{ "cells": [ { "cell_type": "markdown", "metadata": { "id": "VljrHRcPlq_z" }, "source": [ "# 2B - Representational Similarity with Story Reading fMRI data\n", "[![View filled on Github](https://img.shields.io/static/v1.svg?logo=github&label=Repo&message=View%20On%20Github&color=lightgrey)](https://github.com/annabavaresco/ancm2024/blob/main/docs/week_2/2B_RSA_with_fMRI_Data.ipynb)\n", "[![View filled in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/annabavaresco/ancm2024/blob/main/docs/week_2/2B_RSA_with_fMRI_Data.ipynb)\n", "\n", "_by Marianne de Heer Kloots, September 2022_\n", "\n", "---\n", "\n", "In the first part of this week's tutorial we saw how the structure of the embeddings space changes over model layers: the embeddings become more contextualized in deeper layers.\n", "\n", "Recent work comparing language model activations to human brain measurements suggests that these deeper and more contextualized layers align better with the brain than the earlier layers (for example [Caucheteux & King, 2022](https://doi.org/10.1038/s42003-022-03036-1); [Schrimpf et al., 2021](https://doi.org/10.1073/pnas.2105646118)). These studies use trained regression models to map from model activations to brain signals, but we can also use RSA to analyze the same phenomenon. Just as we computed the correlation of RDMs from different model layers before, we can now compute the correlation between model and brain RDMs. So is it true that embeddings from later model layers form more brain-like representational spaces, compared to earlier model layers?\n", "\n", "To answer this question, we'll use fMRI scans recorded from one subject in an experiment where subjects read a chapter from the first Harry Potter book ([Wehbe et al., 2014](https://doi.org/10.1371/journal.pone.0123148)). Participants in the experiment were presented with the chapter text through Rapid Serial Visual Presentation (RSVP), meaning that the words of the chapter appeared one by one on a screen, for 500 ms each. The brain scan TR (repetition time) was 2 seconds, meaning that every 2 seconds a 3d brain volume was recorded. This means that (almost\\*) every scan records the activity of reading 4 words. We'll therefore also average the embeddings over 4 words on the model side, in order to create so-called 'TR embeddings' that give us the same temporal resolution as we have from the participant. In addition, to account for the haemodynamic response delay\\**, we take the brain scan recorded 4 seconds (2 TRs) after each text presentation as the response to that text. Finally, we restrict ourselves to voxels recorded in the left anterior temporal lobe (LATL), which is generally known to be an important area for semantics and language processing (see e.g. [Bonner & Price, 2013](https://doi.org/10.1523/JNEUROSCI.0041-13.2013), [Bemis & Pylkkänen, 2013](https://doi.org/10.1093/cercor/bhs170)).\n", "\n", "_____\n", "\\* In practice, the experiment was divided into 4 blocks, and the last scan in each block contains reading activity for only 3 words. In the code below, we provide you with all 1295 TR texts (one on each line in the `tr_texts.txt` file) and the corresponding 1295 brain responses, so the inputs and recorded activations are aligned correctly.\n", "\n", "\\** The signal recorded in fMRI studies is the so-called Blood Oxygen Level Dependent (BOLD) response, which takes about [4-6 seconds](https://www.nature.com/scitable/blog/brain-metrics/what_does_fmri_measure/) after stimulus presentation to reach its peak. We choose 4 seconds here based on earlier work where we found this to work best for this dataset ([Abnar et al., 2019](https://aclanthology.org/W19-4820/); figure 6)." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "_Res-zZqlm6_", "outputId": "5ef4d11c-4bc0-4a07-920e-0fc5be63df41" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ " Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m10.4/10.4 MB\u001b[0m \u001b[31m23.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25h Building wheel for wget (setup.py) ... \u001b[?25l\u001b[?25hdone\n" ] } ], "source": [ "%%capture\n", "!pip -q install pathlib wget transformers nilearn" ] }, { "cell_type": "markdown", "metadata": { "id": "1I3EtnjmmG6f" }, "source": [ "For this part of the tutorial, we import some helper functions from Marianne's research code for dealing with the fMRI data. If you're curious to know what is going on under the hood, you can look up any specific function in the [fmri_data_loading.py](https://github.com/clclab/ANCM/blob/main/lab2/fmri_data_loading.py) file, or run a code cell with a function name followed by `?`. Although some of these functions have different names than the ones we used before, it should be clear that we will be following the same steps overall: computing distance matrices for different layers of our model (and now also for the brain), and then calculate the correlation between them for RSA." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "NDDfl3PsmC_B" }, "outputs": [], "source": [ "import wget\n", "import os\n", "\n", "if not os.path.exists('fmri_data_loading.py'):\n", " wget.download('https://raw.githubusercontent.com/clclab/ANCM/main/lab2/fmri_data_loading.py')\n", "tr_texts_file = 'tr_texts.txt'\n", "if not os.path.exists(tr_texts_file):\n", " wget.download('https://raw.githubusercontent.com/clclab/ANCM/main/lab2/tr_texts.txt')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "lMfwr3obmVL_" }, "outputs": [], "source": [ "from transformers import AutoModel, AutoTokenizer\n", "import nilearn.signal\n", "import copy\n", "import torch\n", "import numpy as np\n", "import matplotlib.pyplot as plt\n", "from fmri_data_loading import *" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 318, "referenced_widgets": [ "66ab70e2df7c46059adfc2bb11f58351", "1ac6f0d4fc9246fd83f8cd4786410923", "9612167f10df4021b0cea3801d2c6775", "45cbf543fa4c44f0bafce317e2540ff1", "8d30e1d8a0c040eca00f7e0753ef6365", "f1dbfe41d5d1460da49d220ac8001887", "d3e704478033467ca496b6589665a3a7", "9db88eeea7b640b2a53275ee9a817dcc", "d3d9926272004bf09383ed71ef4950ba", "64be3bc93eaf40c684ff5e20e6fe4602", "849d9eaeea8043c89c640260c9a6bc06", "2e28ef8ae068431fb889a05b99013dd8", "e859784c81c94b918bc6f7ceb2654dff", "d08ac99657294f878301d6b557ae42f1", "5a664cfcb8944bd3b1ded120fc7c02a0", "4acfdd1354d4419e9abbd15765478ba2", "b3857dd2378349c1b3cca864039a9ad8", "4552826de1b94795b538d21dbfb11565", "f556230db104493daf232bcde7414f82", "7523d49385b745a99a0461f997e57df8", "ec6e1fc04b0f4aaba7adfdd94bed17de", "a51d67530dd44e9ba2dec41bfa583c4a", "dff032f7adff4384887736627e95ae48", "0c06429c1c084ed182a108c4ba5a8df6", "125fcbfff304461894fb303a452a4ea3", "e211a8e743354e4a8383dbf95c409318", "d769b2b145ec4c6fb4512ca8eee03b04", "10f964364bf14f37a0b6368dcbba24a7", "ab2018b8d26e4b458997008a6e68e4ef", "4d8eba66d77944e1bead86786d8394bd", "5daa68ad4a234283a1c11b5186dab0d2", "4c30d2a75a2849eaa5660ccbd8e02d05", "1456ea33502b4e7e8983a80e83bd2d28", "13d3f3dca0fe432493efc7f0ad7343d6", "14d420c1d4bd4551a9ebb5436811d626", "32c8634bf147493582a7c89964b22b2e", "67e3f45d827d4b47b5e683c69f9e70bc", "8ffa2d196a284e73bb05a9ff103862ef", "bca42bf5e7c444d19cbc0717bfb7f4d6", "88b4d5c1c8224c7394e7ea1a78e962ee", "6128fb10cc314d4993556095e95ef42d", "f2ef79b2274845f2baaf884f9941e283", "2d2d94db4ae74a18a8c026bf6dfb7f69", "14f6db644cc143808bced8e0bfb39cea", "29241987ae854456b68c14ec7f47eb87", "15f8d58f0c274dd6a2af37658a06bec9", "2d1307f732974d4aa1026b880dc3e640", "cfb8eb3e1ebf4d91a3f52c030f3642cc", "1548d053930146bcb292299212a2e6ca", "d1219abffacb4374915cef08607d68d9", "c579f60b321849bfb06fb6ac7063b8c8", "19f9c85fb156441d9b926e495042955f", "1e6c7231ab2c4263ad98690e1ab9d850", "f8f45ae0fda04767829b7ab0f13f8ae9", "aa1996bf620246fcb5d77f38a3a85cdb" ] }, "id": "yWwuJiEBmRjj", "outputId": "a7c5f64e-51e1-4951-8422-0ddf15c8a1bf" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_token.py:89: UserWarning: \n", "The secret `HF_TOKEN` does not exist in your Colab secrets.\n", "To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.\n", "You will be able to reuse this secret in all of your notebooks.\n", "Please note that authentication is recommended but still optional to access public models or datasets.\n", " warnings.warn(\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "66ab70e2df7c46059adfc2bb11f58351", "version_major": 2, "version_minor": 0 }, "text/plain": [ "config.json: 0%| | 0.00/570 [00:00" ] }, "execution_count": 5, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# load the model and tokenizer\n", "model_name = 'bert-base-uncased'\n", "\n", "model = AutoModel.from_pretrained(model_name,\n", " output_hidden_states=True,\n", " output_attentions=True)\n", "\n", "# if you want to try a gpt-like model later,\n", "# we'll need these tokenizer settings\n", "if 'gpt' in model_name:\n", " tokenizer = AutoTokenizer.from_pretrained(model_name,\n", " add_prefix_space=True)\n", " tokenizer.pad_token = tokenizer.eos_token\n", "# but this will work for bert\n", "else:\n", " tokenizer = AutoTokenizer.from_pretrained(model_name)\n", "\n", "torch.set_grad_enabled(False)" ] }, { "cell_type": "markdown", "metadata": { "id": "K9MTS6bSnL6C" }, "source": [ "Below we download the data from subject 8 in the Wehbe et al. (2014) experiment. You can find more information on this dataset, as well as the data from other subjects, [here](http://www.cs.cmu.edu/~fmri/plosone/). In particular, a description of all the information available per subject is available [here](http://www.cs.cmu.edu/~fmri/plosone/files/description.txt) (the original data is stored in .mat files, which we convert to python dictionaries below, but they contain the same information; you can run the `load_subj_dict?` cell below to see more information about the structure of the dictionaries)." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "wehbenodnPd4" }, "outputs": [], "source": [ "load_subj_dict?" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "4JTv-7KunNwm" }, "outputs": [], "source": [ "# download data for subject 8\n", "subj_raw_file = 'subject_8.mat'\n", "if not os.path.exists(subj_raw_file):\n", " url = 'http://www.cs.cmu.edu/~fmri/plosone/files/subject_8.mat'\n", " wget.download(url)\n", "\n", "# load into python dictionary\n", "subj_dict = load_subj_dict(subj_raw_file)\n", "\n", "# preprocess fMRI signals\n", "subj_cleaned_file = 'subject_8_clean.npy'\n", "if not os.path.exists(subj_cleaned_file):\n", " # preprocessing parameters\n", " cleaning_params = {\n", " 't_r': 2, # TR length in seconds\n", " 'low_pass': None, # low-pass filter frequency cutoff (Hz)\n", " 'high_pass': 0.005, # high-pass filter frequency cutoff (Hz)\n", " 'standardize': 'zscore', # standardization method\n", " 'detrend': True, # whether to apply detrending\n", " }\n", "\n", " cleaned_subj_dict = copy.copy(subj_dict)\n", " cleaned_subj_dict['data'] = nilearn.signal.clean(subj_dict['data'],\n", " runs=subj_dict['time'][:,1],\n", " **cleaning_params)\n", " np.save(subj_cleaned_file, cleaned_subj_dict)\n", "subj_dict = np.load(subj_cleaned_file, allow_pickle=True).item()" ] }, { "cell_type": "markdown", "metadata": { "id": "xFsakITwnS4z" }, "source": [ "Below we select the regions of interest (ROIs) in the left anterior temporal lobe (LATL) from which we will retrieve the brain responses and construct the brain-side RDMs. You can later define another selection of ROIs yourself, if you like (run `subj_dict['meta']['ROInumToName']` to see a list of all available ROIs in this dataset, they are based on the [AAL Single-Subject atlas](https://www.pmod.com/files/download/v36/doc/pneuro/6750.htm))." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "KSxgQdASnTQC" }, "outputs": [], "source": [ "# subregions of left-anterior temporal lobe\n", "LATL_ROI = ['Temporal_Sup_L', 'Temporal_Pole_Sup_L',\n", " 'Temporal_Mid_L', 'Temporal_Pole_Mid_L', 'Temporal_Inf_L',\n", " 'Fusiform_L', 'ParaHippocampal_L']" ] }, { "cell_type": "markdown", "metadata": { "id": "T0GV1sXUnVcR" }, "source": [ "We now have the brain response scans for each of the 1295 text TRs; there are 4210 voxels in our LATL ROI selection." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "w2iBn6aHnWDy", "outputId": "5397c071-a377-47cb-9d50-dfd684fd835b" }, "outputs": [ { "data": { "text/plain": [ "(1295, 4210)" ] }, "execution_count": 10, "metadata": {}, "output_type": "execute_result" } ], "source": [ "brain_responses = get_text_response_scans(subj_dict,\n", " delay=2,\n", " ROI=LATL_ROI) # delay in TRs (1 TR = 2 sec)\n", "brain_responses['voxel_signals'].shape" ] }, { "cell_type": "markdown", "metadata": { "id": "yhcZXnqfnZp6" }, "source": [ "Below we load `tr_texts` (a list of texts, one for every TR containing the text presented during that TR), and we calculate the number of words presented during each TR (a list of mostly 4s and some 3s). We then split the text into sentences which we will present to our model to extract the embeddings. Note that for BERT, this means that the model will for some TRs have access to the words at the end of the sentence, which the experiment participant hadn't seen at the time the brain scan was recorded. If you'd like, you can try out different ways of providing input text to the model, for example a fixed text window for each TR excluding words presented after that TR (a way to 'make BERT causal' as discussed in the lecture)." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "f0swHZoKnXzz" }, "outputs": [], "source": [ "tr_texts = open(tr_texts_file, 'r').read().splitlines()\n", "words_per_tr = [len(tr.split(' ')) for tr in tr_texts]\n", "hp_sentences = create_context_sentences(tr_texts)" ] }, { "cell_type": "markdown", "metadata": { "id": "WWIqkX9zncGS" }, "source": [ "We process all sentences of the Harry Potter chapter through BERT, and extract the embeddings for each word at every layer. There are 5176 words and 13 'layers' (input embeddings + 12 model layers), which each have a 768-dimensional activation vector for every word." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "1SNyaleHndF6", "outputId": "ea0f98dc-6abf-4e73-c357-374eb10bd38e" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "BertSdpaSelfAttention is used but `torch.nn.functional.scaled_dot_product_attention` does not support non-absolute `position_embedding_type` or `output_attentions=True` or `head_mask`. Falling back to the manual attention implementation, but specifying the manual implementation will be required from Transformers version v5.0.0 onwards. This warning can be removed using the argument `attn_implementation=\"eager\"` when loading the model.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "(5176, 13, 768)\n", "CPU times: user 2min 52s, sys: 616 ms, total: 2min 53s\n", "Wall time: 2min 55s\n" ] } ], "source": [ "%%time\n", "# this will take a few minutes\n", "layer_acts_bert = get_layer_activations(model,\n", " tokenizer,\n", " hp_sentences)\n", "layer_acts_bert = np.concatenate(layer_acts_bert)\n", "print(layer_acts_bert.shape)" ] }, { "cell_type": "markdown", "metadata": { "id": "2wxIqqwQngFb" }, "source": [ "Then we average over the words in each TR to get the 'TR embeddings':" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "Dwf8l7RKnhQj", "outputId": "46aafb05-d42f-4480-a27e-7380e63e2dc8" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(1295, 13, 768)\n" ] } ], "source": [ "tr_embeddings_bert = get_tr_embeddings(layer_acts_bert, words_per_tr)\n", "print(tr_embeddings_bert.shape)" ] }, { "cell_type": "markdown", "metadata": { "id": "PcoLFRMfnikD" }, "source": [ "Now we have activations vectors for each of the 1295 text TRs for each layer of the model. We also have brain responses to each of the 1295 text TRs, so we can create RDMs for both! (13 RDMs for each layer of the model, and 1 RDM for subject 8's brain responses)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "yHhYtD04njMr", "outputId": "5efa6ca5-ee93-4198-bd51-a48b77254ae6" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "(1295, 1295)\n", "(1295, 1295)\n" ] } ], "source": [ "RDMs_bert = [vector_distance_matrix(tr_embeddings_bert[:,layer,:],\n", " metric=\"cosine\")\n", " for layer in range(tr_embeddings_bert.shape[1])]\n", "\n", "RDM_brain = vector_distance_matrix(brain_responses['voxel_signals'],\n", " metric=\"cosine\")\n", "\n", "print(RDMs_bert[0].shape) # one of the model RDMs\n", "print(RDM_brain.shape) # the brain RDM" ] }, { "cell_type": "markdown", "metadata": { "id": "idv84gWInmO0" }, "source": [ "We can compute the RSA score (Pearson's correlation) between each of the model layers and the brain responses now." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "OeEGzaHknmrb" }, "outputs": [], "source": [ "rsa_scores_bert = [compute_rsa_score(RDM_brain,\n", " RDMs_bert[layer],\n", " score=\"pearsonr\")\n", " for layer in range(len(RDMs_bert))]" ] }, { "cell_type": "markdown", "metadata": { "id": "NRnrxyUmnohb" }, "source": [ "As we see below, the correlation values themselves are quite low (they might get a bit higher if you provide the model with more context text). But we do observe the expected qualitative pattern: the higher layers with more contextualized embeddings score up to twice as high in representational similarity compared to lower layers." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 472 }, "id": "2BZ_SMrSno_M", "outputId": "c1e7521b-9ed1-4389-8ce5-e8f9630153ba" }, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAkgAAAHHCAYAAABEEKc/AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAAB4jklEQVR4nO3dd1xV5R8H8M/lMmUpG5SlorgARUVwYIniSCVNcRSuysqNVmq5GpKWpqnpTys1y9wrcyGOHCguFHIrywEIyPCy7z2/P4ibF1C5CJ4LfN6v130p5zz3nM/lMr485znPIxEEQQARERERKWmJHYCIiIhI07BAIiIiIiqBBRIRERFRCSyQiIiIiEpggURERERUAgskIiIiohJYIBERERGVwAKJiIiIqAQWSEREREQlsECiWksikWDu3LlqPy82NhYSiQTr1q17YduuXbuiZcuW6oerAHVyVaaKfh6fpazXMXfuXEgkkko7RzEnJyeMHDmy0o9LFVfV35fHjh2DRCLBsWPHKpSPag8WSCSqdevWQSKRQCKR4OTJk6X2C4IAe3t7SCQSvPHGGyIkpNrk6tWrmDt3LmJjY8WOQkQi0xY7ABEA6OvrY+PGjejUqZPK9uPHj+PevXvQ09MTKVn14ejoiJycHOjo6LzS8+bk5EBbu/J+lLzK13Hjxg1oaf33d+LVq1cxb948dO3aFU5OTlV+fiLSXOxBIo3Qu3dvbN26FYWFhSrbN27cCE9PT9jY2IiUTDy5ublQKBTlbi+RSKCvrw+pVFqFqUrT19ev1AKpql+HIAjIyckBAOjp6b3yglJsMplM7Aj0HHx/NAcLJNIIQ4cORWpqKkJDQ5Xb8vPzsW3bNgwbNqzM58hkMkydOhX29vbQ09ND06ZN8d1330EQBJV2eXl5mDJlCiwtLWFsbIx+/frh3r17ZR7z/v37GD16NKytraGnp4cWLVrgl19+eenXd+HCBfj4+MDAwADOzs5YtWqVyv7icRGbNm3C559/jvr166NOnTrIzMxEWloapk2bhlatWsHIyAgmJibo1asXLl++rHKMssZgjBw5EkZGRrh//z4CAgJgZGQES0tLTJs2DXK5/IW5z58/D39/f1hYWCizjx49WqVNyTEjxeOFbt68ibfffhumpqawtLTErFmzIAgCEhIS0L9/f5iYmMDGxgaLFi164esoy9q1a/H666/DysoKenp6aN68OVauXFmqnZOTE9544w0cPHgQbdu2hYGBAf73v/8p9xWPQVq3bh0GDRoEAHjttdeUl36PHTuGESNGwMLCAgUFBaWO36NHDzRt2vRFn0ps3boVnp6eMDAwgIWFBd5++23cv39fuf+7776DRCJBXFxcqefOmDEDurq6ePz4sXLb2bNn0bNnT5iamqJOnTrw9fXFqVOnVJ5X/F5cvXoVw4YNQ7169Ur10j6t+JL3yZMnMXHiRFhaWqJu3boYO3Ys8vPzkZ6ejqCgINSrVw/16tXDJ598Uur7rTp9XxY7ceIEBg0aBAcHB+jp6cHe3h5TpkxRFtJA0debRCLBpUuXSj1//vz5kEqlKu/ny74/iYmJGDVqFBo0aAA9PT3Y2tqif//+vPz7CrFAIo3g5OQEb29v/PHHH8pt+/fvR0ZGBoYMGVKqvSAI6NevH77//nv07NkTixcvRtOmTfHxxx8jODhYpe27776LJUuWoEePHvjmm2+go6ODPn36lDpmUlISOnTogMOHD2P8+PFYunQpGjdujDFjxmDJkiUVfm2PHz9G79694enpiYULF6JBgwb48MMPy/wB/+WXX+Kvv/7CtGnTMH/+fOjq6uLu3bvYtWsX3njjDSxevBgff/wxoqKi4OvriwcPHrzw/HK5HP7+/jA3N8d3330HX19fLFq0CKtXr37u85KTk9GjRw/ExsZi+vTpWLZsGYYPH44zZ86U63UHBgZCoVDgm2++gZeXF7766issWbIE3bt3R/369bFgwQI0btwY06ZNw99//12uYz5t5cqVcHR0xMyZM7Fo0SLY29vjo48+wooVK0q1vXHjBoYOHYru3btj6dKl8PDwKNWmS5cumDhxIgBg5syZ2LBhAzZs2IBmzZrhnXfeQWpqKg4ePKjynMTERBw5cgRvv/32c7OuW7cOgwcPhlQqRUhICN577z3s2LEDnTp1Qnp6OgBg8ODBkEgk2LJlS6nnb9myBT169EC9evUAAEeOHEGXLl2QmZmJOXPmYP78+UhPT8frr7+OiIiIUs8fNGgQsrOzMX/+fLz33nvPzQoAEyZMwK1btzBv3jz069cPq1evxqxZs9C3b1/I5XLMnz8fnTp1wrfffosNGzYon1edvi+ftnXrVmRnZ+PDDz/EsmXL4O/vj2XLliEoKEjZ5q233oKBgQF+//33Us///fff0bVrV9SvXx9A5bw/AwcOxM6dOzFq1Cj8+OOPmDhxIrKyshAfH18pr5nKQSAS0dq1awUAwrlz54Tly5cLxsbGQnZ2tiAIgjBo0CDhtddeEwRBEBwdHYU+ffoon7dr1y4BgPDVV1+pHO+tt94SJBKJcPv2bUEQBCEyMlIAIHz00Ucq7YYNGyYAEObMmaPcNmbMGMHW1lZISUlRaTtkyBDB1NRUmSsmJkYAIKxdu/aFr8/X11cAICxatEi5LS8vT/Dw8BCsrKyE/Px8QRAE4ejRowIAoWHDhsrzFMvNzRXkcrnKtpiYGEFPT0/44osvVLaVzDVixAgBgEo7QRCE1q1bC56ens/NvnPnTuV78zwlP49z5swRAAjvv/++clthYaHQoEEDQSKRCN98841y++PHjwUDAwNhxIgRz30dxcd8WsnPkyAIgr+/v9CwYUOVbY6OjgIA4cCBA6XaOzo6qpx769atAgDh6NGjKu3kcrnQoEEDITAwUGX74sWLBYlEIty9e7fUsYvl5+cLVlZWQsuWLYWcnBzl9r179woAhNmzZyu3eXt7l3pfIiIiBADCr7/+KgiCICgUCsHFxUXw9/cXFAqFsl12drbg7OwsdO/eXbmt+PM2dOjQZ+Z7WvH3Y8lje3t7CxKJRPjggw+U24rfU19fX+W26vB9Wfy99vR7XNbXUkhIiCCRSIS4uDjltqFDhwp2dnYq348XL15UOW9lvD+PHz8WAAjffvvtc18LVS32IJHGGDx4MHJycrB3715kZWVh7969z7y8tm/fPkilUuVf/MWmTp0KQRCwf/9+ZTsApdpNnjxZ5WNBELB9+3b07dsXgiAgJSVF+fD390dGRgYuXrxYodelra2NsWPHKj/W1dXF2LFjkZycjAsXLqi0HTFiBAwMDFS26enpKQcSy+VypKamwsjICE2bNi13pg8++EDl486dO+Pu3bvPfU7dunUBAHv37i3z0tKLvPvuu8r/S6VStG3bFoIgYMyYMSrnaNq06QuzlOXpz1NGRgZSUlLg6+uLu3fvIiMjQ6Wts7Mz/P391T5HMS0tLQwfPhx79uxBVlaWcvvvv/8OHx8fODs7P/O558+fR3JyMj766CPo6+srt/fp0weurq7466+/lNsCAwNx4cIF3LlzR7lt8+bN0NPTQ//+/QEAkZGRuHXrFoYNG4bU1FTl16lMJkO3bt3w999/lxq7VvL9f5ExY8aoTKvg5eVV6r0rfk+ffu+q0/fl057+WpLJZEhJSYGPjw8EQVC5pBYUFIQHDx7g6NGjym2///47DAwMMHDgQACV8/4YGBhAV1cXx44dU7msSq8WCyTSGJaWlvDz88PGjRuxY8cOyOVyvPXWW2W2jYuLg52dHYyNjVW2N2vWTLm/+F8tLS00atRIpV3JMSOPHj1Ceno6Vq9eDUtLS5XHqFGjABRdcipLTk4OEhMTVR5Ps7Ozg6Ghocq2Jk2aAECp8QRl/aJVKBT4/vvv4eLiAj09PVhYWMDS0hJXrlwpVQiURV9fH5aWlirb6tWr98IfvL6+vhg4cCDmzZsHCwsL9O/fH2vXrkVeXt4LzwkADg4OKh+bmppCX18fFhYWpbZX5JfAqVOn4OfnB0NDQ9StWxeWlpaYOXMmAJRZIL2soKAg5OTkYOfOnQCKLttduHAB77zzznOfV/y1WNY4JVdXV5UxR4MGDYKWlhY2b94MoKhA2Lp1K3r16gUTExMAwK1btwAUFdMlv1Z/+ukn5OXlvfTrL+u9AwB7e/tS259+7zTp+1Id8fHxGDlyJMzMzJTj9Hx9fQGofi11794dtra2ystsCoUCf/zxB/r37698zZXx/ujp6WHBggXYv38/rK2t0aVLFyxcuLDUzxaqWrzNnzTKsGHD8N577yExMRG9evVS9mJUteK/6N5++22MGDGizDZubm5lbt+8ebPyh3UxocSA1PIq2XsEFA0AnTVrFkaPHo0vv/wSZmZm0NLSwuTJk8t1l1tF7waTSCTYtm0bzpw5gz///BMHDx7E6NGjsWjRIpw5cwZGRkZqn/dZWdT9fN25cwfdunWDq6srFi9eDHt7e+jq6mLfvn34/vvvS31eyvq8qqt58+bw9PTEb7/9hqCgIPz222/Q1dXF4MGDX/rYxezs7NC5c2ds2bIFM2fOxJkzZxAfH48FCxYo2xS/tm+//bbMsVQASr036r7+Z71PZW2v6Nd6ebzM92V5yeVydO/eHWlpafj000/h6uoKQ0ND3L9/HyNHjlT5WpJKpRg2bBjWrFmDH3/8EadOncKDBw9UxqBV1vszefJk9O3bF7t27cLBgwcxa9YshISE4MiRI2jduvVLvWYqHxZIpFHefPNNjB07FmfOnFH+FV0WR0dHHD58GFlZWSp/rV6/fl25v/hfhUKBO3fuqPx1euPGDZXjFd9JI5fL4efnp1Zmf39/lbvvSnrw4AFkMplKL9LNmzcBoFxz7Wzbtg2vvfYafv75Z5Xt6enppXpjqkKHDh3QoUMHfP3119i4cSOGDx+OTZs2qVxCe9X+/PNP5OXlYc+ePSq9HU9f+qiIF83WHRQUhODgYDx8+BAbN25Enz59lAOnn6X4a/HGjRt4/fXXVfbduHFDub9YYGAgPvroI9y4cQObN29GnTp10LdvX+X+4l4XExMTtb9Wq5omfV+WV1RUFG7evIn169erDMp+1vd0UFAQFi1ahD///BP79++HpaWlyuXbynx/GjVqhKlTp2Lq1Km4desWPDw8sGjRIvz2228vdVwqH15iI41iZGSElStXYu7cuSq/FErq3bs35HI5li9frrL9+++/h0QiQa9evQBA+e8PP/yg0q7k3S9SqRQDBw7E9u3bER0dXep8jx49emYWW1tb+Pn5qTyeVlhYqLytHCiavuB///sfLC0t4enp+czjPp2t5F/pW7duVbmluCo8fvy41HmL/yIu72W2qlLck/F0voyMDKxdu/aljltcxBbfWVbS0KFDIZFIMGnSJNy9e/eFd68BQNu2bWFlZYVVq1apfN7279+Pa9eulbpza+DAgZBKpfjjjz+wdetWvPHGGyrFtaenJxo1aoTvvvsOT548KXW+532tVjVN+r4sr7K+lgRBwNKlS8ts7+bmBjc3N/z000/Yvn07hgwZojIPWGW8P9nZ2cjNzVXZ1qhRIxgbG4v+vVebsAeJNM6zutKf1rdvX7z22mv47LPPEBsbC3d3dxw6dAi7d+/G5MmTlX/FeXh4YOjQofjxxx+RkZEBHx8fhIWF4fbt26WO+c033+Do0aPw8vLCe++9h+bNmyMtLQ0XL17E4cOHkZaWVqHXY2dnhwULFiA2NhZNmjTB5s2bERkZidWrV5drksI33ngDX3zxBUaNGgUfHx9ERUXh999/R8OGDSuUp7zWr1+PH3/8EW+++SYaNWqErKwsrFmzBiYmJujdu3eVnvtFevToAV1dXfTt2xdjx47FkydPsGbNGlhZWeHhw4cVPq6HhwekUikWLFiAjIwM6OnpKedaAop6NHr27ImtW7eibt26Zd6WXpKOjg4WLFiAUaNGwdfXF0OHDkVSUhKWLl0KJycnTJkyRaW9lZUVXnvtNSxevBhZWVkIDAxU2a+lpYWffvoJvXr1QosWLTBq1CjUr18f9+/fx9GjR2FiYoI///yzwp+Dl1Gdvi+Lubq6olGjRpg2bRru378PExMTbN++/bnj4oKCgjBt2jQAKFUkV8b7c/PmTXTr1g2DBw9G8+bNoa2tjZ07dyIpKanMaU+oirzq2+aInvb0bf7PU/I2f0EQhKysLGHKlCmCnZ2doKOjI7i4uAjffvutyq21giAIOTk5wsSJEwVzc3PB0NBQ6Nu3r5CQkFDqdmJBEISkpCRh3Lhxgr29vaCjoyPY2NgI3bp1E1avXq1so+5t/i1atBDOnz8veHt7C/r6+oKjo6OwfPlylXbFtx5v3bq11DFyc3OFqVOnCra2toKBgYHQsWNHITw8XPD19VW5xfpZt/kbGhqWOmZZt82XdPHiRWHo0KGCg4ODoKenJ1hZWQlvvPGGcP78eZV2JT+Pxcd+9OiRSrtnZSn+HD3vdZSVd8+ePYKbm5ugr68vODk5CQsWLBB++eUXAYAQExOjbFfW187T+56+zV8QBGHNmjVCw4YNBalUWuYt/1u2bCk1jUF5bN68WWjdurWgp6cnmJmZCcOHDxfu3btXZts1a9YIAARjY2OVqQGedunSJWHAgAGCubm5oKenJzg6OgqDBw8WwsLClG2e9V48y7O+H9V5TzX9+7Ks2/yvXr0q+Pn5CUZGRoKFhYXw3nvvCZcvX37m8R4+fChIpVKhSZMmzzzPy7w/KSkpwrhx4wRXV1fB0NBQMDU1Fby8vIQtW7Y897VR5ZIIQhWOsCMiqmF2796NgIAA/P333+jcubPYcUgEKSkpsLW1xezZszFr1iyx41AV4RgkIiI1rFmzBg0bNnzukh1Us61btw5yufyFUzxQ9cYxSERE5bBp0yZcuXIFf/31F5YuXfrCO96o5jly5AiuXr2Kr7/+GgEBAeW6C5WqL15iIyIqB4lEAiMjIwQGBmLVqlUqdy5R7dC1a1ecPn0aHTt2xG+//aZce41qJhZIRERERCVwDBIRERFRCSyQiIiIiErgRfQKUigUePDgAYyNjTlYk4iIqJoQBAFZWVmws7ODltaz+4lYIFXQgwcPSq1sTURERNVDQkICGjRo8Mz9LJAqqHghxoSEBJiYmIichoiIiMojMzMT9vb2Kgsql4UFUgUVX1YzMTFhgURERFTNvGh4DAdpExEREZXAAomIiIioBBZIRERERCWwQCIiIiIqgQUSERERUQkskIiIiIhKYIFEREREVAILJCIiIqISWCARERERlcACiYiIiKgEFkhEREREJbBAIiIiIipB9AJpxYoVcHJygr6+Pry8vBAREfHc9lu3boWrqyv09fXRqlUr7Nu3T2X/jh070KNHD5ibm0MikSAyMrLUMRITE/HOO+/AxsYGhoaGaNOmDbZv316ZL4uIiEiFXCEgJ18udgwqJ1ELpM2bNyM4OBhz5szBxYsX4e7uDn9/fyQnJ5fZ/vTp0xg6dCjGjBmDS5cuISAgAAEBAYiOjla2kclk6NSpExYsWPDM8wYFBeHGjRvYs2cPoqKiMGDAAAwePBiXLl2q9NdIRESkUAgYte4c2n4Viiv30sWOQ+UgEQRBEOvkXl5eaNeuHZYvXw4AUCgUsLe3x4QJEzB9+vRS7QMDAyGTybB3717ltg4dOsDDwwOrVq1SaRsbGwtnZ2dcunQJHh4eKvuMjIywcuVKvPPOO8pt5ubmWLBgAd59991yZc/MzISpqSkyMjJgYmJS3pdMRES10Maz8Zi5MwoA4GxhiL8mdkIdXW2RU9VO5f39LVoPUn5+Pi5cuAA/P7//wmhpwc/PD+Hh4WU+Jzw8XKU9APj7+z+z/bP4+Phg8+bNSEtLg0KhwKZNm5Cbm4uuXbs+8zl5eXnIzMxUeRAREb1IcmYuQvZfAwDoSrUQkyLDl3uvipyKXkS0AiklJQVyuRzW1tYq262trZGYmFjmcxITE9Vq/yxbtmxBQUEBzM3Noaenh7Fjx2Lnzp1o3LjxM58TEhICU1NT5cPe3l6tcxIRUe00989/kJVbCLcGpvhlZDtIJMAfEQk4EK3e7y56tUQfpC2GWbNmIT09HYcPH8b58+cRHByMwYMHIyoq6pnPmTFjBjIyMpSPhISEV5iYiIiqo9CrSdgXlQiplgTfDHBDJxcLjO3SCAAwfccVJGXmipyQnkW0C6AWFhaQSqVISkpS2Z6UlAQbG5syn2NjY6NW+7LcuXMHy5cvR3R0NFq0aAEAcHd3x4kTJ7BixYpSY5mK6enpQU9Pr9znISKi2i0rtwCzdxfdRPRe54Zoblc03iW4exOcvP0I0fczMXXLZfw6uj20tCRiRqUyiNaDpKurC09PT4SFhSm3KRQKhIWFwdvbu8zneHt7q7QHgNDQ0Ge2L0t2djaAovFOT5NKpVAoFOU+DhER0fMsOnQTDzNy4WBWB5O6uSi362prYemQ1tDX0cLJ2yn45VSMiCnpWUS9xBYcHIw1a9Zg/fr1uHbtGj788EPIZDKMGjUKQNHt+DNmzFC2nzRpEg4cOIBFixbh+vXrmDt3Ls6fP4/x48cr26SlpSEyMhJXrxYNgLtx4wYiIyOV45RcXV3RuHFjjB07FhEREbhz5w4WLVqE0NBQBAQEvLoXT0RENdbF+MdYHx4LAJj/ZisY6EpV9jeyNMLsN4quYiw8cAP/PMh41RHpBUQtkAIDA/Hdd99h9uzZ8PDwQGRkJA4cOKAciB0fH4+HDx8q2/v4+GDjxo1YvXo13N3dsW3bNuzatQstW7ZUttmzZw9at26NPn36AACGDBmC1q1bKy+d6ejoYN++fbC0tETfvn3h5uaGX3/9FevXr0fv3r1f4asnIqKaKL9QgRnboyAIwMA2DdDJxaLMdkPb26N7c2vkyxWYtCmSk0hqGFHnQarOOA8SERGVZcXR2/j24A2YGericLAvzAx1n9k2TZYP/yV/41FWHoK8HfFF/5bPbEuVQ+PnQSIiIqpp7j56gqVhtwAAs99o/tziCADMDHXx3SB3AMCv4XEIu5b03Pb06rBAIiIiqgSCIGDmzijkFyrQpYkl+nvYlet5vk0sMbqjMwDgk21X8CgrrypjUjmxQCIiIqoEW8/fw5m7adDX0cLXAS0hkZT/1v1PejaFq40xUmX5+GTbZXD0i/hYIBEREb2kR1l5+Hpf0XIiwd2bwN6sjlrP19eRYumQ1tDV1sLRG4+w4UxcVcQkNbBAIiIieklf7L2KjJwCtKxvorxcpq6mNsaY2csVAPD1X9dwMymrMiOSmlggERERvYSj15Px5+UH0JIA3wxwg7a04r9aR/g4wbeJJfIKFZj4xyXkFfLWf7GwQCIiIqogWV4hPt9VtJzImE7OaFnf9KWOJ5FI8O0gN5gb6uJ6Yha+PXCjMmJSBbBAIiIiqqBFh27ifnoOGtQzwJTuTSrlmFbG+lj4lhsA4KeTMThx61GlHJfUwwKJiIioAi4npGPd6aJ11L5+sxXq6Fbe+u/dmlnjnQ6OAICpWy4jTZZfacem8mGBREREpKYCuQLTd0RBIQABHnbwbWJZ6eeY2bsZGlsZITkrD59uv8Jb/18xFkhERERq+ulEDK49zETdOjr4/I3mVXIOA10plg7xgI5UgtCrSdh0LqFKzkNlY4FERESkhrhUGZYcvgkA+LxPc1gY6VXZuVrYmeIT/6Jb/7/48yruPHpSZeciVSyQiIiIyql4OZG8QgU6NjbHwDb1q/ycYzo5o2Njc+QUyDF5UyTyCxVVfk6x3UzKwtgN55GdXyhaBhZIRERE5bTj4n2cup0KPW0tfB3QSq3lRCpKS0uCRYM8ULeODqLuZ+D7f3uvaqoD0Yl4c8UpHPwnCQtFnOaABRIREVE5pD7Jw1d/XQUATPZrAicLw1d2bhtTfXwzoOjW/1XH7yD8TuorO/erolAIWBx6Ex/8dgGyfDm8G5pjYjcX0fKwQCIiIiqHr/66hsfZBWhma4J3O1dsOZGX0bOlDYa0s4cgAMFbIpGRXfDKM1SVrNwCvL/hPH4IuwUAGNXRCb+OaQ8zQ13RMrFAIiIieoHjNx9h56X7kEiAbwa0gs5LLCfyMma90RzOFoZ4mJGLmTujasSt/3cePUHAilM4fC0Zutpa+G6QO+b0bSHa57gYCyQiIqLnyM4vxGc7owAAI32c4G5fV7QshnraWBLoAW0tCf6KeojtF++LlqUyHLmehIDlp3DnkQw2JvrYOtYbb3k2EDsWABZIREREz7Xk8C3ce5yD+nUNMK1HU7HjwN2+rnJZkzm7oxGXKhM5kfoEQcDyI7cwZv15ZOUVop1TPfw5oZOoxWdJLJCIiIieIfp+Bn46cRcA8GVACxjqVd5yIi/jA99GaO9kBlm+HJM3R6JQXn1u/ZflFeKj3y/iu0M3IQjA2x0c8Pu7HWBpXHXzSVUECyQiIqIyFMoVmL7jChQC8IabLV53tRY7kpJUS4LFge4w1tfGpfh0LDtyW+xI5RKXKsOAH09jf3QidKQShAxoha8CWkFXW/PKEc1LREREpAHWnopF9P1MmOhrY3bfqllO5GU0qFcHX7/ZCgCw7MgtXIhLEznR85249Qj9lp/CjaQsWBrrYdP7HTC0vYPYsZ6JBRIREVEJCWnZWBxaNCHjZ32awcpYX+REZevnbocBretDIQCTNkUiK1fzbv0XBAGr/76DEb9EICOnAB72dbF3Qid4OpqJHe25WCARERE9RRAEfLYrGjkFcnRoaIbBbe3FjvRc8/q3gL2ZAe49zsGc3f+IHUdFzr9jpObvuw6FAAxu2wCbx3aAtYlmFpxPY4FERET0lN2RD/D3zUfQ1dbC/DdfzXIiL8NYXwdLAj2gJQF2XLqP3ZGacev/vcfZeGvVaeyOfABtLQm+6N8CCwa6QU9bKna0cmGBRERE9K/Hsnx8sbdoOZGJrzdGQ0sjkROVj6ejGSa8XrQsx+e7onHvcbaoecLvpKLf8lP450EmzA118du7XgjydtL4YvNpLJCIiIj+9dVf15Amy0dTa2O836WR2HHUMuH1xmjtUBdZuYUI3nwZcsWrn2VbEASsOxWDt38+izRZPlrYmWDPhE7o0ND8lWd5WSyQiIiIAJy6nYLtF+9BIgHmD9DMW8+fR1uqhaWBrWGoK0VEbBpWHb/zSs+fWyDHx9uuYO6fVyFXCAjwsMO2D3xQv67BK81RWarXu09ERFQFcgvkmPnvciLvdHCEp2M9kRNVjIN5HXzRvyUA4PvQm4hMSH8l532YkYPA/4Vj24V70JIAn/dphu8DPWCgWz3GG5WFBRIREdV6Sw7fQlxqNmxM9PGxv/jLibyMAW3q4w03WxQqBEzedAmyvMIqPd/52DT0XXYKl+9loG4dHfw62gvvdm5YrcYblYUFEhER1WpXH2RijXI5kZYw1tcROdHLkUgk+DqgFexM9RGbmo0v/rxaZef6/Wwchq45g5QneXC1McaecZ3QycWiys73KrFAIiKiWkuuEDBjxxXIFQJ6tbRB9+aas5zIyzCto4PFgR6QSIDN5xOwP+phpR4/v1CBGTui8NnOaBTIBfRpZYsdH/nAwbxOpZ5HTCyQiIio1lp/OhaX72XAWF8b8/q1EDtOperQ0Bwf+hbdiTd9RxQSM3Ir5bjJWbkYtuYM/oiIh0QCfNKzKZYPa406upqxkG9lYYFERES10r3H2fju0A0AwPRerrCqBrM7q2uyXxO4NTBFRk4Bpm6NhOIlb/2PTEhHv2WncD7uMYz1tfHLyHb4qGvjaj/eqCwskIiIqNYRBAGzd/+D7Hw52jnVw9B2mrto6svQ1dbCkkAPGOhIcep2Kn4+GVPhY209n4DB/wtHYmYuGlsZYc/4TnitqVUlptUsLJCIiKjW2XvlIY5cT4auVAshA1pBS6vm9YAUa2hphNl9mwMAFh68jn8eZKj1/AK5AnP3/IOPt11BfqEC3ZtbY+dHPnC2MKyKuBqDBRIREdUq6dn5mPdn0aKuH73WCI2tjEVOVPWGtLNHj+bWKJALmLQpEjn58nI9L/VJHt75+SzWnY4FAEz2c8H/3vas9nf6lQcLJCIiqlVC9l1HypN8NLYywoddq9dyIhUlkUjwzUA3WBnr4XbyE8zfd+2Fz4m+n4F+y0/hzN00GOpKsfodT0z2a1Kje9uexgKJiIhqjfA7qdh8PgEAEDKgVbVZWb4ymBnqYtFgdwDAhjNxCLuW9My2uyPv461Vp3E/PQdO5nWwa1xH9Ghh86qiagQWSEREVCs8vZzIcC8HtHMyEznRq9fZxRLvdnIGAHyy7QqSs1Rv/S+UKzB/3zVM2hSJ3AIFuja1xO7xneBiXfMvQ5bEAomIiGqF5UduIyZFBitjPXzay1XsOKL5uGdTuNoYI1WWj4+3XoEgFN36n56dj1HrzmH130Wzin/UtRF+HtEOpgY1f7xRWVggERFRjXcjMUu5uv0X/VvApBYMMn4WPW0pfhjaGnraWjh+8xHWn47F9cRM9Ft+CidupcBAR4rlw1rjk56ukNaS8UZlqVnTXhIREZUgVwiYvuMKChUCuje3hn8tG0tTlibWxvisTzPM3v0P5u+/Dm0tCbLz5bA3M8Dqd9qima2J2BFFxx4kIiKq0X47E4dL8ekw0tPGF/1b1MhZnyvinQ6OeK2pJfILFcjOl6NjY3PsGdeJxdG/2INEREQ11oP0HCw8cB1A0ZphtqYGIifSHBKJBN8OcseMHVFoZmuCia83hraU/SbFWCAREVGNVLyciCxfjjYOdfG2l6PYkTSOhZEe1gS1FTuGRmKpSERENdKB6EQcvpYEHakEIQPcas0Eh1Q5WCAREVGNk5FTgNl7ipYT+cC3EZra1L55fOjliF4grVixAk5OTtDX14eXlxciIiKe237r1q1wdXWFvr4+WrVqhX379qns37FjB3r06AFzc3NIJBJERkaWeZzw8HC8/vrrMDQ0hImJCbp06YKcnJzKellERCSiBQeu41FWHhpaGGLca43FjkPVkKgF0ubNmxEcHIw5c+bg4sWLcHd3h7+/P5KTk8tsf/r0aQwdOhRjxozBpUuXEBAQgICAAERHRyvbyGQydOrUCQsWLHjmecPDw9GzZ0/06NEDEREROHfuHMaPHw8tLdHrRSIiekkX4h5j49l4AMD8Aa2gr1N7lhOhyiMRiqfQFIGXlxfatWuH5cuXAwAUCgXs7e0xYcIETJ8+vVT7wMBAyGQy7N27V7mtQ4cO8PDwwKpVq1TaxsbGwtnZGZcuXYKHh4fKvg4dOqB79+748ssvK5w9MzMTpqamyMjIgIkJb4kkItIU7/x8FidupeAtzwb4bpC72HFIw5T397doXSb5+fm4cOEC/Pz8/gujpQU/Pz+Eh4eX+Zzw8HCV9gDg7+//zPZlSU5OxtmzZ2FlZQUfHx9YW1vD19cXJ0+efO7z8vLykJmZqfIgIiLNcin+MU7cSoFUS4JJ3VzEjkPVmGgFUkpKCuRyOaytrVW2W1tbIzExscznJCYmqtW+LHfvFq0xM3fuXLz33ns4cOAA2rRpg27duuHWrVvPfF5ISAhMTU2VD3t7+3Kfk4iIXo0VR28DAN5sXR/2ZnVETkPVWa0bdKNQKAAAY8eOxahRo9C6dWt8//33aNq0KX755ZdnPm/GjBnIyMhQPhISEl5VZCIiKod/HmTg8LVkSCRFC60SvQzRJoq0sLCAVCpFUlKSyvakpCTY2JS9To6NjY1a7ctia2sLAGjevLnK9mbNmiE+Pv6Zz9PT04Oenl65z0NERK/Wj0eLFqN9w80ODS2NRE5D1Z1oPUi6urrw9PREWFiYcptCoUBYWBi8vb3LfI63t7dKewAIDQ19ZvuyODk5wc7ODjdu3FDZfvPmTTg6cpZVIqLq6HZyFvZFPwQAjHuNvUf08kRdaiQ4OBgjRoxA27Zt0b59eyxZsgQymQyjRo0CAAQFBaF+/foICQkBAEyaNAm+vr5YtGgR+vTpg02bNuH8+fNYvXq18phpaWmIj4/HgwcPAEBZCNnY2MDGxgYSiQQff/wx5syZA3d3d3h4eGD9+vW4fv06tm3b9oo/A0REVBl+PHoHggD0aG4NVxveWUwvT9QCKTAwEI8ePcLs2bORmJgIDw8PHDhwQDkQOz4+XmVuIh8fH2zcuBGff/45Zs6cCRcXF+zatQstW7ZUttmzZ4+ywAKAIUOGAADmzJmDuXPnAgAmT56M3NxcTJkyBWlpaXB3d0doaCgaNeJfHURE1U1cqgy7Lxf9UTz+dU4KSZVD1HmQqjPOg0REpBlm7LiCPyIS4NvEEutHtxc7Dmk4jZ8HiYiI6GU9SM/Btgv3AAAT2HtElYgFEhERVVur/76LArkAL2cztHUyEzsO1SAVGoNUUFCAxMREZGdnw9LSEmZm/KIkIqJX61FWHv6IKJqeZcLrnDWbKle5e5CysrKwcuVK+Pr6wsTEBE5OTmjWrBksLS3h6OiI9957D+fOnavKrEREREo/nbyLvEIFPOzromNjc7HjUA1TrgJp8eLFcHJywtq1a+Hn54ddu3YhMjISN2/eRHh4OObMmYPCwkL06NEDPXv2fO6SHURERC/rsSwfv4XHASgaeySRSERORDVNuS6xnTt3Dn///TdatGhR5v727dtj9OjRWLVqFdauXYsTJ07AxYXdnUREVDXWno6FLF+OZrYmeN3VSuw4VAOVq0D6448/ynUwPT09fPDBBy8ViIiI6Hkycwuw7lQMAPYeUdVR6y62goICaGtrIzo6uqryEBERPdeG8Dhk5haisZURerYo/1qcROpQq0DS0dGBg4MD5HJ5VeUhIiJ6puz8Qvx8sqj3aNxrjaClxd4jqhpqz4P02WefYebMmUhLS6uKPERERM+08Ww80mT5cDCrg75udmLHoRpM7XmQli9fjtu3b8POzg6Ojo4wNDRU2X/x4sVKC0dERFQst0CO1X/fBQB81LURtKWc65iqjtoFUkBAQBXEICIier6tF+4hOSsPtqb6GNCmgdhxqIZTu0CaM2dOVeQgIiJ6pgK5AquO3QEAfODbCLra7D2iqsWvMCIi0ng7L93H/fQcWBjpIbCdvdhxqBZggURERBpNrhDw49HbAID3uzhDX0cqciKqDVggERGRRtt75QFiU7NRt44Ohns5ih2HagkWSEREpLEUCgEr/u09GtPRGYZ6ag+dJaqQly6Q5HI5IiMj8fjx48rIQ0REpHToahJuJj2BsZ42gnycxI5DtYjaBdLkyZPx888/Aygqjnx9fdGmTRvY29vj2LFjlZ2PiIhqKUEQsPzoLQDACB8nmBroiJyIahO1C6Rt27bB3d0dAPDnn38iJiYG169fx5QpU/DZZ59VekAiIqqdjt18hOj7mTDQkWJ0J2ex41Ato3aBlJKSAhubosUB9+3bh0GDBqFJkyYYPXo0oqKiKj0gERHVPoIgYFlYUe/R2x0cYGaoK3Iiqm3ULpCsra1x9epVyOVyHDhwAN27dwcAZGdnQyrlrZdERPTywu+m4mJ8OnS1tfBe54Zix6FaSO3bAUaNGoXBgwfD1tYWEokEfn5+AICzZ8/C1dW10gMSEVHts/xI0Z1rQ9rZw8pEX+Q0VBupXSDNnTsXLVu2REJCAgYNGgQ9PT0AgFQqxfTp0ys9IBER1S4X4h7j9J1UaGtJMNa3kdhxqJaq0IQSb731VqltI0aMeOkwRERExfMeDWzTAPXrGoichmqrchdIv/76q8rHQUFBlR6GiIhqt+j7GThyPRlaEuDDruw9IvGUu0Bau3at8v8SiYQFEhERVbri3qO+7nZwsjAUOQ3VZuUukI4ePVqVOYiIqJa7mZSF/dGJAIBxrzUWOQ3VdlyLjYiINMKP//Ye9WxhgybWxiKnodpO7UHacrkc69atQ1hYGJKTk6FQKFT2HzlypNLCERFR7RCbIsOeyw8AAONfZ+8RiU/tAmnSpElYt24d+vTpg5YtW0IikVRFLiIiqkVWHrsDhQC81tQSLeubih2HSP0CadOmTdiyZQt69+5dFXmIiKiWuZ+eg+0X7wEAxr/uInIaoiJqj0HS1dVF48bs/iQiosrxv+N3UKgQ4NPIHJ6O9cSOQwSgAgXS1KlTsXTpUgiCUBV5iIioFknOzMWmcwkAOPaINIval9hOnjyJo0ePYv/+/WjRogV0dHRU9u/YsaPSwhERUc225sRd5Bcq4OlYD94NzcWOQ6SkdoFUt25dvPnmm1WRhYiIapE0WT5+OxMPoKj3iDf9kCZRu0B6ekZtIiKiivrlZAxyCuRoWd8EXZtYih2HSEWFFqsFgEePHuHGjRsAgKZNm8LSkl/cRERUPhk5BVh/OhYAMP41F/YekcZRe5C2TCbD6NGjYWtriy5duqBLly6ws7PDmDFjkJ2dXRUZiYiohvn1dCyy8grRxNoIPZpbix2HqBS1C6Tg4GAcP34cf/75J9LT05Geno7du3fj+PHjmDp1alVkJCKiGkSWV4ifT8UAKFpzTUuLvUekedS+xLZ9+3Zs27YNXbt2VW7r3bs3DAwMMHjwYKxcubIy8xERUQ3z+9k4pGcXwNnCEG+42Ykdh6hMavcgZWdnw9q6dHeolZUVL7EREdFz5RbIsfrvot6jD7s2gpS9R6Sh1C6QvL29MWfOHOTm5iq35eTkYN68efD29q7UcEREVLNsPpeAlCd5qF/XAG+2ri92HKJnUvsS29KlS+Hv748GDRrA3d0dAHD58mXo6+vj4MGDlR6QiIhqhvxCBVYdvwMA+KBrI+hI1f4bneiVUbtAatmyJW7duoXff/8d169fBwAMHToUw4cPh4GBQaUHJCKimmHHxXt4mJELK2M9DPJsIHYcoueq0DxIderUwXvvvVfZWYiIqIYqlCuw8t/eo/e7NIS+jlTkRETPp3b/5vr16/HXX38pP/7kk09Qt25d+Pj4IC4urlLDERFRzbD3ykPEpWbDzFAXw7wcxI5D9EJqF0jz589XXkoLDw/H8uXLsXDhQlhYWGDKlCmVHpCIiKo3hULA8qO3AQBjOjmjjm6FF3EgemXULpASEhLQuHFjAMCuXbvw1ltv4f3330dISAhOnDhRoRArVqyAk5MT9PX14eXlhYiIiOe237p1K1xdXaGvr49WrVph3759Kvt37NiBHj16wNzcHBKJBJGRkc88liAI6NWrFyQSCXbt2lWh/ERE9GwH/0nE7eQnMNHXRpC3o9hxiMpF7QLJyMgIqampAIBDhw6he/fuAAB9fX3k5OSoHWDz5s0IDg7GnDlzcPHiRbi7u8Pf3x/Jyclltj99+jSGDh2KMWPG4NKlSwgICEBAQACio6OVbWQyGTp16oQFCxa88PxLlizhGkBERFVEEAQsO1LUezTSxwnG+joiJyIqH4kgCII6Txg+fDiuX7+O1q1b448//kB8fDzMzc2xZ88ezJw5U6VQKQ8vLy+0a9cOy5cvBwAoFArY29tjwoQJmD59eqn2gYGBkMlk2Lt3r3Jbhw4d4OHhgVWrVqm0jY2NhbOzMy5dugQPD49Sx4qMjMQbb7yB8+fPw9bWFjt37kRAQEC5cmdmZsLU1BQZGRkwMTEp/wsmIqpFjlxPwuh151FHV4pTn76Oeoa6YkeiWq68v7/V7kFasWIFfHx88OjRI2zfvh3m5uYAgAsXLmDo0KFqHSs/Px8XLlyAn5/ff4G0tODn54fw8PAynxMeHq7SHgD8/f2f2f5ZsrOzMWzYMKxYsQI2NjYvbJ+Xl4fMzEyVBxERPZsgCPghrKj36J0OjiyOqFpRa6RcYWEhfvjhB3z66ado0EB1Dot58+apffKUlBTI5fJSS5dYW1sr51gqKTExscz2iYmJap17ypQp8PHxQf/+/cvVPiQkpEKvkYiotjp9JxWRCenQ09bCmM7OYschUotaPUja2tpYuHAhCgsLqyrPK7Fnzx4cOXIES5YsKfdzZsyYgYyMDOUjISGh6gISEdUAy47cAgAMbe8AK2N9kdMQqUftS2zdunXD8ePHK+XkFhYWkEqlSEpKUtmelJT0zMteNjY2arUvy5EjR3Dnzh3UrVsX2tra0NYu6kgbOHAgunbtWuZz9PT0YGJiovIgIqKynYtNw5m7adCRSvB+l4ZixyFSm9qTUfTq1QvTp09HVFQUPD09YWhoqLK/X79+5T6Wrq4uPD09ERYWphwcrVAoEBYWhvHjx5f5HG9vb4SFhWHy5MnKbaGhoWotlDt9+nS8++67KttatWqF77//Hn379i33cYiIqGzL/71z7S3PBrCry2WoqPpRu0D66KOPAACLFy8utU8ikUAul6t1vODgYIwYMQJt27ZF+/btsWTJEshkMowaNQoAEBQUhPr16yMkJAQAMGnSJPj6+mLRokXo06cPNm3ahPPnz2P16tXKY6alpSE+Ph4PHjwAANy4cQNAUe/T04+SHBwc4OzM6+RERC/jyr10HL/5CFItCT70bSx2HKIKUbtAUigUlRogMDAQjx49wuzZs5GYmAgPDw8cOHBAORA7Pj4eWlr/XQn08fHBxo0b8fnnn2PmzJlwcXHBrl270LJlS2WbPXv2KAssABgyZAgAYM6cOZg7d26l5iciIlXFvUf93e3gYF5H5DREFaP2PEhUhPMgERGVdj0xEz2XnIBEAoRO6YLGVsZiRyJSUd7f3xVaEEcmk+H48eOIj49Hfn6+yr6JEydW5JBERFQDrDh6BwDQu6UtiyOq1tQukC5duoTevXsjOzsbMpkMZmZmSElJQZ06dWBlZcUCiYiolrrz6An2Xika+znuNY49oupN7dv8p0yZgr59++Lx48cwMDDAmTNnEBcXB09PT3z33XdVkZGIiKqBlcfuQBAAv2ZWaG7HoQdUvaldIEVGRmLq1KnQ0tKCVCpFXl4e7O3tsXDhQsycObMqMhIRkYZLSMvGzkv3AbD3iGoGtQskHR0d5V1lVlZWiI+PBwCYmppydmkiolpq1fE7kCsEdHaxQGuHemLHIXppao9Bat26Nc6dOwcXFxf4+vpi9uzZSElJwYYNG1RutSciotohMSMXW8/fAwCMZ+8R1RBq9yDNnz8ftra2AICvv/4a9erVw4cffohHjx6pTNZIRES1w+q/7yJfrkB7JzN4NTQXOw5RpVC7B6lt27bK/1tZWeHAgQOVGoiIiKqP1Cd52BgRBwAY/zp7j6jmULsHCQAKCwtx+PBh/O9//0NWVhYA4MGDB3jy5EmlhiMiIs3288kY5BYo4N7AFJ1dLMSOQ1Rp1O5BiouLQ8+ePREfH4+8vDx0794dxsbGWLBgAfLy8rBq1aqqyElERBom5Uke1p+OBQCMf90FEolE3EBElUjtHqRJkyahbdu2ynmQir355psICwur1HBERKS5lh6+BVm+HK3qm6Kbq5XYcYgqldo9SCdOnMDp06ehq6urst3JyQn379+vtGBERKS5bic/wcaIomleZvZuBi0t9h5RzaJ2D5JCoYBcLi+1/d69ezA25ro7RES1wTf7r0OuEODXzBrejXjnGtU8ahdIPXr0wJIlS5QfSyQSPHnyBHPmzEHv3r0rMxsREWmgM3dTcfhaEqRaEkzv5Sp2HKIqofYltkWLFsHf3x/NmzdHbm4uhg0bhlu3bsHCwgJ//PFHVWQkIiINoVAImL/vGgBgWHsHNLYyEjkRUdVQu0Bq0KABLl++jE2bNuHKlSt48uQJxowZg+HDh6sM2iYioprnzysPcOVeBoz0tDHJz0XsOERVRu0CCQC0tbXx9ttvV3YWIiLSYLkFciw8cAMA8GHXRrAw0hM5EVHVqVCBdOPGDSxbtgzXrhV1szZr1gzjx4+HqyuvRRMR1VTrTsfifnoObE31Mbqjs9hxiKqU2oO0t2/fjpYtW+LChQtwd3eHu7s7Ll68iFatWmH79u1VkZGIiESWJsvHiiO3AQDTejSFga5U5EREVUvtHqRPPvkEM2bMwBdffKGyfc6cOfjkk08wcODASgtHRESa4YewW8jKK0RzWxO82bq+2HGIqpzaPUgPHz5EUFBQqe1vv/02Hj58WCmhiIhIc8SkyPDbmaIFaT/rw0khqXZQu0Dq2rUrTpw4UWr7yZMn0blz50oJRUREmmPB/usoVAh4raklOjbmgrRUO6h9ia1fv3749NNPceHCBXTo0AEAcObMGWzduhXz5s3Dnj17VNoSEVH1dS42DQf+SYSWBJjRu5nYcYheGYkgCII6T9DSKl+nk0QiKXNJkpoiMzMTpqamyMjIgImJidhxiIgqnSAICPjxNC4npGNoeweEDGgldiSil1be399q9yApFIqXCkZERNXD3isPcTkhHXV0pZjSnZNCUu2i9hgkIiKq+fIK5Vh48DoAYGyXRrAy1hc5EdGrVa4CadOmTeU+YEJCAk6dOlXhQEREJL4N4XFISMuBlbEe3uvCSSGp9ilXgbRy5Uo0a9YMCxcuVM6e/bSMjAzs27cPw4YNQ5s2bZCamlrpQYmI6NVIz87HD2G3ABRNCllHt0KLLhBVa+X6qj9+/Dj27NmDZcuWYcaMGTA0NIS1tTX09fXx+PFjJCYmwsLCAiNHjkR0dDSsra2rOjcREVWRZUduIzO3EK42xhjo2UDsOESiKPefBf369UO/fv2QkpKCkydPIi4uDjk5ObCwsEDr1q3RunXrct/hRkREmikuVYZfw2MBADN7N4OUk0JSLaV2v6mFhQUCAgKqIAoREYlt4cEbKJAL6OxigS5NLMWOQyQadvkQEREA4ELcY/x15SEkkqLeI6LajAUSERFBEATM31d0E84gzwZoZssJcKl2Y4FEREQ4EJ2IC3GPYaAjRXD3pmLHIRIdCyQiolouv1CBbw4UTQr5XpeGsDHlpJBEFS6Q8vPzcePGDRQWFlZmHiIiesV+PxuHuNRsWBjpYWyXhmLHIdIIahdI2dnZGDNmDOrUqYMWLVogPj4eADBhwgR88803lR6QiIiqTkZOAZb+OylkcPcmMNTjpJBEQAUKpBkzZuDy5cs4duwY9PX/64b18/PD5s2bKzUcERFVrR+P3kZ6dgFcrIwwuC0nhSQqpvafCrt27cLmzZvRoUMHSCT/TSDWokUL3Llzp1LDERFR1UlIy8baU7EAim7r15ZyWCpRMbW/Gx49egQrK6tS22UymUrBREREmu3bgzeQL1egY2NzdG3KSSGJnqZ2gdS2bVv89ddfyo+Li6KffvoJ3t7elZeMiIiqzOWEdOy5/AASCTCjVzP+gUtUgtqX2ObPn49evXrh6tWrKCwsxNKlS3H16lWcPn0ax48fr4qMRERUiQRBwNf/Tgr5Zuv6aFnfVORERJpH7R6kTp064fLlyygsLESrVq1w6NAhWFlZITw8HJ6enlWRkYiIKlHo1SRExKRBT1sL03pwUkiisqjVg1RQUICxY8di1qxZWLNmTVVlIiKiKlIgV+Cb/UWTQr7b2Rl2dQ1ETkSkmdTqQdLR0cH27durKgsREVWxPyLicTdFBnNDXXzg20jsOEQaS+1LbAEBAdi1a1cVRCEioqqUmVuAJYeLJoWc7OcCY30dkRMRaS61B2m7uLjgiy++wKlTp+Dp6QlDQ0OV/RMnTqy0cEREVHlWHbuDNFk+GloaYkh7B7HjEGk0iSAIgjpPcHZ2fvbBJBLcvXv3pUNVB5mZmTA1NUVGRgZMTEzEjkNE9Fz303Pw+nfHkFeowJqgtuje3FrsSESiKO/vb7UvscXExDzzUdHiaMWKFXBycoK+vj68vLwQERHx3PZbt26Fq6sr9PX10apVK+zbt09l/44dO9CjRw+Ym5tDIpEgMjJSZX9aWhomTJiApk2bwsDAAA4ODpg4cSIyMjIqlJ+ISNMtOngDeYUKeDmbwa9Z6cl+iUjVS80rLwgC1OyAKmXz5s0IDg7GnDlzcPHiRbi7u8Pf3x/Jyclltj99+jSGDh2KMWPG4NKlSwgICEBAQACio6OVbWQyGTp16oQFCxaUeYwHDx7gwYMH+O677xAdHY1169bhwIEDGDNmzEu9FiIiTRR9PwM7Lt0HAHzWh5NCEpWH2pfYAODXX3/Ft99+i1u3igb7NWnSBB9//DHeeecdtQN4eXmhXbt2WL58OQBAoVDA3t4eEyZMwPTp00u1DwwMhEwmw969e5XbOnToAA8PD6xatUqlbWxsLJydnXHp0iV4eHg8N8fWrVvx9ttvQyaTQVv7xUOzeImNiKoDQRAwbM1ZhN9NRX8POywd0lrsSESiqrJLbIsXL8aHH36I3r17Y8uWLdiyZQt69uyJDz74AN9//71ax8rPz8eFCxfg5+f3XyAtLfj5+SE8PLzM54SHh6u0BwB/f/9nti+v4k9UeYojIqLq4uiNZITfTYUuJ4UkUova1cCyZcuwcuVKBAUFKbf169cPLVq0wNy5czFlypRyHyslJQVyuRzW1qqDBa2trXH9+vUyn5OYmFhm+8TERDVeRekcX375Jd5///1ntsnLy0NeXp7y48zMzAqfj4joVSiUKzB/X9HP0lEdnWBvVkfkRETVh9o9SA8fPoSPj0+p7T4+Pnj48GGlhHqVMjMz0adPHzRv3hxz5859ZruQkBCYmpoqH/b29q8uJBFRBWw+n4DbyU9Qr44OPuraWOw4RNWK2gVS48aNsWXLllLbN2/eDBcXF7WOZWFhAalUiqSkJJXtSUlJsLGxKfM5NjY2arV/nqysLPTs2RPGxsbYuXMndHSePWnajBkzkJGRoXwkJCSofT4iolflSV4hvg+9CQCY1M0FpgacFJJIHWpfYps3bx4CAwPx999/o2PHjgCAU6dOISwsrMzC6Xl0dXXh6emJsLAwBAQEACgapB0WFobx48eX+Rxvb2+EhYVh8uTJym2hoaHw9vZW69yZmZnw9/eHnp4e9uzZA319/ee219PTg56enlrnICISy+rjd5DyJB9O5nUwzMtR7DhE1Y7aBdLAgQNx9uxZfP/998olR5o1a4aIiAi0bq3+3RHBwcEYMWIE2rZti/bt22PJkiWQyWQYNWoUACAoKAj169dHSEgIAGDSpEnw9fXFokWL0KdPH2zatAnnz5/H6tWrlcdMS0tDfHw8Hjx4AAC4ceMGgKLeJxsbG2RmZqJHjx7Izs7Gb7/9hszMTOWYIktLS0ilUrVfBxGRpkjMyMXqE0Xz0k3v5Qpd7Zea0YWoVqrQLVuenp747bffKiVAYGAgHj16hNmzZyMxMREeHh44cOCAciB2fHw8tLT+++b28fHBxo0b8fnnn2PmzJlwcXHBrl270LJlS2WbPXv2KAssABgyZAgAYM6cOZg7dy4uXryIs2fPAii6ZPi0mJgYODk5VcprIyISw6JDN5BboEBbx3rwb6H+8AMiqsA8SPv27YNUKoW/v7/K9oMHD0KhUKBXr16VGlBTcR4kItJEVx9kos+yExAEYOdHPmjtUE/sSEQapcrmQZo+fTrkcnmp7YIglDmxIxERvToh+69BEIA33GxZHBG9BLULpFu3bqF58+altru6uuL27duVEoqIiNR3/OYjnLiVAh2pBJ/4u4odh6haU7tAMjU1LXNR2tu3b8PQ0LBSQhERkXrkCgHz/7oGABjh7QQHc04KSfQy1C6Q+vfvj8mTJ+POnTvKbbdv38bUqVPRr1+/Sg1HRETls+1CAm4kZcHUQAfjX+ekkEQvS+0CaeHChTA0NISrqyucnZ3h7OyMZs2awdzcHN99911VZCQioueQ5RVi0aGiSSEnvN4YdevoipyIqPpT+zZ/U1NTnD59GqGhobh8+TIMDAzg5uaGLl26VEU+IiJ6gTUn7iI5Kw8OZnXwjjcnhSSqDBWaB0kikaBHjx7o0aMHACA9Pb0yMxERUTklZ+Zi9d9F40I/6dkUetqc6JaoMqh9iW3BggXYvHmz8uPBgwfD3Nwc9evXx+XLlys1HBERPd/3h28iO18OD/u66NPKVuw4RDWG2gXSqlWrlCvZh4aGIjQ0FPv370evXr3w8ccfV3pAIiIq243ELGw+V7Rw9ud9mkEikYiciKjmUPsSW2JiorJA2rt3LwYPHowePXrAyckJXl5elR6QiIjKFrL/GhQC0KulDdo6mYkdh6hGUbsHqV69ekhIKPqL5cCBA/Dz8wNQNJN2WTNsExFR5Tt5KwXHbjyCtpYEn/bkpJBElU3tHqQBAwZg2LBhcHFxQWpqqnLttUuXLpVa+JWIiCqfXCHg631Fk0K+3cERThacpJeosqldIH3//fdwcnJCQkICFi5cCCMjIwDAw4cP8dFHH1V6QCIiUrXz0n1ce5gJY31tTOzmInYcohpJIgiCIHaI6qi8qwETEVWmnHw5XvvuGBIzczGjlyvG+jYSOxJRtVLe399qj0EiIiLx/HzyLhIzc1G/rgFG+DiJHYeoxmKBRERUTTzKysPKY0XrYH7Ssyn0dTgpJFFVYYFERFRNLA27CVm+HG4NTNHXzU7sOEQ1WoWWGiEioldHrhDw961H+COiaIqVmb2bQUuLk0ISVSW1C6QRI0ZgzJgxXJyWiKgKyRUCImLSsC/qIQ78k4hHWXkAgO7NrdGhobnI6YhqPrULpIyMDPj5+cHR0RGjRo3CiBEjUL9+/arIRkRUq8gVAs7GpBYVRdFJSHmSp9xnrK+Nni1sML0XJ4UkehUqdJv/o0ePsGHDBqxfvx5Xr16Fn58fxowZg/79+0NHR6cqcmoc3uZPRJWhUK5AREwa/op6iIP/JCLlSb5yn4m+Nnq0sEGfVrbo2NgCutocNkr0ssr7+/ul50G6ePEi1q5di59++glGRkZ4++238dFHH8HFpWZPXsYCiYgqqlCuwNnioig6Eamy/4oiUwMd9Ghujd5utujYiEURUWUr7+/vlxqk/fDhQ4SGhiI0NBRSqRS9e/dGVFQUmjdvjoULF2LKlCkvc3giohqjUK7AmbtFRdGhf1SLorp1/i2K/u0p0pGyKCISm9oFUkFBAfbs2YO1a9fi0KFDcHNzw+TJkzFs2DBlJbZz506MHj2aBRIR1WqFcgXC7xaNKTr4TxLSniqK6tXRgX8LG/RqZQufRuYsiog0jNoFkq2tLRQKBYYOHYqIiAh4eHiUavPaa6+hbt26lRCPiKh6KZArEH6nuChKxOPsAuW+enV00LOlDXq3skWHhiyKiDRZhRarHTRoEPT19Z/Zpm7duoiJiXmpYERE1UWBXIHTd1Kx78pDHLqqWhSZGerC/9+B1h0amkGbRRFRtaB2gXT06FEEBASUKpBkMhkmTJiAX375pdLCERFpqgK5Aqdup2Bf1EMcupqE9KeKInNDXfi3LCqKvJxZFBFVR2rfxSaVSvHw4UNYWVmpbE9JSYGNjQ0KCwsrNaCm4l1sRLVPfqECp+6k/NtTlISMnP+KIguj/3qK2rMoItJYlX4XW2ZmJgRBgCAIyMrKUulBksvl2LdvX6miiYioussvLOop+ivqIUJLFUV66Nmy6O4zL2dzSLn8B1GNUe4CqW7dupBIJJBIJGjSpEmp/RKJBPPmzavUcEREYsgvVODk7Uf460oiQq8mIjP3v55xCyM99Pp3oHV7ZzMWRUQ1VLkLpKNHj0IQBLz++uvYvn07zMzMlPt0dXXh6OgIOzuuLk1E1ZcgCNgXlYi5f/6jXPsMACyN/yuK2jmxKCKqDcpdIPn6+gIAYmJi4ODgAImEPyCIqOZIyszFrF3ROHQ1CUBRUdT736KoLYsiolqnXAXSlStX0LJlS2hpaSEjIwNRUVHPbOvm5lZp4YiIqpogCNh8LgFf77uGrNxCaGtJ8NFrjTHutUbQ05aKHY+IRFKuAsnDwwOJiYmwsrKCh4cHJBIJyrr5TSKRQC6XV3pIIqKqEJcqw4wdUTh9JxUA4N7AFAvecoOrDe9MJartylUgxcTEwNLSUvl/IqLqTK4Q8MvJGCwKvYHcAgX0dbQwrUdTjOrozEtpRASgnAWSo6MjgKJ12ObNm4dZs2bB2dm5SoMREVWF64mZ+HTbFVy+lwEA8GlkjpABreBobihyMiLSJGrNZKajo4Pt27dXVRYioiqTVyjH4tCbeOOHk7h8LwPG+tpYMLAVfn/Xi8UREZWi9lSvAQEB2LVrVxVEISKqGhfiHqPPDyfxQ9gtFCoE9GhujcPBvghsxztyiahsaq/F5uLigi+++AKnTp2Cp6cnDA1V//KaOHFipYUjInoZsrxCfHfoBtadjoUgFC0H8kX/lujV0oaFERE9l9prsT1v7JFEIsHdu3dfOlR1wLXYiDTb3zcfYcaOKNxPzwEADGzTALPeaIa6dXRFTkZEYqr0tdiK8S42ItJk6dn5+Oqva9h24R4AoH5dA8wf0Aq+TSxFTkZE1YnaBRIRkSYSBAH7oxMxe/c/SHmSB4kEGOHthI/9m8JQjz/qiEg9Ffqpce/ePezZswfx8fHIz89X2bd48eJKCUZEVF7JmbmYtTsaB/8pWiaksZURFgx0g6djPZGTEVF1pXaBFBYWhn79+qFhw4a4fv06WrZsidjYWAiCgDZt2lRFRiKiMgmCgC3nE/DVX08tE9K1Eca93pjLhBDRS1G7QJoxYwamTZuGefPmwdjYGNu3b4eVlRWGDx+Onj17VkVGIqJSSi4T4tbAFAsGuqGZLW+aIKKXp3aBdO3aNfzxxx9FT9bWRk5ODoyMjPDFF1+gf//++PDDDys9JBFRMblCwNpTMfju0H/LhEzt3hSjOjpBW6r21G5ERGVSu0AyNDRUjjuytbXFnTt30KJFCwBASkpK5aYjInrK9cRMfLo9CpcT0gEA3g3N8c1ALhNCRJVP7QKpQ4cOOHnyJJo1a4bevXtj6tSpiIqKwo4dO9ChQ4eqyEhEtVxeoRwrjt7Bj0dvo1AhwFhfG5/1bobAdvac8JGIqoTa/dGLFy+Gl5cXAGDevHno1q0bNm/eDCcnJ/z8888VCrFixQo4OTlBX18fXl5eiIiIeG77rVu3wtXVFfr6+mjVqhX27dunsn/Hjh3o0aMHzM3NIZFIEBkZWeoYubm5GDduHMzNzWFkZISBAwciKSmpQvmJqOpcjH+MN55aJqT7v8uEDGnPZUKIqOqoXSA1bNgQbm5uAIout61atQpXrlzB9u3b4ejoqHaAzZs3Izg4GHPmzMHFixfh7u4Of39/JCcnl9n+9OnTGDp0KMaMGYNLly4hICAAAQEBiI6OVraRyWTo1KkTFixY8MzzTpkyBX/++Se2bt2K48eP48GDBxgwYIDa+YmoasjyCjHvz38wcOVp3Ep+AgsjXawY1gar3/GEtYm+2PGIqIZTe6mRyubl5YV27dph+fLlAACFQgF7e3tMmDAB06dPL9U+MDAQMpkMe/fuVW7r0KEDPDw8sGrVKpW2sbGxcHZ2xqVLl+Dh4aHcnpGRAUtLS2zcuBFvvfUWAOD69eto1qwZwsPDy3WpkEuNEFWdE7eKlgm59/i/ZUI+79MM9Qy5TAgRvZxKXWqkXr165e7KTktLK19CAPn5+bhw4QJmzJih3KalpQU/Pz+Eh4eX+Zzw8HAEBwerbPP398euXbvKfd4LFy6goKAAfn5+ym2urq5wcHAod4FERJWPy4QQkaYoV4G0ZMmSKjl5SkoK5HI5rK2tVbZbW1vj+vXrZT4nMTGxzPaJiYnlPm9iYiJ0dXVRt27dch8nLy8PeXl5yo8zMzPLfT4ierH9UQ8xi8uEEJGGKNdPnhEjRlR1Do0XEhKCefPmiR2DqMYpuUxII0tDLHzLDZ6OZiInI6LarFwFUmZmpvI63Yt6TtQZj2NhYQGpVFrq7rGkpCTY2NiU+RwbGxu12j/rGPn5+UhPT1fpRXrecWbMmKFyaS8zMxP29vblPicRlXbwn0RM23qZy4QQkcYp111s9erVU95VVrduXdSrV6/Uo3i7OnR1deHp6YmwsDDlNoVCgbCwMHh7e5f5HG9vb5X2ABAaGvrM9mXx9PSEjo6OynFu3LiB+Pj4Zx5HT08PJiYmKg8iqrgTtx5h/MaLyMothFsDU/w5oROCezRlcUREGqFcPUhHjhyBmVlRd/fRo0crNUBwcDBGjBiBtm3bon379liyZAlkMhlGjRoFAAgKCkL9+vUREhICAJg0aRJ8fX2xaNEi9OnTB5s2bcL58+exevVq5THT0tIQHx+PBw8eACgqfoCiniMbGxuYmppizJgxCA4OhpmZGUxMTDBhwgR4e3tzgDbRK3DlXjrGbriAArmAPm62WBrowWVCiEizCBpg2bJlgoODg6Crqyu0b99eOHPmjHKfr6+vMGLECJX2W7ZsEZo0aSLo6uoKLVq0EP766y+V/WvXrhUAlHrMmTNH2SYnJ0f46KOPhHr16gl16tQR3nzzTeHhw4flzpyRkSEAEDIyMir0molqqzvJWULrLw4Jjp/uFYatCRdyCwrFjkREtUh5f39XaB6k3NxcXLlyBcnJyVAoFCr7+vXr9/JVWzXAeZCI1JeUmYuBK0/j3uMctKpvij/e7wAj3qVGRK9Qpc6D9LQDBw4gKCiozIVpJRIJ5HK5uockologI6cAI36JwL3HOXAyr4O1o9qxOCIijaX2Rf8JEyZg0KBBePjwIRQKhcqDxRERlSW3QI731p/H9cQsWBrrYcMYL1gY6Ykdi4jomdQukJKSkhAcHFxqskYiorIUyhWY+MclRMSmwVhPG+tHtYe9WR2xYxERPZfaBdJbb72FY8eOVUEUIqppBEHArN3ROHQ1CbraWlgzoi2a23HMHhFpPrUHACxfvhyDBg3CiRMn0KpVK+jo6KjsnzhxYqWFI6LqbXHoTfwRkQAtCfDDEA90aGgudiQionJRu0D6448/cOjQIejr6+PYsWMqi9hKJBIWSEQEAFh3KgbLjtwGAHwV0Ao9W9qKnIiIqPzULpA+++wzzJs3D9OnT4eWFid2I6LS/rz8APP2XgUABHdvgmFeDiInIiJSj9oVTn5+PgIDA1kcEVGZTt5KQfCWSAgCEOTtiAmvNxY7EhGR2tSuckaMGIHNmzdXRRYiquai7mVg7IbzRUuItLLFnL4tVC7DExFVF2pfYpPL5Vi4cCEOHjwINze3UoO0Fy9eXGnhiKj6iEmRYeTaCMjy5fBpZI7Fge6QarE4IqLqSe0CKSoqCq1btwYAREdHq+zjX4pEtVNyZi6CfjmLVFk+WtY3wf/e8YSetlTsWEREFaZ2gXT06NGqyEFE1VRmbgFGrD2HhLQcOJrXwdqR7WGsr/PiJxIRaTCOtCaiCiteQuTaw0xYGOlhw2gvWBpzCREiqv7K1YM0YMAArFu3DiYmJhgwYMBz2+7YsaNSghGRZpMrBEzadAlnY9JgpKeN9aPbwcGcS4gQUc1QrgLJ1NRUOb7I1NS0SgMRkeYTBAGf74rGwX+SoCvVwuogT7Sw488GIqo5JIIgCGKHqI4yMzNhamqKjIwMmJhwbSmqXRaH3sQPYbcgkQA/DmuDXq04SzYRVQ/l/f2t9hiknJwcZGdnKz+Oi4vDkiVLcOjQoYolJaJqZUN4LH4IuwUA+LJ/SxZHRFQjqV0g9e/fH7/++isAID09He3bt8eiRYvQv39/rFy5stIDEpHm2HvlAWbv+QcAMNnPBW93cBQ5ERFR1VC7QLp48SI6d+4MANi2bRtsbGwQFxeHX3/9FT/88EOlByQizXDqdgqmbC5aQuTtDg6Y1M1F7EhERFVG7QIpOzsbxsbGAIBDhw5hwIAB0NLSQocOHRAXF1fpAYlIfNH3M/D+r0VLiPRuZYN5/VpyYlgiqtHULpAaN26MXbt2ISEhAQcPHkSPHj0AAMnJyRysTFQDxT61hIh3Q3N8H+jBJUSIqMZTu0CaPXs2pk2bBicnJ3h5ecHb2xtAUW9S8RIkRFQzJGflIuiXCKQ8yUdzWxOsDuISIkRUO1ToNv/ExEQ8fPgQ7u7u0NIqqrEiIiJgYmICV1fXSg+piXibP9V0mbkFCPzfGVx7mAkHszrY9qE3rIz1xY5FRPRSyvv7W+212ADAxsYGNjY2Ktvat29fkUMRkQbKLZDj/V+LlxDRxYYx7VkcEVGtwrXYiEiFXCFg8qZInLlbtITIulHt4WhuKHYsIqJXigUSESkJgoBZu6Nx4J/EoiVE3vFEy/pcQoSIah8WSESktOTwLWw8Gw+JBFgyxAM+jS3EjkREJAoWSEQEANhwJg5L/11C5Iv+LdGbS4gQUS3GAomIsC/qIWbvjgYATOrmgne4hAgR1XIskIhqudO3UzB5U9ESIsO8HDDZj0uIEBGxQCKqxaLvZ+D9DReQL1egZwsbfNmfS4gQEQEskIhqrbhUGUauPYcneYXo0NAMS4ZwCREiomIskIhqoUdZeXjn5wikPMlDM1sTrA5qC30dLiFCRFSMBRJRLZOVW4CRayMQn5YNezMDrB/dDib6OmLHIiLSKCyQiGqRvEI53v/1Av558O8SIqO9uIQIEVEZWCBRuRy9nowt5xIgyysUOwpVkFwhYMrmSITfTYWhrhTrRrWHkwWXECEiKkuFFqul2uXs3VSMXn8OggB8ufcqBrezR5C3I9fnqkZSn+Thu0M3sS/q3yVEgtpyCREioudggUTPlZVbgKlbL0MQACM9bWTlFeLnkzH45VQMurlaYVRHZ/g0Muet4RomI6cAZ++m4vSdVJy5m4rriVkAAIkEWBzojo5cQoSI6LlYINFzfbn3Ku49zoG9mQH+mtgZF+IeY92pWBy/+QiHryXj8LVkuFgZYWRHJ7zZuj7q6PJLSgxP8gpxLjYN4XdSEX4nFdEPMiAIqm1cbYzxYddGeMPNTpyQRETViEQQSv4YpfLIzMyEqakpMjIyYGJiInacKnHon0S8v+ECJBJg8/veaO9sptx359ET/Ho6Ftsu3IMsXw4AMNHXxpD2DningyPszeqIFbtWyC2Q40LcY5y+k4LwO6m4fC8DcoXqt3JDS0N4NzSHTyMLdGhoBnMjPZHSEhFpjvL+/maBVEE1vUBKeZIH/+//RqosH2N9G2JGr2ZltsvMLcDW8/ew/nQs4tOyAQBaEqB7c2uM9HFGh4ZmvPxWCfILFYhMSFcWRJfi05EvV6i0sTczUBZE3o3MYW3Cu9OIiEpigVTFanKBJAgC3t9wAaFXk+BqY4zd4ztCT/v5kwjKFQKO3UjGutOxOHErRbnd1cYYI32cENC6PiciVEOhXIGo+xnKMUTnYtOQW6BaENmY6MO7kXnRo6E5e+2IiMqBBVIVq8kF0tbzCfh42xXoSCXYPa4Tmtup9/puJWVh3elY7Lh4HzkFRZff6tbRwdB/L7/Z1TWoitjVmkIh4OrDTJz5d2B1REwanpSYUsHcUBcdGpnD59+CyNnCkL1zRERqYoFUxWpqgZSQlo1eS0/gSV4hPu3pig+7NqrwsTKyC7DlfALWh8fi3uMcAIBUSwL/FkWX39o51au1v+AFQcCt5CcIv5OK03dScDYmDenZBSptTPS10aHhvwVRIws0sTaqtZ8vIqLKwgKpitXEAkmhEDB0zRmcjUlDO6d62PS+d6UsXipXCDh8LQnrTsUi/G6qcnsLOxOM9HFCX3e7Gn/5TRAExKZmKwuiM3dTkfIkX6WNoa4U7Z3NlGOImtmacPFYIqJKxgKpitXEAmnN33fx9b5rMNSVYv+kLnAwr/wxLdcTM7H+38tveYVFY2rMDHUxrL0D3u7gCBvTmjOw+N7jbOVt9+F3U/EwI1dlv562Fto5mSnHEbWqbwodKSe3JyKqSiyQqlhNK5BuJGah77KTyJcr8M2AVhjS3qFKz/dYlo9N5xKwITwWD/4tHLS1JOjZ0gajOjqjjUPdanE5SRAEpDzJR1yqDDEpMsSmyhCbko2o+xnKu/qK6UglaO1Q7987zczh4VD3hYPfiYiocrFAqmI1qUDKL1QgYMUpXH2YiW6uVvhpRNtXVpwUyhUIvZqEtadjERGTptzu1sAUI32c0MfNVvQiQhAEpMnyEZsqQ0xKNmKLC6FUGeJSspH1jPXppFoSuDUwVd567+lYDwa6LIiIiMRUrQqkFStW4Ntvv0ViYiLc3d2xbNkytG/f/pntt27dilmzZiE2NhYuLi5YsGABevfurdwvCALmzJmDNWvWID09HR07dsTKlSvh4uKibHPz5k18/PHHOHXqFPLz8+Hm5oYvv/wSr732Wrky16QC6duD17Hi6B3Uq6ODg1O6iLa6e/T9DKw/HYvdlx8g/9/LbxZGehju5YDhXg6wqsJ5fQRBwOPsgqJeoBRZUY9Q6n/FUFbusxfplUgAO1MDOFnUgZO5IZwtDNHYygiejvVgrK9TZZmJiEh91aZA2rx5M4KCgrBq1Sp4eXlhyZIl2Lp1K27cuAErK6tS7U+fPo0uXbogJCQEb7zxBjZu3IgFCxbg4sWLaNmyJQBgwYIFCAkJwfr16+Hs7IxZs2YhKioKV69ehb5+0S/ZJk2awMXFBSEhITAwMMCSJUuwbt063LlzBzY2Ni/MXVMKpAtxaRi0KhwKAVj1dhv0bGkrdiSkPsn79/JbHBIziy6/6Ugl6NPKFiM7OsPDvm6Fj/1Ylo+Y1H8LoKd7g1JkyHxOEQQAdqb6cLIwhJOFIZzNDeFoXgfOFoawN6tT4weZExHVFNWmQPLy8kK7du2wfPlyAIBCoYC9vT0mTJiA6dOnl2ofGBgImUyGvXv3Krd16NABHh4eWLVqFQRBgJ2dHaZOnYpp06YBADIyMmBtbY1169ZhyJAhSElJgaWlJf7++2907twZAJCVlQUTExOEhobCz8/vhblrQoEkyytE7x9OIC41GwPa1MfiwR5iR1JRIFfg4D+JWHsqFhfiHiu3e9jXxaiOTujV0ha62qUHNadn5yMmRYa41Oz/xgX92xuUkVNQqv3TbE314WReVAQ5mdcpKoYsDOHAIoiIqEYo7+9vUVcWzc/Px4ULFzBjxgzlNi0tLfj5+SE8PLzM54SHhyM4OFhlm7+/P3bt2gUAiImJQWJiokqRY2pqCi8vL4SHh2PIkCEwNzdH06ZN8euvv6JNmzbQ09PD//73P1hZWcHT07PyX6iG+nrfNcSlZsPOVB9z+7UQO04pOlItvOFmhzfc7HDlXjrWnY7F3ssPEZmQjkmbIvG18TUMaWcPLS3Jvz1B2YhNlZWaT6gkGxN95eWwokLovyKIY4SIiAgQuUBKSUmBXC6HtbW1ynZra2tcv369zOckJiaW2T4xMVG5v3jbs9pIJBIcPnwYAQEBMDY2hpaWFqysrHDgwAHUq1evzPPm5eUhLy9P+XFmZqYar1TzHL2RjI1n4wEA3w1yh4mGj5Vxa1AXiwd7YEavZth4Nh6/nY1DclYefjhyu8z21iZ6cDQvuhRW1AtUB47/Xharoyvqlz0REVUDtfI3hSAIGDduHKysrHDixAkYGBjgp59+Qt++fXHu3DnY2pYehxMSEoJ58+aJkLbyPZbl45NtVwAAozs6w6exhciJys/SWA+T/FzwYddG2B/9EPujEmFioK3sCSrqFWIRREREL0fU3yIWFhaQSqVISkpS2Z6UlPTMgdI2NjbPbV/8b1JSkkqhk5SUBA8PDwDAkSNHsHfvXjx+/Fh5/fHHH39EaGgo1q9fX+bYpxkzZqhc2svMzIS9vb2ar1h8giDg813ReJSVh8ZWRvikZ1OxI1WIrrYW+nvUR3+P+mJHISKiGkjUaXt1dXXh6emJsLAw5TaFQoGwsDB4e3uX+Rxvb2+V9gAQGhqqbO/s7AwbGxuVNpmZmTh79qyyTXZ20QR+WlqqL19LSwsKheqK6cX09PRgYmKi8qiOdkc+wF9RD6GtJcGSQA8OPCYiIiqD6NchgoODMWLECLRt2xbt27fHkiVLIJPJMGrUKABAUFAQ6tevj5CQEADApEmT4Ovri0WLFqFPnz7YtGkTzp8/j9WrVwMoGl80efJkfPXVV3BxcVHe5m9nZ4eAgAAARUVWvXr1MGLECMyePRsGBgZYs2YNYmJi0KdPH1E+D6/Cg/QczNodDQCY1M0FLeubipyIiIhIM4leIAUGBuLRo0eYPXs2EhMT4eHhgQMHDigHWcfHx6v09Pj4+GDjxo34/PPPMXPmTLi4uGDXrl3KOZAA4JNPPoFMJsP777+P9PR0dOrUCQcOHFDOgWRhYYEDBw7gs88+w+uvv46CggK0aNECu3fvhru7+6v9BLwiCoWAj7ddRlZuITzs6+LDro3EjkRERKSxRJ8HqbqqbvMgrTsVg7l/XoW+jhb2TeyMhpZGYkciIiJ65cr7+5tLh9cCt5OfIGR/0bQJn/VuxuKIiIjoBVgg1XAFcgWCt0Qir1CBLk0s8XYHR7EjERERaTwWSDXc8iO3ceVeBkwNdLBwoBskEonYkYiIiDQeC6QaLDIhHcuPFs00/WVAS9iY6ouciIiIqHpggVRD5eTLEbwlEnKFgL7udujnbid2JCIiomqDBVINteDAddx9JIO1iR6+7K95C9ESERFpMhZINdCJW4+w7nQsAODbt9xRt46uuIGIiIiqGRZINUxGdgE+3lq0EO07HRzRpYmlyImIiIiqHxZINczsPdFIzMyFs4UhZvR2FTsOERFRtcQCqQbZe+UBdkc+gFRLgsWD3VFHV/SVZIiIiKolFkg1RHJmLj7fVbQQ7biujdDaoZ7IiYiIiKovFkg1gCAI+GT7FaRnF6BlfRNM6OYidiQiIqJqjQVSDfD72Xgcu/EIutpa+H6wB3SkfFuJiIheBn+TVnMxKTJ8/dc1AMCnPV3hYm0sciIiIqLqjwVSNVb470K0OQVy+DQyxygfJ7EjERER1QgskKqx//19F5fi02Gsp41vB7lDS4sL0RIREVUGFkjVVPT9DHwfehMAMLdfC9SvayByIiIiopqDBVI1lFsgx5TNkShUCOjZwgYD2tQXOxIREVGNwgKpGvru4A3cSn4CCyM9zB/QChIJL60RERFVJhZI1Uz4nVT8fCoGALDwrVYwM+RCtERERJWNBVI1kpVbgGlbL0MQgKHt7fG6q7XYkYiIiGokFkjVyLw/r+J+eg7szQzwWZ/mYschIiKqsVggVRMH/0nEtgv3IJEAiwd7wEiPC9ESERFVFRZI1cCjrDzM2BEFABjbpRHaOZmJnIiIiKhmY4Gk4QRBwIwdV5Amy4erjTGmdOdCtERERFWNBZKG23r+Hg5fS4auVAvfB3pAT1sqdiQiIqIajwWSBktIy8a8P/8BAAT3aIJmtiYiJyIiIqodWCBpKLlCwNQtlyHLl6O9kxne69xQ7EhERES1BgskDfXTibuIiE2Doa4Uiwa7Q8qFaImIiF4ZFkga6NrDTCw6VLQQ7ey+zWFvVkfkRERERLULCyQNk1dYtBBtvlwBv2ZWGNzWXuxIREREtQ4LJA2z5PAtXE/MgpmhLkIGuHEhWiIiIhGwQNIwWpKix/w3W8HSWE/sOERERLUS16vQMB/7u2JgmwZoaGkkdhQiIqJaiz1IGojFERERkbhYIBERERGVwAKJiIiIqAQWSEREREQlsEAiIiIiKoEFEhEREVEJLJCIiIiISmCBRERERFQCCyQiIiKiElggEREREZXAAomIiIioBBZIRERERCWwQCIiIiIqgQUSERERUQnaYgeorgRBAABkZmaKnISIiIjKq/j3dvHv8WdhgVRBWVlZAAB7e3uRkxAREZG6srKyYGpq+sz9EuFFJRSVSaFQ4MGDBzA2NoZEIqm042ZmZsLe3h4JCQkwMTGptOO+LOYqP03MBGhmLk3MBGhmLk3MBDCXOjQxE6CZuaoykyAIyMrKgp2dHbS0nj3SiD1IFaSlpYUGDRpU2fFNTEw05gv1acxVfpqYCdDMXJqYCdDMXJqYCWAudWhiJkAzc1VVpuf1HBXjIG0iIiKiElggEREREZXAAknD6OnpYc6cOdDT0xM7igrmKj9NzARoZi5NzARoZi5NzAQwlzo0MROgmbk0IRMHaRMRERGVwB4kIiIiohJYIBERERGVwAKJiIiIqAQWSEREREQlsEDSMCtWrICTkxP09fXh5eWFiIgIUfP8/fff6Nu3L+zs7CCRSLBr1y5R8wBASEgI2rVrB2NjY1hZWSEgIAA3btwQOxZWrlwJNzc35cRm3t7e2L9/v9ixVHzzzTeQSCSYPHmyqDnmzp0LiUSi8nB1dRU1EwDcv38fb7/9NszNzWFgYIBWrVrh/PnzomZycnIq9bmSSCQYN26cqLnkcjlmzZoFZ2dnGBgYoFGjRvjyyy9fuL5VVcvKysLkyZPh6OgIAwMD+Pj44Ny5c680w4t+bgqCgNmzZ8PW1hYGBgbw8/PDrVu3RM20Y8cO9OjRA+bm5pBIJIiMjKzSPOXJVVBQgE8//RStWrWCoaEh7OzsEBQUhAcPHrySbCyQNMjmzZsRHByMOXPm4OLFi3B3d4e/vz+Sk5NFyySTyeDu7o4VK1aIlqGk48ePY9y4cThz5gxCQ0NRUFCAHj16QCaTiZqrQYMG+Oabb3DhwgWcP38er7/+Ovr3749//vlH1FzFzp07h//9739wc3MTOwoAoEWLFnj48KHycfLkSVHzPH78GB07doSOjg7279+Pq1evYtGiRahXr56ouc6dO6fyeQoNDQUADBo0SNRcCxYswMqVK7F8+XJcu3YNCxYswMKFC7Fs2TJRc7377rsIDQ3Fhg0bEBUVhR49esDPzw/3799/ZRle9HNz4cKF+OGHH7Bq1SqcPXsWhoaG8Pf3R25urmiZZDIZOnXqhAULFlRZBnVzZWdn4+LFi5g1axYuXryIHTt24MaNG+jXr9+rCSeQxmjfvr0wbtw45cdyuVyws7MTQkJCREz1HwDCzp07xY5RSnJysgBAOH78uNhRSqlXr57w008/iR1DyMrKElxcXITQ0FDB19dXmDRpkqh55syZI7i7u4uaoaRPP/1U6NSpk9gxXmjSpElCo0aNBIVCIWqOPn36CKNHj1bZNmDAAGH48OEiJRKE7OxsQSqVCnv37lXZ3qZNG+Gzzz4TJVPJn5sKhUKwsbERvv32W+W29PR0QU9PT/jjjz9EyfS0mJgYAYBw6dKlV5LlaeX5HRMRESEAEOLi4qo8D3uQNER+fj4uXLgAPz8/5TYtLS34+fkhPDxcxGSaLyMjAwBgZmYmcpL/yOVybNq0CTKZDN7e3mLHwbhx49CnTx+Vry+x3bp1C3Z2dmjYsCGGDx+O+Ph4UfPs2bMHbdu2xaBBg2BlZYXWrVtjzZo1omYqKT8/H7/99htGjx5dqYtkV4SPjw/CwsJw8+ZNAMDly5dx8uRJ9OrVS7RMhYWFkMvl0NfXV9luYGAgeg9lsZiYGCQmJqp8L5qamsLLy4s/68shIyMDEokEdevWrfJzcbFaDZGSkgK5XA5ra2uV7dbW1rh+/bpIqTSfQqHA5MmT0bFjR7Rs2VLsOIiKioK3tzdyc3NhZGSEnTt3onnz5qJm2rRpEy5evPjKx2E8j5eXF9atW4emTZvi4cOHmDdvHjp37ozo6GgYGxuLkunu3btYuXIlgoODMXPmTJw7dw4TJ06Erq4uRowYIUqmknbt2oX09HSMHDlS7CiYPn06MjMz4erqCqlUCrlcjq+//hrDhw8XLZOxsTG8vb3x5ZdfolmzZrC2tsYff/yB8PBwNG7cWLRcT0tMTASAMn/WF++jsuXm5uLTTz/F0KFDX8miuiyQqFobN24coqOjNeavw6ZNmyIyMhIZGRnYtm0bRowYgePHj4tWJCUkJGDSpEkIDQ0t9Ve1mJ7uZXBzc4OXlxccHR2xZcsWjBkzRpRMCoUCbdu2xfz58wEArVu3RnR0NFatWqUxBdLPP/+MXr16wc7OTuwo2LJlC37//Xds3LgRLVq0QGRkJCZPngw7OztRP18bNmzA6NGjUb9+fUilUrRp0wZDhw7FhQsXRMtEL6+goACDBw+GIAhYuXLlKzknL7FpCAsLC0ilUiQlJalsT0pKgo2NjUipNNv48eOxd+9eHD16FA0aNBA7DgBAV1cXjRs3hqenJ0JCQuDu7o6lS5eKlufChQtITk5GmzZtoK2tDW1tbRw/fhw//PADtLW1IZfLRcv2tLp166JJkya4ffu2aBlsbW1LFbLNmjUT/dJfsbi4OBw+fBjvvvuu2FEAAB9//DGmT5+OIUOGoFWrVnjnnXcwZcoUhISEiJqrUaNGOH78OJ48eYKEhARERESgoKAADRs2FDVXseKf5/xZX37FxVFcXBxCQ0NfSe8RwAJJY+jq6sLT0xNhYWHKbQqFAmFhYRoxhkWTCIKA8ePHY+fOnThy5AicnZ3FjvRMCoUCeXl5op2/W7duiIqKQmRkpPLRtm1bDB8+HJGRkZBKpaJle9qTJ09w584d2NraipahY8eOpaaLuHnzJhwdHUVKpGrt2rWwsrJCnz59xI4CoOgOIy0t1V8hUqkUCoVCpESqDA0NYWtri8ePH+PgwYPo37+/2JEAAM7OzrCxsVH5WZ+ZmYmzZ8/yZ30ZioujW7du4fDhwzA3N39l5+YlNg0SHByMESNGoG3btmjfvj2WLFkCmUyGUaNGiZbpyZMnKn/Vx8TEIDIyEmZmZnBwcBAl07hx47Bx40bs3r0bxsbGyuv2pqamMDAwECUTAMyYMQO9evWCg4MDsrKysHHjRhw7dgwHDx4ULZOxsXGpsVmGhoYwNzcXdczWtGnT0LdvXzg6OuLBgweYM2cOpFIphg4dKlqmKVOmwMfHB/Pnz8fgwYMRERGB1atXY/Xq1aJlKqZQKLB27VqMGDEC2tqa8WO7b9+++Prrr+Hg4IAWLVrg0qVLWLx4MUaPHi1qroMHD0IQBDRt2hS3b9/Gxx9/DFdX11f6c/RFPzcnT56Mr776Ci4uLnB2dsasWbNgZ2eHgIAA0TKlpaUhPj5eOcdQ8R8LNjY2Vdqz9bxctra2eOutt3Dx4kXs3bsXcrlc+fPezMwMurq6VZYLAG/z1zTLli0THBwcBF1dXaF9+/bCmTNnRM1z9OhRAUCpx4gRI0TLVFYeAMLatWtFyyQIgjB69GjB0dFR0NXVFSwtLYVu3boJhw4dEjVTWTThNv/AwEDB1tZW0NXVFerXry8EBgYKt2/fFjWTIAjCn3/+KbRs2VLQ09MTXF1dhdWrV4sdSRAEQTh48KAAQLhx44bYUZQyMzOFSZMmCQ4ODoK+vr7QsGFD4bPPPhPy8vJEzbV582ahYcOGgq6urmBjYyOMGzdOSE9Pf6UZXvRzU6FQCLNmzRKsra0FPT09oVu3blX+3r4o09q1a8vcP2fOHNFyFU85UNbj6NGjVZpLEARBIggiT3tKREREpGE4BomIiIioBBZIRERERCWwQCIiIiIqgQUSERERUQkskIiIiIhKYIFEREREVAILJCIiIqISWCARUY3XtWtXTJ48udzt161bh7p16z5zf2xsLCQSCSIjI186GxFpJhZIRERERCWwQCIiqqby8/PFjkBUY7FAIiJRdO3aFRMmTMDkyZNRr149WFtbY82aNcoFmo2NjdG4cWPs379f5XnHjx9H+/btoaenB1tbW0yfPh2FhYXK/TKZDEFBQTAyMoKtrS0WLVpU6tx5eXmYNm0a6tevD0NDQ3h5eeHYsWMVfi1yuRxjxoyBs7MzDAwM0LRpUyxdulS5/++//4aOjo5yoc1ikydPRufOnZUfnzx5Ep07d4aBgQHs7e0xceJEyGQy5X4nJyd8+eWXCAoKgomJCd5///0KZyai52OBRESiWb9+PSwsLBAREYEJEybgww8/xKBBg+Dj44OLFy+iR48eeOedd5CdnQ0AuH//Pnr37o127drh8uXLWLlyJX7++Wd89dVXymN+/PHHOH78OHbv3o1Dhw7h2LFjuHjxosp5x48fj/DwcGzatAlXrlzBoEGD0LNnT9y6datCr0OhUKBBgwbYunUrrl69itmzZ2PmzJnYsmULAKBLly5o2LAhNmzYoHxOQUEBfv/9d4wePRoAcOfOHfTs2RMDBw7ElStXsHnzZpw8eRLjx49XOdd3330Hd3d3XLp0CbNmzapQXiIqhypfDpeIqAy+vr5Cp06dlB8XFhYKhoaGwjvvvKPc9vDhQwGAEB4eLgiCIMycOVNo2rSpoFAolG1WrFghGBkZCXK5XMjKyhJ0dXWFLVu2KPenpqYKBgYGwqRJkwRBEIS4uDhBKpUK9+/fV8nTrVs3YcaMGYIgFK1sbmpq+szsxauMX7p06Zltxo0bJwwcOFD58YIFC4RmzZopP96+fbtgZGQkPHnyRBAEQRgzZozw/vvvqxzjxIkTgpaWlpCTkyMIgiA4OjoKAQEBzzwnEVUebbELNCKqvdzc3JT/l0qlMDc3R6tWrZTbrK2tAQDJyckAgGvXrsHb2xsSiUTZpmPHjnjy5Anu3buHx48fIz8/H15eXsr9ZmZmaNq0qfLjqKgoyOVyNGnSRCVLXl4ezM3NK/xaVqxYgV9++QXx8fHIyclBfn4+PDw8lPtHjhyJzz//HGfOnEGHDh2wbt06DB48GIaGhgCAy5cv48qVK/j999+VzxEEAQqFAjExMWjWrBkAoG3bthXOSETlxwKJiESjo6Oj8rFEIlHZVlwIKRSKSjvnkydPIJVKceHCBUilUpV9RkZGFTrmpk2bMG3aNCxatAje3t4wNjbGt99+i7NnzyrbWFlZoW/fvli7di2cnZ2xf/9+lXFPT548wdixYzFx4sRSx3dwcFD+v7igIqKqxQKJiKqNZs2aYfv27RAEQVk8nTp1CsbGxmjQoAHMzMygo6ODs2fPKouKx48f4+bNm/D19QUAtG7dGnK5HMnJySoDpF/GqVOn4OPjg48++ki57c6dO6Xavfvuuxg6dCgaNGiARo0aoWPHjsp9bdq0wdWrV9G4ceNKyUREL4eDtImo2vjoo4+QkJCACRMm4Pr169i9ezfmzJmD4OBgaGlpwcjICGPGjMHHH3+MI0eOIDo6GiNHjoSW1n8/6po0aYLhw4cjKCgIO3bsQExMDCIiIhASEoK//vqrQrlcXFxw/vx5HDx4EDdv3sSsWbNw7ty5Uu38/f1hYmKCr776CqNGjVLZ9+mnn+L06dMYP348IiMjcevWLezevbvUIG0iejVYIBFRtVG/fn3s27cPERERcHd3xwcffIAxY8bg888/V7b59ttv0blzZ/Tt2xd+fn7o1KkTPD09VY6zdu1aBAUFYerUqWjatCkCAgJw7tw5lUtZ6hg7diwGDBiAwMBAeHl5ITU1VaU3qZiWlhZGjhwJuVyOoKAglX1ubm44fvw4bt68ic6dO6N169aYPXs27OzsKpSJiF6ORBAEQewQRES1xZgxY/Do0SPs2bNH7ChE9Bwcg0RE9ApkZGQgKioKGzduZHFEVA2wQCIiegX69++PiIgIfPDBB+jevbvYcYjoBXiJjYiIiKgEDtImIiIiKoEFEhEREVEJLJCIiIiISmCBRERERFQCCyQiIiKiElggEREREZXAAomIiIioBBZIRERERCWwQCIiIiIq4f+XKERqs6RaAQAAAABJRU5ErkJggg==", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.plot(rsa_scores_bert)\n", "plt.xlabel('model layer')\n", "plt.xticks(range(len(rsa_scores_bert)))\n", "plt.ylabel('similarity score (pearson\\'s r)')\n", "plt.title('Model-brain similarity over model layers')\n", "plt.show()" ] }, { "cell_type": "markdown", "metadata": { "id": "vZjj2yuunrID" }, "source": [ "### **QUESTIONS**\n", "\n", "At first sight, the result above seems to nicely confirm the idea that the more contextualized embeddings from middle-to-high model layers show better alignment with human brain responses. But what have we really learned about language processing?\n", "\n", "To make sure that this result really captures something about the linguistic processes involved in story reading, we would ideally compare it to some 'control' or 'baseline' condition where we would _not_ expect the effect to occur. One option would be to compare results with a different brain region that we would not expect to be as much involved in language processing. Another option could be to shuffle the RDMs before computing the RSA scores, such that we compute the correlation between model and brain RDMs for unmatched TRs (you could do this several times to create a 'null distribution' of RSA scores). You might also want to see if the result can be reproduced at the group level (comparing RSA scores across individual subjects or computing a mean RDM for several subjects), compute some kind of 'noise ceiling' based on RDM-correlation across subjects ([Nili et al., 2014](https://doi.org/10.1371/journal.pcbi.1003553)), or compare to results using a different model architecture (like GPT-2).\n", "\n", "Choose one of the options above, and compare the result obtained above to your 'baseline' / 'control' condition or analysis extension. Then write a concise report (less than one page) describing the approach you have used and answering the following questions:\n", "\n", "- Do your new results still confirm the idea that contextualized embeddings from middle-to-high model layers show better alignment with language processing in the human brain?\n", "- Why is your particular baseline / control / extension important to include in analyses comparing DNN activations and brain responses?\n", "- What are some limitations of this particular baseline / control / extension for your analysis (i.e., alternative explanations that it does not rule out yet)?\n", "\n", "Please also include in your report one (or more) plot(s) comparing the result obtained above to your 'baseline' / 'control' condition or analysis extension. The plot doesn't count towards the page limit." ] } ], "metadata": { "colab": { "provenance": [], "toc_visible": true }, "kernelspec": { "display_name": "Python 3.7.6 64-bit ('3.7.6')", "language": "python", "name": "python3" }, "language_info": { "name": "python", "version": "3.7.6" }, "vscode": { "interpreter": { "hash": "e9865b8fc30c7210bbbe2c0b0464dbc9700000eff1f4e229588b0a8358506f7f" } }, "widgets": { "application/vnd.jupyter.widget-state+json": { "0c06429c1c084ed182a108c4ba5a8df6": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_10f964364bf14f37a0b6368dcbba24a7", "placeholder": "​", "style": "IPY_MODEL_ab2018b8d26e4b458997008a6e68e4ef", "value": "tokenizer_config.json: 100%" } }, "10f964364bf14f37a0b6368dcbba24a7": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "125fcbfff304461894fb303a452a4ea3": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_4d8eba66d77944e1bead86786d8394bd", "max": 48, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_5daa68ad4a234283a1c11b5186dab0d2", "value": 48 } }, "13d3f3dca0fe432493efc7f0ad7343d6": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_14d420c1d4bd4551a9ebb5436811d626", "IPY_MODEL_32c8634bf147493582a7c89964b22b2e", "IPY_MODEL_67e3f45d827d4b47b5e683c69f9e70bc" ], "layout": "IPY_MODEL_8ffa2d196a284e73bb05a9ff103862ef" } }, "1456ea33502b4e7e8983a80e83bd2d28": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "14d420c1d4bd4551a9ebb5436811d626": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_bca42bf5e7c444d19cbc0717bfb7f4d6", "placeholder": "​", "style": "IPY_MODEL_88b4d5c1c8224c7394e7ea1a78e962ee", "value": "vocab.txt: 100%" } }, "14f6db644cc143808bced8e0bfb39cea": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "1548d053930146bcb292299212a2e6ca": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "15f8d58f0c274dd6a2af37658a06bec9": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_d1219abffacb4374915cef08607d68d9", "placeholder": "​", "style": "IPY_MODEL_c579f60b321849bfb06fb6ac7063b8c8", "value": "tokenizer.json: 100%" } }, "19f9c85fb156441d9b926e495042955f": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "1ac6f0d4fc9246fd83f8cd4786410923": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_f1dbfe41d5d1460da49d220ac8001887", "placeholder": "​", "style": "IPY_MODEL_d3e704478033467ca496b6589665a3a7", "value": "config.json: 100%" } }, "1e6c7231ab2c4263ad98690e1ab9d850": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "29241987ae854456b68c14ec7f47eb87": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_15f8d58f0c274dd6a2af37658a06bec9", "IPY_MODEL_2d1307f732974d4aa1026b880dc3e640", "IPY_MODEL_cfb8eb3e1ebf4d91a3f52c030f3642cc" ], "layout": "IPY_MODEL_1548d053930146bcb292299212a2e6ca" } }, "2d1307f732974d4aa1026b880dc3e640": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_19f9c85fb156441d9b926e495042955f", "max": 466062, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_1e6c7231ab2c4263ad98690e1ab9d850", "value": 466062 } }, "2d2d94db4ae74a18a8c026bf6dfb7f69": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "2e28ef8ae068431fb889a05b99013dd8": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_e859784c81c94b918bc6f7ceb2654dff", "IPY_MODEL_d08ac99657294f878301d6b557ae42f1", "IPY_MODEL_5a664cfcb8944bd3b1ded120fc7c02a0" ], "layout": "IPY_MODEL_4acfdd1354d4419e9abbd15765478ba2" } }, "32c8634bf147493582a7c89964b22b2e": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_6128fb10cc314d4993556095e95ef42d", "max": 231508, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_f2ef79b2274845f2baaf884f9941e283", "value": 231508 } }, "4552826de1b94795b538d21dbfb11565": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "45cbf543fa4c44f0bafce317e2540ff1": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_64be3bc93eaf40c684ff5e20e6fe4602", "placeholder": "​", "style": "IPY_MODEL_849d9eaeea8043c89c640260c9a6bc06", "value": " 570/570 [00:00<00:00, 10.5kB/s]" } }, "4acfdd1354d4419e9abbd15765478ba2": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "4c30d2a75a2849eaa5660ccbd8e02d05": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "4d8eba66d77944e1bead86786d8394bd": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "5a664cfcb8944bd3b1ded120fc7c02a0": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_ec6e1fc04b0f4aaba7adfdd94bed17de", "placeholder": "​", "style": "IPY_MODEL_a51d67530dd44e9ba2dec41bfa583c4a", "value": " 440M/440M [00:02<00:00, 200MB/s]" } }, "5daa68ad4a234283a1c11b5186dab0d2": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "6128fb10cc314d4993556095e95ef42d": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "64be3bc93eaf40c684ff5e20e6fe4602": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "66ab70e2df7c46059adfc2bb11f58351": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_1ac6f0d4fc9246fd83f8cd4786410923", "IPY_MODEL_9612167f10df4021b0cea3801d2c6775", "IPY_MODEL_45cbf543fa4c44f0bafce317e2540ff1" ], "layout": "IPY_MODEL_8d30e1d8a0c040eca00f7e0753ef6365" } }, "67e3f45d827d4b47b5e683c69f9e70bc": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_2d2d94db4ae74a18a8c026bf6dfb7f69", "placeholder": "​", "style": "IPY_MODEL_14f6db644cc143808bced8e0bfb39cea", "value": " 232k/232k [00:00<00:00, 1.40MB/s]" } }, "7523d49385b745a99a0461f997e57df8": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "849d9eaeea8043c89c640260c9a6bc06": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "88b4d5c1c8224c7394e7ea1a78e962ee": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "8d30e1d8a0c040eca00f7e0753ef6365": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "8ffa2d196a284e73bb05a9ff103862ef": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "9612167f10df4021b0cea3801d2c6775": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_9db88eeea7b640b2a53275ee9a817dcc", "max": 570, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_d3d9926272004bf09383ed71ef4950ba", "value": 570 } }, "9db88eeea7b640b2a53275ee9a817dcc": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "a51d67530dd44e9ba2dec41bfa583c4a": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "aa1996bf620246fcb5d77f38a3a85cdb": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "ab2018b8d26e4b458997008a6e68e4ef": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "b3857dd2378349c1b3cca864039a9ad8": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "bca42bf5e7c444d19cbc0717bfb7f4d6": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "c579f60b321849bfb06fb6ac7063b8c8": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "cfb8eb3e1ebf4d91a3f52c030f3642cc": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_f8f45ae0fda04767829b7ab0f13f8ae9", "placeholder": "​", "style": "IPY_MODEL_aa1996bf620246fcb5d77f38a3a85cdb", "value": " 466k/466k [00:00<00:00, 1.93MB/s]" } }, "d08ac99657294f878301d6b557ae42f1": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_f556230db104493daf232bcde7414f82", "max": 440449768, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_7523d49385b745a99a0461f997e57df8", "value": 440449768 } }, "d1219abffacb4374915cef08607d68d9": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d3d9926272004bf09383ed71ef4950ba": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "d3e704478033467ca496b6589665a3a7": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "d769b2b145ec4c6fb4512ca8eee03b04": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "dff032f7adff4384887736627e95ae48": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_0c06429c1c084ed182a108c4ba5a8df6", "IPY_MODEL_125fcbfff304461894fb303a452a4ea3", "IPY_MODEL_e211a8e743354e4a8383dbf95c409318" ], "layout": "IPY_MODEL_d769b2b145ec4c6fb4512ca8eee03b04" } }, "e211a8e743354e4a8383dbf95c409318": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_4c30d2a75a2849eaa5660ccbd8e02d05", "placeholder": "​", "style": "IPY_MODEL_1456ea33502b4e7e8983a80e83bd2d28", "value": " 48.0/48.0 [00:00<00:00, 1.40kB/s]" } }, "e859784c81c94b918bc6f7ceb2654dff": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_b3857dd2378349c1b3cca864039a9ad8", "placeholder": "​", "style": "IPY_MODEL_4552826de1b94795b538d21dbfb11565", "value": "model.safetensors: 100%" } }, "ec6e1fc04b0f4aaba7adfdd94bed17de": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "f1dbfe41d5d1460da49d220ac8001887": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "f2ef79b2274845f2baaf884f9941e283": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "f556230db104493daf232bcde7414f82": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "f8f45ae0fda04767829b7ab0f13f8ae9": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } } } } }, "nbformat": 4, "nbformat_minor": 0 }