-    """This is the MADE model configuration instance.
+    """This is the Inverse Autoregressive Flow model configuration instance.
 
     Parameters:
         input_dim (tuple): The input data dimension. Default: None.
-        n_made_blocks (int): The number of MADE model to consider in the IAF. Default: 2.
+        n_blocks (int): The number of IAF blocks to consider in the flow. Default: 2.
         n_hidden_in_made (int): The number of hidden layers in the MADE models. Default: 3.
         hidden_size (list): The number of unit in each hidder layer. The same number of units is
-            used across the `n_hidden_in_made` and `n_made_blocks`. Default: 128.
+            used across the `n_hidden_in_made` and `n_blocks`. Default: 128.
+        context_dim (int): The dimension of the context. Default: None.
         include_batch_norm (bool): Whether to include batch normalization after each
             :class:`~pythae.models.normalizing_flows.MADE` layers. Default: False.
     """
 
-    n_made_blocks: int = 2
+    n_blocks: int = 2
     n_hidden_in_made: int = 3
+    context_dim: Union[int, None] = None
     hidden_size: int = 128
     include_batch_norm: bool = False
diff --git a/src/pythae/models/normalizing_flows/iaf/iaf_model.py b/src/pythae/models/normalizing_flows/iaf/iaf_model.py
index 6366a652..0f978aba 100644
--- a/src/pythae/models/normalizing_flows/iaf/iaf_model.py
+++ b/src/pythae/models/normalizing_flows/iaf/iaf_model.py
@@ -29,6 +29,7 @@ def __init__(self, model_config: IAFConfig):
         self.model_config = model_config
         self.input_dim = np.prod(model_config.input_dim)
         self.hidden_size = model_config.hidden_size
+        self.context_dim = np.prod(model_config.context_dim)
         self.model_name = "IAF"
 
         made_config = MADEConfig(
@@ -36,20 +37,22 @@ def __init__(self, model_config: IAFConfig):
             output_dim=(self.input_dim,),
             hidden_sizes=[self.hidden_size] * self.model_config.n_hidden_in_made,
             degrees_ordering="sequential",
+            context_dim=(self.context_dim,) if self.context_dim is not None else None,
         )
 
-        for i in range(model_config.n_made_blocks):
+        for i in range(model_config.n_blocks):
             self.net.extend([MADE(made_config)])
             if self.model_config.include_batch_norm:
                 self.net.extend([BatchNorm(self.input_dim)])
 
         self.net = nn.ModuleList(self.net)
 
-    def forward(self, x: torch.Tensor, **kwargs) -> ModelOutput:
+    def forward(self, x: torch.Tensor, h: torch.Tensor = None, **kwargs) -> ModelOutput:
         """The input data is transformed toward the prior (f^{-1})
 
         Args:
-            inputs (torch.Tensor): An input tensor
+            x (torch.Tensor): An input tensor.
+            h (torch.Tensor): The context tensor. Default: None.
 
         Returns:
             ModelOutput: An instance of ModelOutput containing all the relevant parameters
@@ -61,7 +64,7 @@ def forward(self, x: torch.Tensor, **kwargs) -> ModelOutput:
             if layer.__class__.__name__ == "MADE":
                 y = torch.zeros_like(x)
                 for i in range(self.input_dim):
-                    layer_out = layer(y.clone())
+                    layer_out = layer(y.clone(), h=h)
 
                     m, s = layer_out.mu, layer_out.log_var
 
@@ -79,11 +82,12 @@ def forward(self, x: torch.Tensor, **kwargs) -> ModelOutput:
 
         return ModelOutput(out=x, log_abs_det_jac=sum_log_abs_det_jac)
 
-    def inverse(self, y: torch.Tensor, **kwargs) -> ModelOutput:
+    def inverse(self, y: torch.Tensor, h: torch.Tensor = None, **kwargs) -> ModelOutput:
         """The prior is transformed toward the input data (f)
 
         Args:
-            inputs (torch.Tensor): An input tensor
+            x (torch.Tensor): An input tensor.
+            h (torch.Tensor): The context tensor. Default: None.
 
         Returns:
             ModelOutput: An instance of ModelOutput containing all the relevant parameters
@@ -94,7 +98,7 @@ def inverse(self, y: torch.Tensor, **kwargs) -> ModelOutput:
         for layer in self.net[::-1]:
             y = y.flip(dims=(1,))
             if layer.__class__.__name__ == "MADE":
-                layer_out = layer(y)
+                layer_out = layer(y, h=h)
                 m, s = layer_out.mu, layer_out.log_var
                 y = y * s.exp() + m
                 sum_log_abs_det_jac += s.sum(dim=-1)
diff --git a/src/pythae/models/normalizing_flows/layers.py b/src/pythae/models/normalizing_flows/layers.py
index aa410c0d..6ea0060d 100644
--- a/src/pythae/models/normalizing_flows/layers.py
+++ b/src/pythae/models/normalizing_flows/layers.py
@@ -17,13 +17,20 @@ class MaskedLinear(nn.Linear):
     only a selection of weight.
     """
 
-    def __init__(self, in_features, out_features, mask):
+    def __init__(self, in_features, out_features, mask, context_features=None):
         nn.Linear.__init__(self, in_features=in_features, out_features=out_features)
 
         self.register_buffer("mask", mask)
 
-    def forward(self, x):
-        return F.linear(x, self.mask * self.weight, self.bias)
+        if context_features is not None:
+            self.context_linear = nn.Linear(context_features, out_features, bias=False)
+
+    def forward(self, x, h=None):
+        out = F.linear(x, self.mask * self.weight, self.bias)
+        if h is None:
+            return out
+        else:
+            return out + self.context_linear(h)
 
 
 class BatchNorm(nn.Module):
diff --git a/src/pythae/models/normalizing_flows/made/made_config.py b/src/pythae/models/normalizing_flows/made/made_config.py
index 9ab312c2..d6bcecb7 100644
--- a/src/pythae/models/normalizing_flows/made/made_config.py
+++ b/src/pythae/models/normalizing_flows/made/made_config.py
@@ -18,8 +18,10 @@ class MADEConfig(BaseNFConfig):
             Default: [128].
         degrees_ordering (str): The ordering to use for the mask creation. Can be either
             `sequential` or `random`. Default: `sequential`.
+        context_dim (tuple): The dimension of the context. Default: None.
     """
 
     output_dim: Union[Tuple[int, ...], None] = None
     hidden_sizes: List[int] = field(default_factory=lambda: [128])
     degrees_ordering: Literal["sequential", "random"] = "sequential"
+    context_dim: Union[Tuple[int, ...], None] = None
diff --git a/src/pythae/models/normalizing_flows/made/made_model.py b/src/pythae/models/normalizing_flows/made/made_model.py
index 191e703d..6a8f5eec 100644
--- a/src/pythae/models/normalizing_flows/made/made_model.py
+++ b/src/pythae/models/normalizing_flows/made/made_model.py
@@ -29,6 +29,7 @@ def __init__(self, model_config: MADEConfig):
         self.input_dim = np.prod(model_config.input_dim)
         self.output_dim = np.prod(model_config.output_dim)
         self.hidden_sizes = model_config.hidden_sizes
+        self.context_dim = np.prod(model_config.context_dim)
         self.model_name = "MADE"
 
         if model_config.input_dim is None:
@@ -47,11 +48,18 @@ def __init__(self, model_config: MADEConfig):
                 "automatically"
             )
 
-        hidden_sizes = [self.input_dim] + model_config.hidden_sizes + [self.output_dim]
+        hidden_sizes = model_config.hidden_sizes + [self.output_dim]
 
         masks = self._make_mask(ordering=self.model_config.degrees_ordering)
 
-        for inp, out, mask in zip(hidden_sizes[:-1], hidden_sizes[1:-1], masks[:-1]):
+        self.context_input_layer = MaskedLinear(
+            self.input_dim,
+            hidden_sizes[0],
+            masks[0],
+            context_features=self.context_dim,
+        )
+
+        for inp, out, mask in zip(hidden_sizes[:-1], hidden_sizes[1:-1], masks[1:-1]):
 
             self.net.extend([MaskedLinear(inp, out, mask), nn.ReLU()])
 
@@ -69,14 +77,22 @@ def __init__(self, model_config: MADEConfig):
     def _make_mask(self, ordering="sequential"):
 
         # Get degrees for mask creation
-
+        self.m[-1] = torch.arange(1, self.input_dim + 1)
         if ordering == "sequential":
-            self.m[-1] = torch.arange(self.input_dim)
             for i in range(len(self.hidden_sizes)):
-                self.m[i] = torch.arange(self.hidden_sizes[i]) % (self.input_dim - 1)
+                min_deg = min(torch.min(self.m[i - 1]), self.input_dim - 1)
+                self.m[i] = np.maximum(
+                    min_deg,
+                    np.ceil(
+                        np.arange(1, self.hidden_sizes[i] + 1)
+                        * (self.input_dim - 1)
+                        / float(self.hidden_sizes[i] + 1)
+                    ).astype(np.int32),
+                )
 
         else:
-            self.m[-1] = torch.randperm(self.input_dim)
+            idx = torch.randperm(self.input_dim)
+            self.m[-1] = self.m[-1][idx]
             for i in range(len(self.hidden_sizes)):
                 self.m[i] = torch.randint(
                     self.m[-1].min(), self.input_dim - 1, (self.hidden_sizes[i],)
@@ -95,16 +111,18 @@ def _make_mask(self, ordering="sequential"):
 
         return masks
 
-    def forward(self, x: torch.tensor, **kwargs) -> ModelOutput:
+    def forward(self, x: torch.tensor, h=None, **kwargs) -> ModelOutput:
         """The input data is transformed toward the prior
 
         Args:
-            inputs (torch.Tensor): An input tensor
+            x (torch.Tensor): An input tensor.
+            h (torch.Tensor): The context tensor. Default: None.
 
         Returns:
             ModelOutput: An instance of ModelOutput containing all the relevant parameters
         """
-        net_output = self.net(x.reshape(x.shape[0], -1))
+        out = self.context_input_layer(x.reshape(x.shape[0], -1), h)
+        net_output = self.net(out)
 
         mu = net_output[:, : self.input_dim]
         log_var = net_output[:, self.input_dim :]
diff --git a/src/pythae/models/normalizing_flows/maf/maf_config.py b/src/pythae/models/normalizing_flows/maf/maf_config.py
index 1203e8af..0309d61d 100644
--- a/src/pythae/models/normalizing_flows/maf/maf_config.py
+++ b/src/pythae/models/normalizing_flows/maf/maf_config.py
@@ -1,3 +1,5 @@
+from typing import Union
+
 from pydantic.dataclasses import dataclass
 
 from ..base import BaseNFConfig
@@ -9,15 +11,17 @@ class MAFConfig(BaseNFConfig):
 
     Parameters:
         input_dim (tuple): The input data dimension. Default: None.
-        n_made_blocks (int): The number of MADE model to consider in the MAF. Default: 2.
+        n_blocks (int): The number of MAF blocks to consider in the flow. Default: 2.
         n_hidden_in_made (int): The number of hidden layers in the MADE models. Default: 3.
         hidden_size (list): The number of unit in each hidder layer. The same number of units is
-            used across the `n_hidden_in_made` and `n_made_blocks`
+            used across the `n_hidden_in_made` and `n_blocks`
+        context_dim (int): The dimension of the context. Default: None.
         include_batch_norm (bool): Whether to include batch normalization after each
             :class:`~pythae.models.normalizing_flows.MADE` layers. Default: False.
     """
 
-    n_made_blocks: int = 2
+    n_blocks: int = 2
     n_hidden_in_made: int = 3
+    context_dim: Union[int, None] = None
     hidden_size: int = 128
     include_batch_norm: bool = False
diff --git a/src/pythae/models/normalizing_flows/maf/maf_model.py b/src/pythae/models/normalizing_flows/maf/maf_model.py
index 1b2f11f2..0ad19024 100644
--- a/src/pythae/models/normalizing_flows/maf/maf_model.py
+++ b/src/pythae/models/normalizing_flows/maf/maf_model.py
@@ -26,6 +26,7 @@ def __init__(self, model_config: MAFConfig):
         self.m = {}
         self.model_config = model_config
         self.hidden_size = model_config.hidden_size
+        self.context_dim = model_config.context_dim
 
         self.model_name = "MAF"
 
@@ -34,20 +35,22 @@ def __init__(self, model_config: MAFConfig):
             output_dim=(self.input_dim,),
             hidden_sizes=[self.hidden_size] * self.model_config.n_hidden_in_made,
             degrees_ordering="sequential",
+            context_dim=(self.context_dim,) if self.context_dim is not None else None,
         )
 
-        for i in range(model_config.n_made_blocks):
+        for i in range(model_config.n_blocks):
             self.net.extend([MADE(made_config)])
             if self.model_config.include_batch_norm:
                 self.net.extend([BatchNorm(self.input_dim)])
 
         self.net = nn.ModuleList(self.net)
 
-    def forward(self, x: torch.Tensor, **kwargs) -> ModelOutput:
+    def forward(self, x: torch.Tensor, h: torch.Tensor = None, **kwargs) -> ModelOutput:
         """The input data is transformed toward the prior
 
         Args:
-            inputs (torch.Tensor): An input tensor
+            x (torch.Tensor): An input tensor.
+            h (torch.Tensor): The context tensor. Default: None.
 
         Returns:
             ModelOutput: An instance of ModelOutput containing all the relevant parameters
@@ -57,14 +60,15 @@ def forward(self, x: torch.Tensor, **kwargs) -> ModelOutput:
         sum_log_abs_det_jac = torch.zeros(x.shape[0]).to(x.device)
 
         for layer in self.net:
-            layer_out = layer(x)
             if layer.__class__.__name__ == "MADE":
+                layer_out = layer(x, h)
                 mu, log_var = layer_out.mu, layer_out.log_var
 
                 x = (x - mu) * (-log_var).exp()
                 sum_log_abs_det_jac += -log_var.sum(dim=-1)  # - alpha
 
             else:
+                layer_out = layer(x)
                 x = layer_out.out
                 sum_log_abs_det_jac += layer_out.log_abs_det_jac
 
@@ -72,11 +76,12 @@ def forward(self, x: torch.Tensor, **kwargs) -> ModelOutput:
 
         return ModelOutput(out=x, log_abs_det_jac=sum_log_abs_det_jac)
 
-    def inverse(self, y: torch.Tensor, **kwargs) -> ModelOutput:
+    def inverse(self, y: torch.Tensor, h: torch.Tensor = None, **kwargs) -> ModelOutput:
         """The prior is transformed toward the input data
 
         Args:
-            inputs (torch.Tensor): An input tensor
+            x (torch.Tensor): An input tensor.
+            h (torch.Tensor): The context tensor. Default: None.
 
         Returns:
             ModelOutput: An instance of ModelOutput containing all the relevant parameters
@@ -90,7 +95,7 @@ def inverse(self, y: torch.Tensor, **kwargs) -> ModelOutput:
             if layer.__class__.__name__ == "MADE":
                 x = torch.zeros_like(y)
                 for i in range(self.input_dim):
-                    layer_out = layer(x.clone())
+                    layer_out = layer(x.clone(), h=h)
 
                     mu, log_var = layer_out.mu, layer_out.log_var
 
diff --git a/src/pythae/models/normalizing_flows/planar_flow/planar_flow_model.py b/src/pythae/models/normalizing_flows/planar_flow/planar_flow_model.py
index 4ef15611..e821ec99 100644
--- a/src/pythae/models/normalizing_flows/planar_flow/planar_flow_model.py
+++ b/src/pythae/models/normalizing_flows/planar_flow/planar_flow_model.py
@@ -44,7 +44,7 @@ def forward(self, x: torch.Tensor, **kwargs) -> ModelOutput:
         """The input data is transformed toward the prior
 
         Args:
-            inputs (torch.Tensor): An input tensor
+            x (torch.Tensor): An input tensor.
 
         Returns:
             ModelOutput: An instance of ModelOutput containing all the relevant parameters
diff --git a/src/pythae/models/normalizing_flows/radial_flow/radial_flow_model.py b/src/pythae/models/normalizing_flows/radial_flow/radial_flow_model.py
index 4f2b9e5a..2339e172 100644
--- a/src/pythae/models/normalizing_flows/radial_flow/radial_flow_model.py
+++ b/src/pythae/models/normalizing_flows/radial_flow/radial_flow_model.py
@@ -33,7 +33,7 @@ def forward(self, x: torch.Tensor, **kwargs) -> ModelOutput:
         """The input data is transformed toward the prior
 
         Args:
-            inputs (torch.Tensor): An input tensor
+            inputs (torch.Tensor): An input tensor.
 
         Returns:
             ModelOutput: An instance of ModelOutput containing all the relevant parameters
diff --git a/src/pythae/models/vae_iaf/vae_iaf_config.py b/src/pythae/models/vae_iaf/vae_iaf_config.py
index 56046741..14cae7d2 100644
--- a/src/pythae/models/vae_iaf/vae_iaf_config.py
+++ b/src/pythae/models/vae_iaf/vae_iaf_config.py
@@ -1,3 +1,5 @@
+from typing import Union
+
 from pydantic.dataclasses import dataclass
 
 from ..vae import VAEConfig
@@ -11,16 +13,18 @@ class VAE_IAF_Config(VAEConfig):
         input_dim (int): The input_data dimension
         latent_dim (int): The latent space dimension. Default: None.
         reconstruction_loss (str): The reconstruction loss to use ['bce', 'mse']. Default: 'mse'.
-        n_made_blocks (int): The number of :class:`~pythae.models.normalizing_flows.MADE` models
-            to consider in the IAF used in the VAE. Default: 2.
+        n_blocks (int): The number of :class:`~pythae.models.normalizing_flows.IAF` blocks
+            to consider in the VAE. Default: 2.
         n_hidden_in_made (int): The number of hidden layers in the
             :class:`~pythae.models.normalizing_flows.MADE` models composing the IAF in the VAE.
             Default: 3.
         hidden_size (list): The number of unit in each hidder layerin the
             :class:`~pythae.models.normalizing_flows.MADE` model. The same number of
-            units is used across the `n_hidden_in_made` and `n_made_blocks`. Default: 128.
+            units is used across the `n_hidden_in_made` and `n_blocks`. Default: 128.
+        context_dim (tuple): The dimension of the context. Default: None.
     """
 
-    n_made_blocks: int = 2
+    n_blocks: int = 2
     n_hidden_in_made: int = 3
     hidden_size: int = 128
+    context_dim: Union[int, None] = None
diff --git a/src/pythae/models/vae_iaf/vae_iaf_model.py b/src/pythae/models/vae_iaf/vae_iaf_model.py
index 37c646c8..64ae1f53 100644
--- a/src/pythae/models/vae_iaf/vae_iaf_model.py
+++ b/src/pythae/models/vae_iaf/vae_iaf_model.py
@@ -49,9 +49,10 @@ def __init__(
 
         iaf_config = IAFConfig(
             input_dim=(model_config.latent_dim,),
-            n_made_blocks=model_config.n_made_blocks,
+            n_blocks=model_config.n_blocks,
             n_hidden_in_made=model_config.n_hidden_in_made,
             hidden_size=model_config.hidden_size,
+            context_dim=model_config.context_dim,
             include_batch_norm=False,
         )
 
@@ -80,8 +81,23 @@ def forward(self, inputs: BaseDataset, **kwargs):
 
         z0 = z
 
-        # Pass it through the Normalizing flows
-        flow_output = self.iaf_flow.inverse(z)  # sampling
+        if self.iaf_flow.context_dim is not None:
+            try:
+                h = encoder_output.context
+
+            except AttributeError as e:
+                raise AttributeError(
+                    "Cannot get context from encoder outputs. If you set `context_dim` argument to "
+                    "something different from None please ensure that the encoder actually outputs "
+                    f"the context vector 'h'. Exception caught: {e}."
+                )
+
+            # Pass it through the Normalizing flows
+            flow_output = self.iaf_flow.inverse(z, h=h)  # sampling
+
+        else:
+            # Pass it through the Normalizing flows
+            flow_output = self.iaf_flow.inverse(z)  # sampling
 
         z = flow_output.out
         log_abs_det_jac = flow_output.log_abs_det_jac
diff --git a/src/pythae/samplers/iaf_sampler/iaf_sampler.py b/src/pythae/samplers/iaf_sampler/iaf_sampler.py
index a544b5ae..a61f5dc7 100644
--- a/src/pythae/samplers/iaf_sampler/iaf_sampler.py
+++ b/src/pythae/samplers/iaf_sampler/iaf_sampler.py
@@ -44,7 +44,7 @@ def __init__(self, model: BaseAE, sampler_config: IAFSamplerConfig = None):
 
         iaf_config = IAFConfig(
             input_dim=(model.model_config.latent_dim,),
-            n_made_blocks=sampler_config.n_made_blocks,
+            n_blocks=sampler_config.n_blocks,
             n_hidden_in_made=sampler_config.n_hidden_in_made,
             hidden_size=sampler_config.hidden_size,
             include_batch_norm=sampler_config.include_batch_norm,
diff --git a/src/pythae/samplers/iaf_sampler/iaf_sampler_config.py b/src/pythae/samplers/iaf_sampler/iaf_sampler_config.py
index b915c64f..6af2d253 100644
--- a/src/pythae/samplers/iaf_sampler/iaf_sampler_config.py
+++ b/src/pythae/samplers/iaf_sampler/iaf_sampler_config.py
@@ -8,15 +8,15 @@ class IAFSamplerConfig(BaseSamplerConfig):
     """This is the IAF sampler model configuration instance.
 
     Parameters:
-        n_made_blocks (int): The number of MADE model to consider in the IAF. Default: 2.
+        n_blocks (int): The number of IAF blocks to consider in the flow. Default: 2.
         n_hidden_in_made (int): The number of hidden layers in the MADE models. Default: 3.
         hidden_size (list): The number of unit in each hidder layer. The same number of units is
-            used across the `n_hidden_in_made` and `n_made_blocks`
+            used across the `n_hidden_in_made` and `n_blocks`
         include_batch_norm (bool): Whether to include batch normalization after each
             :class:`~pythae.models.normalizing_flows.MADE` layers. Default: False.
     """
 
-    n_made_blocks: int = 2
+    n_blocks: int = 2
     n_hidden_in_made: int = 3
     hidden_size: int = 128
     include_batch_norm: bool = False
diff --git a/src/pythae/samplers/maf_sampler/maf_sampler.py b/src/pythae/samplers/maf_sampler/maf_sampler.py
index bd303ba9..985f9b31 100644
--- a/src/pythae/samplers/maf_sampler/maf_sampler.py
+++ b/src/pythae/samplers/maf_sampler/maf_sampler.py
@@ -44,7 +44,7 @@ def __init__(self, model: BaseAE, sampler_config: MAFSamplerConfig = None):
 
         maf_config = MAFConfig(
             input_dim=(model.model_config.latent_dim,),
-            n_made_blocks=sampler_config.n_made_blocks,
+            n_blocks=sampler_config.n_blocks,
             n_hidden_in_made=sampler_config.n_hidden_in_made,
             hidden_size=sampler_config.hidden_size,
             include_batch_norm=sampler_config.include_batch_norm,
diff --git a/src/pythae/samplers/maf_sampler/maf_sampler_config.py b/src/pythae/samplers/maf_sampler/maf_sampler_config.py
index 64bab067..b057a749 100644
--- a/src/pythae/samplers/maf_sampler/maf_sampler_config.py
+++ b/src/pythae/samplers/maf_sampler/maf_sampler_config.py
@@ -8,15 +8,15 @@ class MAFSamplerConfig(BaseSamplerConfig):
     """This is the MAF sampler model configuration instance.
 
     Parameters:
-        n_made_blocks (int): The number of MADE model to consider in the MAF. Default: 2.
+        n_blocks (int): The number of MAF blocks to consider in the flow. Default: 2.
         n_hidden_in_made (int): The number of hidden layers in the MADE models. Default: 3.
         hidden_size (list): The number of unit in each hidder layer. The same number of units is
-            used across the `n_hidden_in_made` and `n_made_blocks`
+            used across the `n_hidden_in_made` and `n_blocks`
         include_batch_norm (bool): Whether to include batch normalization after each
             :class:`~pythae.models.normalizing_flows.MADE` layers. Default: False.
     """
 
-    n_made_blocks: int = 2
+    n_blocks: int = 2
     n_hidden_in_made: int = 3
     hidden_size: int = 128
     include_batch_norm: bool = False
diff --git a/src/pythae/trainers/training_callbacks.py b/src/pythae/trainers/training_callbacks.py
index 5bb70f60..359e6afb 100644
--- a/src/pythae/trainers/training_callbacks.py
+++ b/src/pythae/trainers/training_callbacks.py
@@ -15,9 +15,11 @@
 def wandb_is_available():
     return importlib.util.find_spec("wandb") is not None
 
+
 def mlflow_is_available():
     return importlib.util.find_spec("mlflow") is not None
 
+
 def rename_logs(logs):
     train_prefix = "train_"
     eval_prefix = "eval_"
@@ -356,6 +358,7 @@ def on_prediction_step(self, training_config, **kwargs):
     def on_train_end(self, training_config: BaseTrainerConfig, **kwargs):
         self.run.finish()
 
+
 class MLFlowCallback(TrainingCallback):  # pragma: no cover
     def __init__(self):
         if not mlflow_is_available():
@@ -378,7 +381,9 @@ def setup(self, training_config, **kwargs):
 
         self._mlflow.start_run(run_name=run_name)
 
-        logger.info(f"MLflow run started with run_id={self._mlflow.active_run().info.run_id}")
+        logger.info(
+            f"MLflow run started with run_id={self._mlflow.active_run().info.run_id}"
+        )
         if model_config is not None:
             model_config_dict = model_config.to_dict()
 
@@ -418,4 +423,4 @@ def __del__(self):
             callable(getattr(self._mlflow, "active_run", None))
             and self._mlflow.active_run() is not None
         ):
-            self._mlflow.end_run()
\ No newline at end of file
+            self._mlflow.end_run()
diff --git a/tests/data/custom_architectures.py b/tests/data/custom_architectures.py
index 0b086b1e..373319a2 100644
--- a/tests/data/custom_architectures.py
+++ b/tests/data/custom_architectures.py
@@ -96,6 +96,7 @@ def __init__(self, args):
         self.input_dim = args.input_dim
         self.latent_dim = args.latent_dim
         self.n_channels = 1
+        self.outputs_context = False
 
         layers = nn.ModuleList()
 
@@ -131,6 +132,10 @@ def __init__(self, args):
         self.embedding = nn.Linear(512, self.latent_dim)
         self.log_var = nn.Linear(512, self.latent_dim)
 
+        if hasattr(args, "context_dim") and args.context_dim is not None:
+            self.outputs_context = True
+            self.context_layer = nn.Linear(512, args.context_dim)
+
     def forward(self, x: torch.Tensor, output_layer_levels: List[int] = None):
         output = ModelOutput()
 
@@ -163,6 +168,8 @@ def forward(self, x: torch.Tensor, output_layer_levels: List[int] = None):
             if i + 1 == self.depth:
                 output["embedding"] = self.embedding(out.reshape(x.shape[0], -1))
                 output["log_covariance"] = self.log_var(out.reshape(x.shape[0], -1))
+                if self.outputs_context:
+                    output["context"] = self.context_layer(out.reshape(x.shape[0], -1))
 
         return output
 
diff --git a/tests/test_IAF.py b/tests/test_IAF.py
index 0116f458..2ac4132d 100644
--- a/tests/test_IAF.py
+++ b/tests/test_IAF.py
@@ -20,7 +20,7 @@
 PATH = os.path.dirname(os.path.abspath(__file__))
 
 
-@pytest.fixture(params=[IAFConfig(n_hidden_in_made=10), IAFConfig(n_made_blocks=2)])
+@pytest.fixture(params=[IAFConfig(n_hidden_in_made=10), IAFConfig(n_blocks=2)])
 def model_configs_no_input_output_dim(request):
     return request.param
 
@@ -28,13 +28,13 @@ def model_configs_no_input_output_dim(request):
 @pytest.fixture(
     params=[
         IAFConfig(
-            input_dim=(1, 8, 2), n_made_blocks=2, n_hidden_in_made=1, hidden_size=3
+            input_dim=(1, 8, 2), n_blocks=2, n_hidden_in_made=1, hidden_size=3
         ),
         IAFConfig(
             input_dim=(1, 2, 18),
             hidden_size=12,
             include_batch_norm=True,
-            n_made_blocks=1,
+            n_blocks=1,
         ),
     ]
 )
@@ -188,7 +188,7 @@ def training_configs(self, tmpdir, request):
     @pytest.fixture(
         params=[
             IAFConfig(
-                input_dim=(12,), n_made_blocks=3, n_hidden_in_made=3, hidden_size=134
+                input_dim=(12,), n_blocks=3, n_hidden_in_made=3, hidden_size=134
             ),
         ]
     )
diff --git a/tests/test_MAF.py b/tests/test_MAF.py
index 720dd671..54283aed 100644
--- a/tests/test_MAF.py
+++ b/tests/test_MAF.py
@@ -19,14 +19,14 @@
 PATH = os.path.dirname(os.path.abspath(__file__))
 
 
-@pytest.fixture(params=[MAFConfig(n_hidden_in_made=10), MAFConfig(n_made_blocks=2)])
+@pytest.fixture(params=[MAFConfig(n_hidden_in_made=10), MAFConfig(n_blocks=2)])
 def model_configs_no_input_output_dim(request):
     return request.param
 
 
 @pytest.fixture(
     params=[
-        MAFConfig(input_dim=(1, 8, 2), n_made_blocks=2, n_hidden_in_made=1),
+        MAFConfig(input_dim=(1, 8, 2), n_blocks=2, n_hidden_in_made=1),
         MAFConfig(input_dim=(1, 2, 18), hidden_size=12, include_batch_norm=True),
     ]
 )
@@ -180,7 +180,7 @@ def training_configs(self, tmpdir, request):
     @pytest.fixture(
         params=[
             MAFConfig(
-                input_dim=(784,), n_made_blocks=3, n_hidden_in_made=3, hidden_size=134
+                input_dim=(784,), n_blocks=3, n_hidden_in_made=3, hidden_size=134
             ),
         ]
     )
diff --git a/tests/test_VAE_IAF.py b/tests/test_VAE_IAF.py
index 09eb68ca..ede10755 100644
--- a/tests/test_VAE_IAF.py
+++ b/tests/test_VAE_IAF.py
@@ -31,9 +31,10 @@ def model_configs_no_input_dim(request):
         VAE_IAF_Config(
             input_dim=(1, 28),
             latent_dim=5,
-            n_made_blocks=1,
+            n_blocks=1,
             n_hidden_in_made=2,
             hidden_size=142,
+            context_dim=15
         ),
     ]
 )
@@ -280,6 +281,18 @@ def vae(self, model_configs, demo_data):
         model_configs.input_dim = tuple(demo_data["data"][0].shape)
         return VAE_IAF(model_configs)
 
+    def test_raises_no_context(self, model_configs, demo_data):
+
+        # Set context to None to build wrong encoder
+        model_configs.context_dim = None
+        bad_enc = Encoder_VAE_Conv(model_configs)
+        model_configs.context_dim = 12
+        model_configs.input_dim = tuple(demo_data["data"][0].shape)
+        vae = VAE_IAF(model_configs, encoder=bad_enc)
+
+        with pytest.raises(AttributeError):
+            out = vae(demo_data)
+
     def test_model_train_output(self, vae, demo_data):
 
         vae.train()
diff --git a/tests/test_iaf_sampler.py b/tests/test_iaf_sampler.py
index eff123de..4d4ded76 100644
--- a/tests/test_iaf_sampler.py
+++ b/tests/test_iaf_sampler.py
@@ -30,7 +30,7 @@ def model(request):
 
 @pytest.fixture(
     params=[
-        IAFSamplerConfig(n_made_blocks=2, n_hidden_in_made=1),
+        IAFSamplerConfig(n_blocks=2, n_hidden_in_made=1),
         IAFSamplerConfig(hidden_size=12, include_batch_norm=True),
         None,
     ]
diff --git a/tests/test_maf_sampler.py b/tests/test_maf_sampler.py
index 03af31a5..39d614eb 100644
--- a/tests/test_maf_sampler.py
+++ b/tests/test_maf_sampler.py
@@ -30,7 +30,7 @@ def model(request):
 
 @pytest.fixture(
     params=[
-        MAFSamplerConfig(n_made_blocks=2, n_hidden_in_made=1),
+        MAFSamplerConfig(n_blocks=2, n_hidden_in_made=1),
         MAFSamplerConfig(hidden_size=12, include_batch_norm=True),
         None,
     ]
diff --git a/tests/test_nn_benchmark.py b/tests/test_nn_benchmark.py
index e19c494a..4e263058 100644
--- a/tests/test_nn_benchmark.py
+++ b/tests/test_nn_benchmark.py
@@ -114,6 +114,7 @@ def test_ae_encoding_decoding_default(
     def test_vae_encoding_decoding_default(
         self, ae_mnist_config, mnist_like_data, recon_layers_default
     ):
+        ae_mnist_config.context_dim = 12
         encoder = Encoder_VAE_MLP(ae_mnist_config).to(device)
         decoder = Decoder_AE_MLP(ae_mnist_config).to(device)
 
@@ -129,6 +130,11 @@ def test_vae_encoding_decoding_default(
             ae_mnist_config.latent_dim,
         )
 
+        assert output.context.shape == (
+            mnist_like_data.shape[0],
+            ae_mnist_config.context_dim,
+        )
+
         reconstruction = decoder(embedding).reconstruction
 
         assert reconstruction.shape == mnist_like_data.shape
@@ -352,6 +358,7 @@ def test_ae_encoding_decoding(
     def test_vae_encoding_decoding(
         self, ae_mnist_config, mnist_like_data, recon_layers
     ):
+        ae_mnist_config.context_dim = 12
         encoder = Encoder_Conv_VAE_MNIST(ae_mnist_config).to(device)
         decoder = Decoder_Conv_AE_MNIST(ae_mnist_config).to(device)
 
@@ -367,6 +374,11 @@ def test_vae_encoding_decoding(
             ae_mnist_config.latent_dim,
         )
 
+        assert output.context.shape == (
+            mnist_like_data.shape[0],
+            ae_mnist_config.context_dim,
+        )
+
         reconstruction = decoder(embedding).reconstruction
 
         assert reconstruction.shape == mnist_like_data.shape
@@ -631,12 +643,21 @@ def test_ae_encoding_decoding(
     def test_vae_encoding_decoding(
         self, ae_mnist_config, mnist_like_data, recon_layers
     ):
+        ae_mnist_config.context_dim = 12
         encoder = Encoder_ResNet_VAE_MNIST(ae_mnist_config).to(device)
         decoder = Decoder_ResNet_AE_MNIST(ae_mnist_config).to(device)
 
-        embedding = encoder(mnist_like_data).embedding
+        encoder_output = encoder(mnist_like_data)
+
+        embedding, log_covariance = encoder_output.embedding, encoder_output.log_covariance 
 
         assert embedding.shape == (mnist_like_data.shape[0], ae_mnist_config.latent_dim)
+        assert log_covariance.shape == (mnist_like_data.shape[0], ae_mnist_config.latent_dim)
+
+        assert encoder_output.context.shape == (
+            mnist_like_data.shape[0],
+            ae_mnist_config.context_dim,
+        )
 
         reconstruction = decoder(embedding).reconstruction
 
@@ -923,6 +944,7 @@ def test_ae_encoding_decoding(self, ae_cifar_config, cifar_like_data, recon_laye
     def test_vae_encoding_decoding(
         self, ae_cifar_config, cifar_like_data, recon_layers
     ):
+        ae_cifar_config.context_dim = 12
         encoder = Encoder_Conv_VAE_CIFAR(ae_cifar_config).to(device)
         decoder = Decoder_Conv_AE_CIFAR(ae_cifar_config).to(device)
 
@@ -937,6 +959,10 @@ def test_vae_encoding_decoding(
             cifar_like_data.shape[0],
             ae_cifar_config.latent_dim,
         )
+        assert output.context.shape == (
+            cifar_like_data.shape[0],
+            ae_cifar_config.context_dim,
+        )
 
         reconstruction = decoder(embedding).reconstruction
 
@@ -1201,12 +1227,21 @@ def test_ae_encoding_decoding(
     def test_vae_encoding_decoding(
         self, ae_cifar_config, cifar_like_data, recon_layers
     ):
+        ae_cifar_config.context_dim = 12
         encoder = Encoder_ResNet_VAE_CIFAR(ae_cifar_config).to(device)
         decoder = Decoder_ResNet_AE_CIFAR(ae_cifar_config).to(device)
 
-        embedding = encoder(cifar_like_data).embedding
+        encoder_output = encoder(cifar_like_data)
+
+        embedding, log_covariance = encoder_output.embedding, encoder_output.log_covariance 
 
         assert embedding.shape == (cifar_like_data.shape[0], ae_cifar_config.latent_dim)
+        assert log_covariance.shape == (cifar_like_data.shape[0], ae_cifar_config.latent_dim)
+
+        assert encoder_output.context.shape == (
+            cifar_like_data.shape[0],
+            ae_cifar_config.context_dim,
+        )
 
         reconstruction = decoder(embedding).reconstruction
 
@@ -1491,6 +1526,7 @@ def test_ae_encoding_decoding(
     def test_vae_encoding_decoding(
         self, ae_celeba_config, celeba_like_data, recon_layers
     ):
+        ae_celeba_config.context_dim = 12
         encoder = Encoder_Conv_VAE_CELEBA(ae_celeba_config).to(device)
         decoder = Decoder_Conv_AE_CELEBA(ae_celeba_config).to(device)
 
@@ -1505,6 +1541,10 @@ def test_vae_encoding_decoding(
             celeba_like_data.shape[0],
             ae_celeba_config.latent_dim,
         )
+        assert output.context.shape == (
+            celeba_like_data.shape[0],
+            ae_celeba_config.context_dim,
+        )
 
         reconstruction = decoder(embedding).reconstruction
 
@@ -1775,6 +1815,7 @@ def test_ae_encoding_decoding(
     def test_vae_encoding_decoding(
         self, ae_celeba_config, celeba_like_data, recon_layers
     ):
+        ae_celeba_config.context_dim = 12
         encoder = Encoder_ResNet_VAE_CELEBA(ae_celeba_config).to(device)
         decoder = Decoder_ResNet_AE_CELEBA(ae_celeba_config).to(device)
 
@@ -1789,6 +1830,10 @@ def test_vae_encoding_decoding(
             celeba_like_data.shape[0],
             ae_celeba_config.latent_dim,
         )
+        assert output.context.shape == (
+            celeba_like_data.shape[0],
+            ae_celeba_config.context_dim,
+        )
 
         reconstruction = decoder(embedding).reconstruction