Hugging Face's logo

NIHRDataInsights
/
HRCSResearchActivityCodes

Text Classification
Safetensors
bert
biology
medical
Model card Files
xet
 Community
AshleyBanksNIHR commited on
Commit
9ed5fb4
·
verified ·
1 Parent(s): 58b7cb1

Upload inference_script.ipynb

Browse files
Files changed (1) hide show
  1. inference/inference_script.ipynb +1021 -0
inference/inference_script.ipynb ADDED
@@ -0,0 +1,1021 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "code",
5
+ "execution_count": null,
6
+ "metadata": {
7
+ "colab": {
8
+ "base_uri": "https://localhost:8080/",
9
+ "height": 220,
10
+ "referenced_widgets": [
11
+ "d6d7368c1c7b4a549d9a706ee1a62785",
12
+ "0e22f97db509402a9b4d4a2fa8c80fe0",
13
+ "475728820f8e4b6fa0c33a1e9989179a",
14
+ "cf5e926c8c004525b5aad36d821ef928",
15
+ "9275c5cf7b314dc69419611128cb0c09",
16
+ "926c9a0562f3455b958c71bd0a138558",
17
+ "ef276c365d604dcc83b4a0133c6b7652",
18
+ "3dc315e087f44330badbb6749b0611a9",
19
+ "bc6c346b95424eb881b793bf6fd2f53e",
20
+ "c26db3dd5a86405b81f510fd759c3af7",
21
+ "dae2b5afeee243e682322c1ecb8238e6",
22
+ "f66e121a24e441c2a4cb32fb87d22632",
23
+ "1776c0895e7f400f85d3a2123cb573f1",
24
+ "e7fd82b589eb49aaba73aeafcc340421",
25
+ "210ec65a874a4f51ab9f059d3de804a9",
26
+ "c91d89b903ce4f02b635454d3bd87877",
27
+ "9cba2384346645499516a7923ad6fcef",
28
+ "491f71a8889c4c7aa0042e99f374be79",
29
+ "9f60072613d84754a0efe7813d853565",
30
+ "bf48a3e692ae4e6da5379152f51baa09",
31
+ "25529d785e9047e1b9bd197a7ec56773",
32
+ "9dda1a77133c4247bac106a9c4699153"
33
+ ]
34
+ },
35
+ "id": "Sm-TvQo5chAc",
36
+ "outputId": "031ba45c-fc02-4ee6-ddd4-eeca67c6f92e"
37
+ },
38
+ "outputs": [
39
+ {
40
+ "name": "stdout",
41
+ "output_type": "stream",
42
+ "text": [
43
+ "Initialising HRCS Classifier Pipeline...\n",
44
+ "Loading model and tokenizer from: NIHRDataInsights/HRCSHealthCategories...\n"
45
+ ]
46
+ },
47
+ {
48
+ "ename": "SSLError",
49
+ "evalue": "(MaxRetryError(\"HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /NIHRDataInsights/HRCSHealthCategories/resolve/main/tokenizer_config.json (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1000)')))\"), '(Request ID: c39f4927-7e74-4ee1-b0ff-59c87354a7cb)')",
50
+ "output_type": "error",
51
+ "traceback": [
52
+ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
53
+ "\u001b[1;31mSSLCertVerificationError\u001b[0m Traceback (most recent call last)",
54
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\urllib3\\connectionpool.py:466\u001b[0m, in \u001b[0;36mHTTPConnectionPool._make_request\u001b[1;34m(self, conn, method, url, body, headers, retries, timeout, chunked, response_conn, preload_content, decode_content, enforce_content_length)\u001b[0m\n\u001b[0;32m 465\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 466\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_validate_conn(conn)\n\u001b[0;32m 467\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (SocketTimeout, BaseSSLError) \u001b[38;5;28;01mas\u001b[39;00m e:\n",
55
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\urllib3\\connectionpool.py:1095\u001b[0m, in \u001b[0;36mHTTPSConnectionPool._validate_conn\u001b[1;34m(self, conn)\u001b[0m\n\u001b[0;32m 1094\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m conn\u001b[38;5;241m.\u001b[39mis_closed:\n\u001b[1;32m-> 1095\u001b[0m conn\u001b[38;5;241m.\u001b[39mconnect()\n\u001b[0;32m 1097\u001b[0m \u001b[38;5;66;03m# TODO revise this, see https://github.com/urllib3/urllib3/issues/2791\u001b[39;00m\n",
56
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\urllib3\\connection.py:730\u001b[0m, in \u001b[0;36mHTTPSConnection.connect\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 728\u001b[0m server_hostname_rm_dot \u001b[38;5;241m=\u001b[39m server_hostname\u001b[38;5;241m.\u001b[39mrstrip(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m--> 730\u001b[0m sock_and_verified \u001b[38;5;241m=\u001b[39m _ssl_wrap_socket_and_match_hostname(\n\u001b[0;32m 731\u001b[0m sock\u001b[38;5;241m=\u001b[39msock,\n\u001b[0;32m 732\u001b[0m cert_reqs\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcert_reqs,\n\u001b[0;32m 733\u001b[0m ssl_version\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mssl_version,\n\u001b[0;32m 734\u001b[0m ssl_minimum_version\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mssl_minimum_version,\n\u001b[0;32m 735\u001b[0m ssl_maximum_version\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mssl_maximum_version,\n\u001b[0;32m 736\u001b[0m ca_certs\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mca_certs,\n\u001b[0;32m 737\u001b[0m ca_cert_dir\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mca_cert_dir,\n\u001b[0;32m 738\u001b[0m ca_cert_data\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mca_cert_data,\n\u001b[0;32m 739\u001b[0m cert_file\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcert_file,\n\u001b[0;32m 740\u001b[0m key_file\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mkey_file,\n\u001b[0;32m 741\u001b[0m key_password\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mkey_password,\n\u001b[0;32m 742\u001b[0m server_hostname\u001b[38;5;241m=\u001b[39mserver_hostname_rm_dot,\n\u001b[0;32m 743\u001b[0m ssl_context\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mssl_context,\n\u001b[0;32m 744\u001b[0m tls_in_tls\u001b[38;5;241m=\u001b[39mtls_in_tls,\n\u001b[0;32m 745\u001b[0m assert_hostname\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39massert_hostname,\n\u001b[0;32m 746\u001b[0m assert_fingerprint\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39massert_fingerprint,\n\u001b[0;32m 747\u001b[0m )\n\u001b[0;32m 748\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msock \u001b[38;5;241m=\u001b[39m sock_and_verified\u001b[38;5;241m.\u001b[39msocket\n",
57
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\urllib3\\connection.py:909\u001b[0m, in \u001b[0;36m_ssl_wrap_socket_and_match_hostname\u001b[1;34m(sock, cert_reqs, ssl_version, ssl_minimum_version, ssl_maximum_version, cert_file, key_file, key_password, ca_certs, ca_cert_dir, ca_cert_data, assert_hostname, assert_fingerprint, server_hostname, ssl_context, tls_in_tls)\u001b[0m\n\u001b[0;32m 907\u001b[0m server_hostname \u001b[38;5;241m=\u001b[39m normalized\n\u001b[1;32m--> 909\u001b[0m ssl_sock \u001b[38;5;241m=\u001b[39m ssl_wrap_socket(\n\u001b[0;32m 910\u001b[0m sock\u001b[38;5;241m=\u001b[39msock,\n\u001b[0;32m 911\u001b[0m keyfile\u001b[38;5;241m=\u001b[39mkey_file,\n\u001b[0;32m 912\u001b[0m certfile\u001b[38;5;241m=\u001b[39mcert_file,\n\u001b[0;32m 913\u001b[0m key_password\u001b[38;5;241m=\u001b[39mkey_password,\n\u001b[0;32m 914\u001b[0m ca_certs\u001b[38;5;241m=\u001b[39mca_certs,\n\u001b[0;32m 915\u001b[0m ca_cert_dir\u001b[38;5;241m=\u001b[39mca_cert_dir,\n\u001b[0;32m 916\u001b[0m ca_cert_data\u001b[38;5;241m=\u001b[39mca_cert_data,\n\u001b[0;32m 917\u001b[0m server_hostname\u001b[38;5;241m=\u001b[39mserver_hostname,\n\u001b[0;32m 918\u001b[0m ssl_context\u001b[38;5;241m=\u001b[39mcontext,\n\u001b[0;32m 919\u001b[0m tls_in_tls\u001b[38;5;241m=\u001b[39mtls_in_tls,\n\u001b[0;32m 920\u001b[0m )\n\u001b[0;32m 922\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n",
58
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\urllib3\\util\\ssl_.py:469\u001b[0m, in \u001b[0;36mssl_wrap_socket\u001b[1;34m(sock, keyfile, certfile, cert_reqs, ca_certs, server_hostname, ssl_version, ciphers, ssl_context, ca_cert_dir, key_password, ca_cert_data, tls_in_tls)\u001b[0m\n\u001b[0;32m 467\u001b[0m context\u001b[38;5;241m.\u001b[39mset_alpn_protocols(ALPN_PROTOCOLS)\n\u001b[1;32m--> 469\u001b[0m ssl_sock \u001b[38;5;241m=\u001b[39m _ssl_wrap_socket_impl(sock, context, tls_in_tls, server_hostname)\n\u001b[0;32m 470\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m ssl_sock\n",
59
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\urllib3\\util\\ssl_.py:513\u001b[0m, in \u001b[0;36m_ssl_wrap_socket_impl\u001b[1;34m(sock, ssl_context, tls_in_tls, server_hostname)\u001b[0m\n\u001b[0;32m 511\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m SSLTransport(sock, ssl_context, server_hostname)\n\u001b[1;32m--> 513\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m ssl_context\u001b[38;5;241m.\u001b[39mwrap_socket(sock, server_hostname\u001b[38;5;241m=\u001b[39mserver_hostname)\n",
60
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\ssl.py:455\u001b[0m, in \u001b[0;36mSSLContext.wrap_socket\u001b[1;34m(self, sock, server_side, do_handshake_on_connect, suppress_ragged_eofs, server_hostname, session)\u001b[0m\n\u001b[0;32m 449\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mwrap_socket\u001b[39m(\u001b[38;5;28mself\u001b[39m, sock, server_side\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[0;32m 450\u001b[0m do_handshake_on_connect\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[0;32m 451\u001b[0m suppress_ragged_eofs\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[0;32m 452\u001b[0m server_hostname\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m, session\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m):\n\u001b[0;32m 453\u001b[0m \u001b[38;5;66;03m# SSLSocket class handles server_hostname encoding before it calls\u001b[39;00m\n\u001b[0;32m 454\u001b[0m \u001b[38;5;66;03m# ctx._wrap_socket()\u001b[39;00m\n\u001b[1;32m--> 455\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msslsocket_class\u001b[38;5;241m.\u001b[39m_create(\n\u001b[0;32m 456\u001b[0m sock\u001b[38;5;241m=\u001b[39msock,\n\u001b[0;32m 457\u001b[0m server_side\u001b[38;5;241m=\u001b[39mserver_side,\n\u001b[0;32m 458\u001b[0m do_handshake_on_connect\u001b[38;5;241m=\u001b[39mdo_handshake_on_connect,\n\u001b[0;32m 459\u001b[0m suppress_ragged_eofs\u001b[38;5;241m=\u001b[39msuppress_ragged_eofs,\n\u001b[0;32m 460\u001b[0m server_hostname\u001b[38;5;241m=\u001b[39mserver_hostname,\n\u001b[0;32m 461\u001b[0m context\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m 462\u001b[0m session\u001b[38;5;241m=\u001b[39msession\n\u001b[0;32m 463\u001b[0m )\n",
61
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\ssl.py:1041\u001b[0m, in \u001b[0;36mSSLSocket._create\u001b[1;34m(cls, sock, server_side, do_handshake_on_connect, suppress_ragged_eofs, server_hostname, context, session)\u001b[0m\n\u001b[0;32m 1040\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdo_handshake_on_connect should not be specified for non-blocking sockets\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m-> 1041\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdo_handshake()\n\u001b[0;32m 1042\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m:\n",
62
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\ssl.py:1319\u001b[0m, in \u001b[0;36mSSLSocket.do_handshake\u001b[1;34m(self, block)\u001b[0m\n\u001b[0;32m 1318\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msettimeout(\u001b[38;5;28;01mNone\u001b[39;00m)\n\u001b[1;32m-> 1319\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_sslobj\u001b[38;5;241m.\u001b[39mdo_handshake()\n\u001b[0;32m 1320\u001b[0m \u001b[38;5;28;01mfinally\u001b[39;00m:\n",
63
+ "\u001b[1;31mSSLCertVerificationError\u001b[0m: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1000)",
64
+ "\nDuring handling of the above exception, another exception occurred:\n",
65
+ "\u001b[1;31mSSLError\u001b[0m Traceback (most recent call last)",
66
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\urllib3\\connectionpool.py:789\u001b[0m, in \u001b[0;36mHTTPConnectionPool.urlopen\u001b[1;34m(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, preload_content, decode_content, **response_kw)\u001b[0m\n\u001b[0;32m 788\u001b[0m \u001b[38;5;66;03m# Make the request on the HTTPConnection object\u001b[39;00m\n\u001b[1;32m--> 789\u001b[0m response \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_make_request(\n\u001b[0;32m 790\u001b[0m conn,\n\u001b[0;32m 791\u001b[0m method,\n\u001b[0;32m 792\u001b[0m url,\n\u001b[0;32m 793\u001b[0m timeout\u001b[38;5;241m=\u001b[39mtimeout_obj,\n\u001b[0;32m 794\u001b[0m body\u001b[38;5;241m=\u001b[39mbody,\n\u001b[0;32m 795\u001b[0m headers\u001b[38;5;241m=\u001b[39mheaders,\n\u001b[0;32m 796\u001b[0m chunked\u001b[38;5;241m=\u001b[39mchunked,\n\u001b[0;32m 797\u001b[0m retries\u001b[38;5;241m=\u001b[39mretries,\n\u001b[0;32m 798\u001b[0m response_conn\u001b[38;5;241m=\u001b[39mresponse_conn,\n\u001b[0;32m 799\u001b[0m preload_content\u001b[38;5;241m=\u001b[39mpreload_content,\n\u001b[0;32m 800\u001b[0m decode_content\u001b[38;5;241m=\u001b[39mdecode_content,\n\u001b[0;32m 801\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mresponse_kw,\n\u001b[0;32m 802\u001b[0m )\n\u001b[0;32m 804\u001b[0m \u001b[38;5;66;03m# Everything went great!\u001b[39;00m\n",
67
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\urllib3\\connectionpool.py:490\u001b[0m, in \u001b[0;36mHTTPConnectionPool._make_request\u001b[1;34m(self, conn, method, url, body, headers, retries, timeout, chunked, response_conn, preload_content, decode_content, enforce_content_length)\u001b[0m\n\u001b[0;32m 489\u001b[0m new_e \u001b[38;5;241m=\u001b[39m _wrap_proxy_error(new_e, conn\u001b[38;5;241m.\u001b[39mproxy\u001b[38;5;241m.\u001b[39mscheme)\n\u001b[1;32m--> 490\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m new_e\n\u001b[0;32m 492\u001b[0m \u001b[38;5;66;03m# conn.request() calls http.client.*.request, not the method in\u001b[39;00m\n\u001b[0;32m 493\u001b[0m \u001b[38;5;66;03m# urllib3.request. It also calls makefile (recv) on the socket.\u001b[39;00m\n",
68
+ "\u001b[1;31mSSLError\u001b[0m: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1000)",
69
+ "\nThe above exception was the direct cause of the following exception:\n",
70
+ "\u001b[1;31mMaxRetryError\u001b[0m Traceback (most recent call last)",
71
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\requests\\adapters.py:667\u001b[0m, in \u001b[0;36mHTTPAdapter.send\u001b[1;34m(self, request, stream, timeout, verify, cert, proxies)\u001b[0m\n\u001b[0;32m 666\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m--> 667\u001b[0m resp \u001b[38;5;241m=\u001b[39m conn\u001b[38;5;241m.\u001b[39murlopen(\n\u001b[0;32m 668\u001b[0m method\u001b[38;5;241m=\u001b[39mrequest\u001b[38;5;241m.\u001b[39mmethod,\n\u001b[0;32m 669\u001b[0m url\u001b[38;5;241m=\u001b[39murl,\n\u001b[0;32m 670\u001b[0m body\u001b[38;5;241m=\u001b[39mrequest\u001b[38;5;241m.\u001b[39mbody,\n\u001b[0;32m 671\u001b[0m headers\u001b[38;5;241m=\u001b[39mrequest\u001b[38;5;241m.\u001b[39mheaders,\n\u001b[0;32m 672\u001b[0m redirect\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[0;32m 673\u001b[0m assert_same_host\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[0;32m 674\u001b[0m preload_content\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[0;32m 675\u001b[0m decode_content\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[0;32m 676\u001b[0m retries\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mmax_retries,\n\u001b[0;32m 677\u001b[0m timeout\u001b[38;5;241m=\u001b[39mtimeout,\n\u001b[0;32m 678\u001b[0m chunked\u001b[38;5;241m=\u001b[39mchunked,\n\u001b[0;32m 679\u001b[0m )\n\u001b[0;32m 681\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (ProtocolError, \u001b[38;5;167;01mOSError\u001b[39;00m) \u001b[38;5;28;01mas\u001b[39;00m err:\n",
72
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\urllib3\\connectionpool.py:843\u001b[0m, in \u001b[0;36mHTTPConnectionPool.urlopen\u001b[1;34m(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, preload_content, decode_content, **response_kw)\u001b[0m\n\u001b[0;32m 841\u001b[0m new_e \u001b[38;5;241m=\u001b[39m ProtocolError(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mConnection aborted.\u001b[39m\u001b[38;5;124m\"\u001b[39m, new_e)\n\u001b[1;32m--> 843\u001b[0m retries \u001b[38;5;241m=\u001b[39m retries\u001b[38;5;241m.\u001b[39mincrement(\n\u001b[0;32m 844\u001b[0m method, url, error\u001b[38;5;241m=\u001b[39mnew_e, _pool\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m, _stacktrace\u001b[38;5;241m=\u001b[39msys\u001b[38;5;241m.\u001b[39mexc_info()[\u001b[38;5;241m2\u001b[39m]\n\u001b[0;32m 845\u001b[0m )\n\u001b[0;32m 846\u001b[0m retries\u001b[38;5;241m.\u001b[39msleep()\n",
73
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\urllib3\\util\\retry.py:519\u001b[0m, in \u001b[0;36mRetry.increment\u001b[1;34m(self, method, url, response, error, _pool, _stacktrace)\u001b[0m\n\u001b[0;32m 518\u001b[0m reason \u001b[38;5;241m=\u001b[39m error \u001b[38;5;129;01mor\u001b[39;00m ResponseError(cause)\n\u001b[1;32m--> 519\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m MaxRetryError(_pool, url, reason) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mreason\u001b[39;00m \u001b[38;5;66;03m# type: ignore[arg-type]\u001b[39;00m\n\u001b[0;32m 521\u001b[0m log\u001b[38;5;241m.\u001b[39mdebug(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mIncremented Retry for (url=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m%s\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m): \u001b[39m\u001b[38;5;132;01m%r\u001b[39;00m\u001b[38;5;124m\"\u001b[39m, url, new_retry)\n",
74
+ "\u001b[1;31mMaxRetryError\u001b[0m: HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /NIHRDataInsights/HRCSHealthCategories/resolve/main/tokenizer_config.json (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1000)')))",
75
+ "\nDuring handling of the above exception, another exception occurred:\n",
76
+ "\u001b[1;31mSSLError\u001b[0m Traceback (most recent call last)",
77
+ "Cell \u001b[1;32mIn[1], line 200\u001b[0m\n\u001b[0;32m 197\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mInitialising HRCS Classifier Pipeline...\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m 199\u001b[0m \u001b[38;5;66;03m# Load models once outside the loop to save memory/time\u001b[39;00m\n\u001b[1;32m--> 200\u001b[0m hc_assets \u001b[38;5;241m=\u001b[39m load_hf_model(HC_REPO_ID)\n\u001b[0;32m 201\u001b[0m rac_assets \u001b[38;5;241m=\u001b[39m load_hf_model(RAC_REPO_ID)\n\u001b[0;32m 203\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m folder \u001b[38;5;129;01min\u001b[39;00m DATA_FOLDERS:\n",
78
+ "Cell \u001b[1;32mIn[1], line 75\u001b[0m, in \u001b[0;36mload_hf_model\u001b[1;34m(repo_id)\u001b[0m\n\u001b[0;32m 70\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m 71\u001b[0m \u001b[38;5;124;03mThis section downloads the models from hugging face and the optimal thresholds.\u001b[39;00m\n\u001b[0;32m 72\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m 73\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mLoading model and tokenizer from: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mrepo_id\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m...\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m---> 75\u001b[0m tok \u001b[38;5;241m=\u001b[39m AutoTokenizer\u001b[38;5;241m.\u001b[39mfrom_pretrained(repo_id, use_fast\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m)\n\u001b[0;32m 76\u001b[0m model \u001b[38;5;241m=\u001b[39m AutoModelForSequenceClassification\u001b[38;5;241m.\u001b[39mfrom_pretrained(repo_id)\n\u001b[0;32m 78\u001b[0m model\u001b[38;5;241m.\u001b[39meval()\n",
79
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\transformers\\models\\auto\\tokenization_auto.py:983\u001b[0m, in \u001b[0;36mAutoTokenizer.from_pretrained\u001b[1;34m(cls, pretrained_model_name_or_path, *inputs, **kwargs)\u001b[0m\n\u001b[0;32m 980\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m tokenizer_class\u001b[38;5;241m.\u001b[39mfrom_pretrained(pretrained_model_name_or_path, \u001b[38;5;241m*\u001b[39minputs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m 982\u001b[0m \u001b[38;5;66;03m# Next, let's try to use the tokenizer_config file to get the tokenizer class.\u001b[39;00m\n\u001b[1;32m--> 983\u001b[0m tokenizer_config \u001b[38;5;241m=\u001b[39m get_tokenizer_config(pretrained_model_name_or_path, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m 984\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_commit_hash\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m tokenizer_config:\n\u001b[0;32m 985\u001b[0m kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_commit_hash\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m tokenizer_config[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_commit_hash\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n",
80
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\transformers\\models\\auto\\tokenization_auto.py:815\u001b[0m, in \u001b[0;36mget_tokenizer_config\u001b[1;34m(pretrained_model_name_or_path, cache_dir, force_download, resume_download, proxies, token, revision, local_files_only, subfolder, **kwargs)\u001b[0m\n\u001b[0;32m 812\u001b[0m token \u001b[38;5;241m=\u001b[39m use_auth_token\n\u001b[0;32m 814\u001b[0m commit_hash \u001b[38;5;241m=\u001b[39m kwargs\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_commit_hash\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m)\n\u001b[1;32m--> 815\u001b[0m resolved_config_file \u001b[38;5;241m=\u001b[39m cached_file(\n\u001b[0;32m 816\u001b[0m pretrained_model_name_or_path,\n\u001b[0;32m 817\u001b[0m TOKENIZER_CONFIG_FILE,\n\u001b[0;32m 818\u001b[0m cache_dir\u001b[38;5;241m=\u001b[39mcache_dir,\n\u001b[0;32m 819\u001b[0m force_download\u001b[38;5;241m=\u001b[39mforce_download,\n\u001b[0;32m 820\u001b[0m resume_download\u001b[38;5;241m=\u001b[39mresume_download,\n\u001b[0;32m 821\u001b[0m proxies\u001b[38;5;241m=\u001b[39mproxies,\n\u001b[0;32m 822\u001b[0m token\u001b[38;5;241m=\u001b[39mtoken,\n\u001b[0;32m 823\u001b[0m revision\u001b[38;5;241m=\u001b[39mrevision,\n\u001b[0;32m 824\u001b[0m local_files_only\u001b[38;5;241m=\u001b[39mlocal_files_only,\n\u001b[0;32m 825\u001b[0m subfolder\u001b[38;5;241m=\u001b[39msubfolder,\n\u001b[0;32m 826\u001b[0m _raise_exceptions_for_gated_repo\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[0;32m 827\u001b[0m _raise_exceptions_for_missing_entries\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[0;32m 828\u001b[0m _raise_exceptions_for_connection_errors\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[0;32m 829\u001b[0m _commit_hash\u001b[38;5;241m=\u001b[39mcommit_hash,\n\u001b[0;32m 830\u001b[0m )\n\u001b[0;32m 831\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m resolved_config_file \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m 832\u001b[0m logger\u001b[38;5;241m.\u001b[39minfo(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCould not locate the tokenizer configuration file, will try to use the model config instead.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
81
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\transformers\\utils\\hub.py:312\u001b[0m, in \u001b[0;36mcached_file\u001b[1;34m(path_or_repo_id, filename, **kwargs)\u001b[0m\n\u001b[0;32m 254\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mcached_file\u001b[39m(\n\u001b[0;32m 255\u001b[0m path_or_repo_id: Union[\u001b[38;5;28mstr\u001b[39m, os\u001b[38;5;241m.\u001b[39mPathLike],\n\u001b[0;32m 256\u001b[0m filename: \u001b[38;5;28mstr\u001b[39m,\n\u001b[0;32m 257\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs,\n\u001b[0;32m 258\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Optional[\u001b[38;5;28mstr\u001b[39m]:\n\u001b[0;32m 259\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m 260\u001b[0m \u001b[38;5;124;03m Tries to locate a file in a local folder and repo, downloads and cache it if necessary.\u001b[39;00m\n\u001b[0;32m 261\u001b[0m \n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 310\u001b[0m \u001b[38;5;124;03m ```\u001b[39;00m\n\u001b[0;32m 311\u001b[0m \u001b[38;5;124;03m \"\"\"\u001b[39;00m\n\u001b[1;32m--> 312\u001b[0m file \u001b[38;5;241m=\u001b[39m cached_files(path_or_repo_id\u001b[38;5;241m=\u001b[39mpath_or_repo_id, filenames\u001b[38;5;241m=\u001b[39m[filename], \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m 313\u001b[0m file \u001b[38;5;241m=\u001b[39m file[\u001b[38;5;241m0\u001b[39m] \u001b[38;5;28;01mif\u001b[39;00m file \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m file\n\u001b[0;32m 314\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m file\n",
82
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\transformers\\utils\\hub.py:557\u001b[0m, in \u001b[0;36mcached_files\u001b[1;34m(path_or_repo_id, filenames, cache_dir, force_download, resume_download, proxies, token, revision, local_files_only, subfolder, repo_type, user_agent, _raise_exceptions_for_gated_repo, _raise_exceptions_for_missing_entries, _raise_exceptions_for_connection_errors, _commit_hash, **deprecated_kwargs)\u001b[0m\n\u001b[0;32m 554\u001b[0m \u001b[38;5;66;03m# Any other Exception type should now be re-raised, in order to provide helpful error messages and break the execution flow\u001b[39;00m\n\u001b[0;32m 555\u001b[0m \u001b[38;5;66;03m# (EntryNotFoundError will be treated outside this block and correctly re-raised if needed)\u001b[39;00m\n\u001b[0;32m 556\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(e, EntryNotFoundError):\n\u001b[1;32m--> 557\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m e\n\u001b[0;32m 559\u001b[0m resolved_files \u001b[38;5;241m=\u001b[39m [\n\u001b[0;32m 560\u001b[0m _get_cache_file_to_return(path_or_repo_id, filename, cache_dir, revision) \u001b[38;5;28;01mfor\u001b[39;00m filename \u001b[38;5;129;01min\u001b[39;00m full_filenames\n\u001b[0;32m 561\u001b[0m ]\n\u001b[0;32m 562\u001b[0m \u001b[38;5;66;03m# If there are any missing file and the flag is active, raise\u001b[39;00m\n",
83
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\transformers\\utils\\hub.py:470\u001b[0m, in \u001b[0;36mcached_files\u001b[1;34m(path_or_repo_id, filenames, cache_dir, force_download, resume_download, proxies, token, revision, local_files_only, subfolder, repo_type, user_agent, _raise_exceptions_for_gated_repo, _raise_exceptions_for_missing_entries, _raise_exceptions_for_connection_errors, _commit_hash, **deprecated_kwargs)\u001b[0m\n\u001b[0;32m 467\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m 468\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(full_filenames) \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[0;32m 469\u001b[0m \u001b[38;5;66;03m# This is slightly better for only 1 file\u001b[39;00m\n\u001b[1;32m--> 470\u001b[0m hf_hub_download(\n\u001b[0;32m 471\u001b[0m path_or_repo_id,\n\u001b[0;32m 472\u001b[0m filenames[\u001b[38;5;241m0\u001b[39m],\n\u001b[0;32m 473\u001b[0m subfolder\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(subfolder) \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m0\u001b[39m \u001b[38;5;28;01melse\u001b[39;00m subfolder,\n\u001b[0;32m 474\u001b[0m repo_type\u001b[38;5;241m=\u001b[39mrepo_type,\n\u001b[0;32m 475\u001b[0m revision\u001b[38;5;241m=\u001b[39mrevision,\n\u001b[0;32m 476\u001b[0m cache_dir\u001b[38;5;241m=\u001b[39mcache_dir,\n\u001b[0;32m 477\u001b[0m user_agent\u001b[38;5;241m=\u001b[39muser_agent,\n\u001b[0;32m 478\u001b[0m force_download\u001b[38;5;241m=\u001b[39mforce_download,\n\u001b[0;32m 479\u001b[0m proxies\u001b[38;5;241m=\u001b[39mproxies,\n\u001b[0;32m 480\u001b[0m resume_download\u001b[38;5;241m=\u001b[39mresume_download,\n\u001b[0;32m 481\u001b[0m token\u001b[38;5;241m=\u001b[39mtoken,\n\u001b[0;32m 482\u001b[0m local_files_only\u001b[38;5;241m=\u001b[39mlocal_files_only,\n\u001b[0;32m 483\u001b[0m )\n\u001b[0;32m 484\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[0;32m 485\u001b[0m snapshot_download(\n\u001b[0;32m 486\u001b[0m path_or_repo_id,\n\u001b[0;32m 487\u001b[0m allow_patterns\u001b[38;5;241m=\u001b[39mfull_filenames,\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 496\u001b[0m local_files_only\u001b[38;5;241m=\u001b[39mlocal_files_only,\n\u001b[0;32m 497\u001b[0m )\n",
84
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\huggingface_hub\\utils\\_validators.py:114\u001b[0m, in \u001b[0;36mvalidate_hf_hub_args.<locals>._inner_fn\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m 111\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m check_use_auth_token:\n\u001b[0;32m 112\u001b[0m kwargs \u001b[38;5;241m=\u001b[39m smoothly_deprecate_use_auth_token(fn_name\u001b[38;5;241m=\u001b[39mfn\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m, has_token\u001b[38;5;241m=\u001b[39mhas_token, kwargs\u001b[38;5;241m=\u001b[39mkwargs)\n\u001b[1;32m--> 114\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m fn(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
85
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\huggingface_hub\\file_download.py:1008\u001b[0m, in \u001b[0;36mhf_hub_download\u001b[1;34m(repo_id, filename, subfolder, repo_type, revision, library_name, library_version, cache_dir, local_dir, user_agent, force_download, proxies, etag_timeout, token, local_files_only, headers, endpoint, resume_download, force_filename, local_dir_use_symlinks)\u001b[0m\n\u001b[0;32m 988\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m _hf_hub_download_to_local_dir(\n\u001b[0;32m 989\u001b[0m \u001b[38;5;66;03m# Destination\u001b[39;00m\n\u001b[0;32m 990\u001b[0m local_dir\u001b[38;5;241m=\u001b[39mlocal_dir,\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 1005\u001b[0m local_files_only\u001b[38;5;241m=\u001b[39mlocal_files_only,\n\u001b[0;32m 1006\u001b[0m )\n\u001b[0;32m 1007\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1008\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m _hf_hub_download_to_cache_dir(\n\u001b[0;32m 1009\u001b[0m \u001b[38;5;66;03m# Destination\u001b[39;00m\n\u001b[0;32m 1010\u001b[0m cache_dir\u001b[38;5;241m=\u001b[39mcache_dir,\n\u001b[0;32m 1011\u001b[0m \u001b[38;5;66;03m# File info\u001b[39;00m\n\u001b[0;32m 1012\u001b[0m repo_id\u001b[38;5;241m=\u001b[39mrepo_id,\n\u001b[0;32m 1013\u001b[0m filename\u001b[38;5;241m=\u001b[39mfilename,\n\u001b[0;32m 1014\u001b[0m repo_type\u001b[38;5;241m=\u001b[39mrepo_type,\n\u001b[0;32m 1015\u001b[0m revision\u001b[38;5;241m=\u001b[39mrevision,\n\u001b[0;32m 1016\u001b[0m \u001b[38;5;66;03m# HTTP info\u001b[39;00m\n\u001b[0;32m 1017\u001b[0m endpoint\u001b[38;5;241m=\u001b[39mendpoint,\n\u001b[0;32m 1018\u001b[0m etag_timeout\u001b[38;5;241m=\u001b[39metag_timeout,\n\u001b[0;32m 1019\u001b[0m headers\u001b[38;5;241m=\u001b[39mhf_headers,\n\u001b[0;32m 1020\u001b[0m proxies\u001b[38;5;241m=\u001b[39mproxies,\n\u001b[0;32m 1021\u001b[0m token\u001b[38;5;241m=\u001b[39mtoken,\n\u001b[0;32m 1022\u001b[0m \u001b[38;5;66;03m# Additional options\u001b[39;00m\n\u001b[0;32m 1023\u001b[0m local_files_only\u001b[38;5;241m=\u001b[39mlocal_files_only,\n\u001b[0;32m 1024\u001b[0m force_download\u001b[38;5;241m=\u001b[39mforce_download,\n\u001b[0;32m 1025\u001b[0m )\n",
86
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\huggingface_hub\\file_download.py:1071\u001b[0m, in \u001b[0;36m_hf_hub_download_to_cache_dir\u001b[1;34m(cache_dir, repo_id, filename, repo_type, revision, endpoint, etag_timeout, headers, proxies, token, local_files_only, force_download)\u001b[0m\n\u001b[0;32m 1067\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m pointer_path\n\u001b[0;32m 1069\u001b[0m \u001b[38;5;66;03m# Try to get metadata (etag, commit_hash, url, size) from the server.\u001b[39;00m\n\u001b[0;32m 1070\u001b[0m \u001b[38;5;66;03m# If we can't, a HEAD request error is returned.\u001b[39;00m\n\u001b[1;32m-> 1071\u001b[0m (url_to_download, etag, commit_hash, expected_size, xet_file_data, head_call_error) \u001b[38;5;241m=\u001b[39m _get_metadata_or_catch_error(\n\u001b[0;32m 1072\u001b[0m repo_id\u001b[38;5;241m=\u001b[39mrepo_id,\n\u001b[0;32m 1073\u001b[0m filename\u001b[38;5;241m=\u001b[39mfilename,\n\u001b[0;32m 1074\u001b[0m repo_type\u001b[38;5;241m=\u001b[39mrepo_type,\n\u001b[0;32m 1075\u001b[0m revision\u001b[38;5;241m=\u001b[39mrevision,\n\u001b[0;32m 1076\u001b[0m endpoint\u001b[38;5;241m=\u001b[39mendpoint,\n\u001b[0;32m 1077\u001b[0m proxies\u001b[38;5;241m=\u001b[39mproxies,\n\u001b[0;32m 1078\u001b[0m etag_timeout\u001b[38;5;241m=\u001b[39metag_timeout,\n\u001b[0;32m 1079\u001b[0m headers\u001b[38;5;241m=\u001b[39mheaders,\n\u001b[0;32m 1080\u001b[0m token\u001b[38;5;241m=\u001b[39mtoken,\n\u001b[0;32m 1081\u001b[0m local_files_only\u001b[38;5;241m=\u001b[39mlocal_files_only,\n\u001b[0;32m 1082\u001b[0m storage_folder\u001b[38;5;241m=\u001b[39mstorage_folder,\n\u001b[0;32m 1083\u001b[0m relative_filename\u001b[38;5;241m=\u001b[39mrelative_filename,\n\u001b[0;32m 1084\u001b[0m )\n\u001b[0;32m 1086\u001b[0m \u001b[38;5;66;03m# etag can be None for several reasons:\u001b[39;00m\n\u001b[0;32m 1087\u001b[0m \u001b[38;5;66;03m# 1. we passed local_files_only.\u001b[39;00m\n\u001b[0;32m 1088\u001b[0m \u001b[38;5;66;03m# 2. we don't have a connection\u001b[39;00m\n\u001b[1;32m (...)\u001b[0m\n\u001b[0;32m 1094\u001b[0m \u001b[38;5;66;03m# If the specified revision is a commit hash, look inside \"snapshots\".\u001b[39;00m\n\u001b[0;32m 1095\u001b[0m \u001b[38;5;66;03m# If the specified revision is a branch or tag, look inside \"refs\".\u001b[39;00m\n\u001b[0;32m 1096\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m head_call_error \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m 1097\u001b[0m \u001b[38;5;66;03m# Couldn't make a HEAD call => let's try to find a local file\u001b[39;00m\n",
87
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\huggingface_hub\\file_download.py:1533\u001b[0m, in \u001b[0;36m_get_metadata_or_catch_error\u001b[1;34m(repo_id, filename, repo_type, revision, endpoint, proxies, etag_timeout, headers, token, local_files_only, relative_filename, storage_folder)\u001b[0m\n\u001b[0;32m 1531\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m 1532\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m-> 1533\u001b[0m metadata \u001b[38;5;241m=\u001b[39m get_hf_file_metadata(\n\u001b[0;32m 1534\u001b[0m url\u001b[38;5;241m=\u001b[39murl, proxies\u001b[38;5;241m=\u001b[39mproxies, timeout\u001b[38;5;241m=\u001b[39metag_timeout, headers\u001b[38;5;241m=\u001b[39mheaders, token\u001b[38;5;241m=\u001b[39mtoken\n\u001b[0;32m 1535\u001b[0m )\n\u001b[0;32m 1536\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m EntryNotFoundError \u001b[38;5;28;01mas\u001b[39;00m http_error:\n\u001b[0;32m 1537\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m storage_folder \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m relative_filename \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m 1538\u001b[0m \u001b[38;5;66;03m# Cache the non-existence of the file\u001b[39;00m\n",
88
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\huggingface_hub\\utils\\_validators.py:114\u001b[0m, in \u001b[0;36mvalidate_hf_hub_args.<locals>._inner_fn\u001b[1;34m(*args, **kwargs)\u001b[0m\n\u001b[0;32m 111\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m check_use_auth_token:\n\u001b[0;32m 112\u001b[0m kwargs \u001b[38;5;241m=\u001b[39m smoothly_deprecate_use_auth_token(fn_name\u001b[38;5;241m=\u001b[39mfn\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m, has_token\u001b[38;5;241m=\u001b[39mhas_token, kwargs\u001b[38;5;241m=\u001b[39mkwargs)\n\u001b[1;32m--> 114\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m fn(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n",
89
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\huggingface_hub\\file_download.py:1450\u001b[0m, in \u001b[0;36mget_hf_file_metadata\u001b[1;34m(url, token, proxies, timeout, library_name, library_version, user_agent, headers)\u001b[0m\n\u001b[0;32m 1447\u001b[0m hf_headers[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mAccept-Encoding\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124midentity\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;66;03m# prevent any compression => we want to know the real size of the file\u001b[39;00m\n\u001b[0;32m 1449\u001b[0m \u001b[38;5;66;03m# Retrieve metadata\u001b[39;00m\n\u001b[1;32m-> 1450\u001b[0m r \u001b[38;5;241m=\u001b[39m _request_wrapper(\n\u001b[0;32m 1451\u001b[0m method\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mHEAD\u001b[39m\u001b[38;5;124m\"\u001b[39m,\n\u001b[0;32m 1452\u001b[0m url\u001b[38;5;241m=\u001b[39murl,\n\u001b[0;32m 1453\u001b[0m headers\u001b[38;5;241m=\u001b[39mhf_headers,\n\u001b[0;32m 1454\u001b[0m allow_redirects\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[0;32m 1455\u001b[0m follow_relative_redirects\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m,\n\u001b[0;32m 1456\u001b[0m proxies\u001b[38;5;241m=\u001b[39mproxies,\n\u001b[0;32m 1457\u001b[0m timeout\u001b[38;5;241m=\u001b[39mtimeout,\n\u001b[0;32m 1458\u001b[0m )\n\u001b[0;32m 1459\u001b[0m hf_raise_for_status(r)\n\u001b[0;32m 1461\u001b[0m \u001b[38;5;66;03m# Return\u001b[39;00m\n",
90
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\huggingface_hub\\file_download.py:286\u001b[0m, in \u001b[0;36m_request_wrapper\u001b[1;34m(method, url, follow_relative_redirects, **params)\u001b[0m\n\u001b[0;32m 284\u001b[0m \u001b[38;5;66;03m# Recursively follow relative redirects\u001b[39;00m\n\u001b[0;32m 285\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m follow_relative_redirects:\n\u001b[1;32m--> 286\u001b[0m response \u001b[38;5;241m=\u001b[39m _request_wrapper(\n\u001b[0;32m 287\u001b[0m method\u001b[38;5;241m=\u001b[39mmethod,\n\u001b[0;32m 288\u001b[0m url\u001b[38;5;241m=\u001b[39murl,\n\u001b[0;32m 289\u001b[0m follow_relative_redirects\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[0;32m 290\u001b[0m \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mparams,\n\u001b[0;32m 291\u001b[0m )\n\u001b[0;32m 293\u001b[0m \u001b[38;5;66;03m# If redirection, we redirect only relative paths.\u001b[39;00m\n\u001b[0;32m 294\u001b[0m \u001b[38;5;66;03m# This is useful in case of a renamed repository.\u001b[39;00m\n\u001b[0;32m 295\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;241m300\u001b[39m \u001b[38;5;241m<\u001b[39m\u001b[38;5;241m=\u001b[39m response\u001b[38;5;241m.\u001b[39mstatus_code \u001b[38;5;241m<\u001b[39m\u001b[38;5;241m=\u001b[39m \u001b[38;5;241m399\u001b[39m:\n",
91
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\huggingface_hub\\file_download.py:309\u001b[0m, in \u001b[0;36m_request_wrapper\u001b[1;34m(method, url, follow_relative_redirects, **params)\u001b[0m\n\u001b[0;32m 306\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m response\n\u001b[0;32m 308\u001b[0m \u001b[38;5;66;03m# Perform request and return if status_code is not in the retry list.\u001b[39;00m\n\u001b[1;32m--> 309\u001b[0m response \u001b[38;5;241m=\u001b[39m http_backoff(method\u001b[38;5;241m=\u001b[39mmethod, url\u001b[38;5;241m=\u001b[39murl, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mparams, retry_on_exceptions\u001b[38;5;241m=\u001b[39m(), retry_on_status_codes\u001b[38;5;241m=\u001b[39m(\u001b[38;5;241m429\u001b[39m,))\n\u001b[0;32m 310\u001b[0m hf_raise_for_status(response)\n\u001b[0;32m 311\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m response\n",
92
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\huggingface_hub\\utils\\_http.py:310\u001b[0m, in \u001b[0;36mhttp_backoff\u001b[1;34m(method, url, max_retries, base_wait_time, max_wait_time, retry_on_exceptions, retry_on_status_codes, **kwargs)\u001b[0m\n\u001b[0;32m 307\u001b[0m kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdata\u001b[39m\u001b[38;5;124m\"\u001b[39m]\u001b[38;5;241m.\u001b[39mseek(io_obj_initial_pos)\n\u001b[0;32m 309\u001b[0m \u001b[38;5;66;03m# Perform request and return if status_code is not in the retry list.\u001b[39;00m\n\u001b[1;32m--> 310\u001b[0m response \u001b[38;5;241m=\u001b[39m session\u001b[38;5;241m.\u001b[39mrequest(method\u001b[38;5;241m=\u001b[39mmethod, url\u001b[38;5;241m=\u001b[39murl, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m 311\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m response\u001b[38;5;241m.\u001b[39mstatus_code \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m retry_on_status_codes:\n\u001b[0;32m 312\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m response\n",
93
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\requests\\sessions.py:589\u001b[0m, in \u001b[0;36mSession.request\u001b[1;34m(self, method, url, params, data, headers, cookies, files, auth, timeout, allow_redirects, proxies, hooks, stream, verify, cert, json)\u001b[0m\n\u001b[0;32m 584\u001b[0m send_kwargs \u001b[38;5;241m=\u001b[39m {\n\u001b[0;32m 585\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtimeout\u001b[39m\u001b[38;5;124m\"\u001b[39m: timeout,\n\u001b[0;32m 586\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mallow_redirects\u001b[39m\u001b[38;5;124m\"\u001b[39m: allow_redirects,\n\u001b[0;32m 587\u001b[0m }\n\u001b[0;32m 588\u001b[0m send_kwargs\u001b[38;5;241m.\u001b[39mupdate(settings)\n\u001b[1;32m--> 589\u001b[0m resp \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39msend(prep, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39msend_kwargs)\n\u001b[0;32m 591\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m resp\n",
94
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\requests\\sessions.py:703\u001b[0m, in \u001b[0;36mSession.send\u001b[1;34m(self, request, **kwargs)\u001b[0m\n\u001b[0;32m 700\u001b[0m start \u001b[38;5;241m=\u001b[39m preferred_clock()\n\u001b[0;32m 702\u001b[0m \u001b[38;5;66;03m# Send the request\u001b[39;00m\n\u001b[1;32m--> 703\u001b[0m r \u001b[38;5;241m=\u001b[39m adapter\u001b[38;5;241m.\u001b[39msend(request, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m 705\u001b[0m \u001b[38;5;66;03m# Total elapsed time of the request (approximately)\u001b[39;00m\n\u001b[0;32m 706\u001b[0m elapsed \u001b[38;5;241m=\u001b[39m preferred_clock() \u001b[38;5;241m-\u001b[39m start\n",
95
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\huggingface_hub\\utils\\_http.py:96\u001b[0m, in \u001b[0;36mUniqueRequestIdAdapter.send\u001b[1;34m(self, request, *args, **kwargs)\u001b[0m\n\u001b[0;32m 94\u001b[0m logger\u001b[38;5;241m.\u001b[39mdebug(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mSend: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m_curlify(request)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m 95\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m---> 96\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39msend(request, \u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m 97\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m requests\u001b[38;5;241m.\u001b[39mRequestException \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m 98\u001b[0m request_id \u001b[38;5;241m=\u001b[39m request\u001b[38;5;241m.\u001b[39mheaders\u001b[38;5;241m.\u001b[39mget(X_AMZN_TRACE_ID)\n",
96
+ "File \u001b[1;32mc:\\Users\\Ashley.Banks\\AppData\\Local\\anaconda3\\Lib\\site-packages\\requests\\adapters.py:698\u001b[0m, in \u001b[0;36mHTTPAdapter.send\u001b[1;34m(self, request, stream, timeout, verify, cert, proxies)\u001b[0m\n\u001b[0;32m 694\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m ProxyError(e, request\u001b[38;5;241m=\u001b[39mrequest)\n\u001b[0;32m 696\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(e\u001b[38;5;241m.\u001b[39mreason, _SSLError):\n\u001b[0;32m 697\u001b[0m \u001b[38;5;66;03m# This branch is for urllib3 v1.22 and later.\u001b[39;00m\n\u001b[1;32m--> 698\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m SSLError(e, request\u001b[38;5;241m=\u001b[39mrequest)\n\u001b[0;32m 700\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mConnectionError\u001b[39;00m(e, request\u001b[38;5;241m=\u001b[39mrequest)\n\u001b[0;32m 702\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m ClosedPoolError \u001b[38;5;28;01mas\u001b[39;00m e:\n",
97
+ "\u001b[1;31mSSLError\u001b[0m: (MaxRetryError(\"HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /NIHRDataInsights/HRCSHealthCategories/resolve/main/tokenizer_config.json (Caused by SSLError(SSLCertVerificationError(1, '[SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1000)')))\"), '(Request ID: c39f4927-7e74-4ee1-b0ff-59c87354a7cb)')"
98
+ ]
99
+ }
100
+ ],
101
+ "source": [
102
+ "\"\"\"\n",
103
+ "HRCS Health Category & Research Activity Code - Inference Script\n",
104
+ "Developed by National Institute for Health and Care Research (NIHR)\n",
105
+ "\n",
106
+ "This script downloads the trained models from Hugging Face and runs\n",
107
+ "predictions locally on a provided CSV of research awards.\n",
108
+ "\n",
109
+ "Dependencies required:\n",
110
+ "pip install torch pandas numpy tqdm transformers huggingface_hub\n",
111
+ "\"\"\"\n",
112
+ "\n",
113
+ "import os, json\n",
114
+ "from typing import List\n",
115
+ "import numpy as np\n",
116
+ "import pandas as pd\n",
117
+ "from tqdm import tqdm\n",
118
+ "\n",
119
+ "import torch\n",
120
+ "from torch.utils.data import Dataset as TorchDataset, DataLoader\n",
121
+ "from torch.nn.functional import sigmoid\n",
122
+ "\n",
123
+ "from transformers import AutoTokenizer, AutoModelForSequenceClassification\n",
124
+ "from huggingface_hub import hf_hub_download\n",
125
+ "\n",
126
+ "# --- USER SETTINGS ---\n",
127
+ "# Set the path to the folder containing your CSV and the desired filenames\n",
128
+ "DATA_FOLDERS = [\"./\"] # can input more than one folder if needed\n",
129
+ "TEST_FILENAME = r\"test_data.csv\"\n",
130
+ "OUTPUT_FILENAME = \"hc_rac_predictions.csv\"\n",
131
+ "\n",
132
+ "# --- HUGGING FACE REPO SETTINGS ---\n",
133
+ "HC_REPO_ID = \"NIHRDataInsights/HRCSHealthCategories\"\n",
134
+ "RAC_REPO_ID = \"NIHRDataInsights/HRCSResearchActivityCodes\"\n",
135
+ "\n",
136
+ "BATCH_SIZE = 16 # Adjust based on your hardware (use 64+ for GPUs, 2-16 for CPUs)\n",
137
+ "MAX_LEN = 512\n",
138
+ "USE_GPU = torch.cuda.is_available()\n",
139
+ "\n",
140
+ "# -------------------- DATASET --------------------\n",
141
+ "class TextDataset(TorchDataset):\n",
142
+ " \"\"\"\n",
143
+ " This section takes your spreadsheet and packages it so the AI can read it.\n",
144
+ " It combines the 'AwardTitle' and 'AwardAbstract' together into 'text' (to be categorised).\n",
145
+ " \"\"\"\n",
146
+ " def __init__(self, df: pd.DataFrame, tokenizer, max_len: int = 512):\n",
147
+ " df = df.copy()\n",
148
+ " df[\"text\"] = (\n",
149
+ " df[\"AwardTitle\"].fillna(\"\").astype(str) + \"\\n\" +\n",
150
+ " df[\"AwardAbstract\"].fillna(\"\").astype(str)\n",
151
+ " )\n",
152
+ " self.texts = df[\"text\"].tolist()\n",
153
+ " self.tokenizer = tokenizer\n",
154
+ " self.max_len = max_len\n",
155
+ "\n",
156
+ " def __len__(self):\n",
157
+ " return len(self.texts)\n",
158
+ "\n",
159
+ " def __getitem__(self, idx):\n",
160
+ " enc = self.tokenizer(\n",
161
+ " self.texts[idx],\n",
162
+ " truncation=True, # cuts if too long\n",
163
+ " padding=\"max_length\", # adds spaces if under limit\n",
164
+ " max_length=self.max_len,\n",
165
+ " return_tensors=\"pt\"\n",
166
+ " )\n",
167
+ " return {k: v.squeeze(0) for k, v in enc.items()}\n",
168
+ "\n",
169
+ "# -------------------- MODEL LOADING --------------------\n",
170
+ "def load_hf_model(repo_id: str):\n",
171
+ " \"\"\"\n",
172
+ " This section downloads the models from hugging face and the optimal thresholds.\n",
173
+ " \"\"\"\n",
174
+ " print(f\"Loading model and tokenizer from: {repo_id}...\")\n",
175
+ "\n",
176
+ " tok = AutoTokenizer.from_pretrained(repo_id, use_fast=True)\n",
177
+ " model = AutoModelForSequenceClassification.from_pretrained(repo_id)\n",
178
+ "\n",
179
+ " model.eval()\n",
180
+ " device = torch.device(\"cuda\" if USE_GPU else \"cpu\")\n",
181
+ " model.to(device)\n",
182
+ "\n",
183
+ " # Download custom metadata.json from the repo for specific threshold values\n",
184
+ " try:\n",
185
+ " meta_path = hf_hub_download(repo_id=repo_id, filename=\"metadata.json\")\n",
186
+ " with open(meta_path, \"r\") as f:\n",
187
+ " meta = json.load(f)\n",
188
+ " labels = meta.get(\"labels\")\n",
189
+ " thresholds = np.array(meta.get(\"optimal_thresholds\", []), dtype=float)\n",
190
+ " except Exception as e:\n",
191
+ " print(f\"Warning: Could not load metadata.json from {repo_id}. {e}\")\n",
192
+ " labels, thresholds = None, None\n",
193
+ "\n",
194
+ " if labels is None:\n",
195
+ " num_labels = int(model.config.num_labels)\n",
196
+ " labels = [model.config.id2label.get(i, f\"L{i}\") for i in range(num_labels)]\n",
197
+ "\n",
198
+ " if thresholds is None or len(thresholds) != len(labels):\n",
199
+ " print(f\"Using default 0.5 threshold for {repo_id}\")\n",
200
+ " thresholds = np.full(len(labels), 0.5, dtype=float)\n",
201
+ "\n",
202
+ " return tok, model, labels, thresholds\n",
203
+ "\n",
204
+ "# -------------------- INFERENCE & BUILD --------------------\n",
205
+ "def predict(model, dataloader: DataLoader, thresholds: np.ndarray):\n",
206
+ " device = next(model.parameters()).device\n",
207
+ " all_logits = []\n",
208
+ "\n",
209
+ " with torch.no_grad():\n",
210
+ " for batch in tqdm(dataloader, desc=\"Inferencing\"):\n",
211
+ " inputs = {k: v.to(device) for k, v in batch.items()}\n",
212
+ " logits = model(**inputs).logits\n",
213
+ " all_logits.append(logits.cpu())\n",
214
+ "\n",
215
+ " logits = torch.cat(all_logits, dim=0).numpy()\n",
216
+ " probs = sigmoid(torch.tensor(logits)).numpy()\n",
217
+ " preds = (probs > thresholds.reshape(1, -1)).astype(int)\n",
218
+ " return logits, probs, preds\n",
219
+ "\n",
220
+ "def build_outputs(df, logits, probs, preds, label_list, thresholds, prefix: str):\n",
221
+ " \"\"\"\n",
222
+ " This section builds the final columns for your spreadsheet.\n",
223
+ " Crucially, it calculates the 'Smallest Logit Diff'.\n",
224
+ " This can be considered an 'AI Certainty Score'. The closer this number is to 0,\n",
225
+ " the more confused the AI was. Please see the Hugging Face READMEs for each model which contains details on the impact on performance.\n",
226
+ " \"\"\"\n",
227
+ " # Clip thresholds to avoid log(0) warnings\n",
228
+ " safe_thresholds = np.clip(thresholds, 1e-7, 1 - 1e-7)\n",
229
+ " thr_logits = np.log(safe_thresholds / (1 - safe_thresholds))\n",
230
+ "\n",
231
+ " rows = {}\n",
232
+ " for i in range(len(df)):\n",
233
+ " logit_row = logits[i]\n",
234
+ " pred_row = preds[i]\n",
235
+ "\n",
236
+ " # gather categories labelled as 'yes'\n",
237
+ " chosen = [label_list[j] for j, val in enumerate(pred_row) if val == 1]\n",
238
+ "\n",
239
+ " # Calculate the uncertainty score\n",
240
+ " smallest_diff = float(np.min(np.abs(logit_row - thr_logits)))\n",
241
+ " rows[i] = {\n",
242
+ " f\"{prefix}_PredictedLabels\": \";\".join(chosen),\n",
243
+ " f\"{prefix}_SmallestLogitDiff\": smallest_diff\n",
244
+ " }\n",
245
+ " return rows\n",
246
+ "\n",
247
+ "# -------------------- PROCESS FOLDER --------------------\n",
248
+ "def run_folder(data_folder: str, hc_assets, rac_assets):\n",
249
+ " \"\"\"\n",
250
+ " This function opens your specific folder (selected in the first section), reads your CSV, passes it through\n",
251
+ " both AI models (Health Categories and Research Activity Codes), and saves the result.\n",
252
+ " \"\"\"\n",
253
+ " test_file = os.path.join(data_folder, TEST_FILENAME)\n",
254
+ " output_file = os.path.join(data_folder, OUTPUT_FILENAME)\n",
255
+ "\n",
256
+ " if not os.path.exists(test_file):\n",
257
+ " print(f\"Skipping: {test_file} not found in {data_folder}.\")\n",
258
+ " return\n",
259
+ "\n",
260
+ " print(f\"\\n=== Processing folder: {data_folder} ===\")\n",
261
+ " df = pd.read_csv(test_file).reset_index(drop=True)\n",
262
+ "\n",
263
+ " # Validate Input Data contains title and abstract\n",
264
+ " if \"AwardTitle\" not in df.columns or \"AwardAbstract\" not in df.columns:\n",
265
+ " print(f\"ERROR: '{TEST_FILENAME}' must contain 'AwardTitle' and 'AwardAbstract' columns. Skipping.\")\n",
266
+ " return\n",
267
+ "\n",
268
+ " # HC Inference\n",
269
+ " hc_tok, hc_model, hc_labels, hc_thr = hc_assets\n",
270
+ " hc_loader = DataLoader(TextDataset(df, hc_tok), batch_size=BATCH_SIZE)\n",
271
+ " hc_logits, _, hc_preds = predict(hc_model, hc_loader, hc_thr)\n",
272
+ " hc_rows = build_outputs(df, hc_logits, None, hc_preds, hc_labels, hc_thr, \"HC\")\n",
273
+ "\n",
274
+ " # RAC Inference\n",
275
+ " rac_tok, rac_model, rac_labels, rac_thr = rac_assets\n",
276
+ " rac_loader = DataLoader(TextDataset(df, rac_tok), batch_size=BATCH_SIZE)\n",
277
+ " rac_logits, _, rac_preds = predict(rac_model, rac_loader, rac_thr)\n",
278
+ " rac_rows = build_outputs(df, rac_logits, None, rac_preds, rac_labels, rac_thr, \"RAC\")\n",
279
+ "\n",
280
+ " # Construct final dataframe\n",
281
+ " output_data = []\n",
282
+ " for i in range(len(df)):\n",
283
+ " row = {\n",
284
+ " \"ID\": df.loc[i, \"ID\"] if \"ID\" in df.columns else i,\n",
285
+ " \"FunderAcronym\": df.loc[i, \"FunderAcronym\"] if \"FunderAcronym\" in df.columns else \"\",\n",
286
+ " \"AwardTitle\": df.loc[i, \"AwardTitle\"],\n",
287
+ " \"AwardAbstract\": df.loc[i, \"AwardAbstract\"],\n",
288
+ " **hc_rows[i],\n",
289
+ " **rac_rows[i]\n",
290
+ " }\n",
291
+ " output_data.append(row)\n",
292
+ "\n",
293
+ " pd.DataFrame(output_data).to_csv(OUTPUT_FILENAME, index=False)\n",
294
+ " print(f\"Success! Predictions saved to: {output_file}\")\n",
295
+ "\n",
296
+ "# -------------------- MAIN --------------------\n",
297
+ "if __name__ == \"__main__\":\n",
298
+ " print(\"Initialising HRCS Classifier Pipeline...\")\n",
299
+ "\n",
300
+ " # Load models once outside the loop to save memory/time\n",
301
+ " hc_assets = load_hf_model(HC_REPO_ID)\n",
302
+ " rac_assets = load_hf_model(RAC_REPO_ID)\n",
303
+ "\n",
304
+ " for folder in DATA_FOLDERS:\n",
305
+ " run_folder(folder, hc_assets, rac_assets)"
306
+ ]
307
+ }
308
+ ],
309
+ "metadata": {
310
+ "colab": {
311
+ "provenance": []
312
+ },
313
+ "kernelspec": {
314
+ "display_name": "base",
315
+ "language": "python",
316
+ "name": "python3"
317
+ },
318
+ "language_info": {
319
+ "codemirror_mode": {
320
+ "name": "ipython",
321
+ "version": 3
322
+ },
323
+ "file_extension": ".py",
324
+ "mimetype": "text/x-python",
325
+ "name": "python",
326
+ "nbconvert_exporter": "python",
327
+ "pygments_lexer": "ipython3",
328
+ "version": "3.12.7"
329
+ },
330
+ "widgets": {
331
+ "application/vnd.jupyter.widget-state+json": {
332
+ "0e22f97db509402a9b4d4a2fa8c80fe0": {
333
+ "model_module": "@jupyter-widgets/controls",
334
+ "model_module_version": "1.5.0",
335
+ "model_name": "HTMLModel",
336
+ "state": {
337
+ "_dom_classes": [],
338
+ "_model_module": "@jupyter-widgets/controls",
339
+ "_model_module_version": "1.5.0",
340
+ "_model_name": "HTMLModel",
341
+ "_view_count": null,
342
+ "_view_module": "@jupyter-widgets/controls",
343
+ "_view_module_version": "1.5.0",
344
+ "_view_name": "HTMLView",
345
+ "description": "",
346
+ "description_tooltip": null,
347
+ "layout": "IPY_MODEL_926c9a0562f3455b958c71bd0a138558",
348
+ "placeholder": "​",
349
+ "style": "IPY_MODEL_ef276c365d604dcc83b4a0133c6b7652",
350
+ "value": "Loading weights: 100%"
351
+ }
352
+ },
353
+ "1776c0895e7f400f85d3a2123cb573f1": {
354
+ "model_module": "@jupyter-widgets/controls",
355
+ "model_module_version": "1.5.0",
356
+ "model_name": "HTMLModel",
357
+ "state": {
358
+ "_dom_classes": [],
359
+ "_model_module": "@jupyter-widgets/controls",
360
+ "_model_module_version": "1.5.0",
361
+ "_model_name": "HTMLModel",
362
+ "_view_count": null,
363
+ "_view_module": "@jupyter-widgets/controls",
364
+ "_view_module_version": "1.5.0",
365
+ "_view_name": "HTMLView",
366
+ "description": "",
367
+ "description_tooltip": null,
368
+ "layout": "IPY_MODEL_9cba2384346645499516a7923ad6fcef",
369
+ "placeholder": "​",
370
+ "style": "IPY_MODEL_491f71a8889c4c7aa0042e99f374be79",
371
+ "value": "Loading weights: 100%"
372
+ }
373
+ },
374
+ "210ec65a874a4f51ab9f059d3de804a9": {
375
+ "model_module": "@jupyter-widgets/controls",
376
+ "model_module_version": "1.5.0",
377
+ "model_name": "HTMLModel",
378
+ "state": {
379
+ "_dom_classes": [],
380
+ "_model_module": "@jupyter-widgets/controls",
381
+ "_model_module_version": "1.5.0",
382
+ "_model_name": "HTMLModel",
383
+ "_view_count": null,
384
+ "_view_module": "@jupyter-widgets/controls",
385
+ "_view_module_version": "1.5.0",
386
+ "_view_name": "HTMLView",
387
+ "description": "",
388
+ "description_tooltip": null,
389
+ "layout": "IPY_MODEL_25529d785e9047e1b9bd197a7ec56773",
390
+ "placeholder": "​",
391
+ "style": "IPY_MODEL_9dda1a77133c4247bac106a9c4699153",
392
+ "value": " 393/393 [00:00&lt;00:00, 581.79it/s, Materializing param=classifier.weight]"
393
+ }
394
+ },
395
+ "25529d785e9047e1b9bd197a7ec56773": {
396
+ "model_module": "@jupyter-widgets/base",
397
+ "model_module_version": "1.2.0",
398
+ "model_name": "LayoutModel",
399
+ "state": {
400
+ "_model_module": "@jupyter-widgets/base",
401
+ "_model_module_version": "1.2.0",
402
+ "_model_name": "LayoutModel",
403
+ "_view_count": null,
404
+ "_view_module": "@jupyter-widgets/base",
405
+ "_view_module_version": "1.2.0",
406
+ "_view_name": "LayoutView",
407
+ "align_content": null,
408
+ "align_items": null,
409
+ "align_self": null,
410
+ "border": null,
411
+ "bottom": null,
412
+ "display": null,
413
+ "flex": null,
414
+ "flex_flow": null,
415
+ "grid_area": null,
416
+ "grid_auto_columns": null,
417
+ "grid_auto_flow": null,
418
+ "grid_auto_rows": null,
419
+ "grid_column": null,
420
+ "grid_gap": null,
421
+ "grid_row": null,
422
+ "grid_template_areas": null,
423
+ "grid_template_columns": null,
424
+ "grid_template_rows": null,
425
+ "height": null,
426
+ "justify_content": null,
427
+ "justify_items": null,
428
+ "left": null,
429
+ "margin": null,
430
+ "max_height": null,
431
+ "max_width": null,
432
+ "min_height": null,
433
+ "min_width": null,
434
+ "object_fit": null,
435
+ "object_position": null,
436
+ "order": null,
437
+ "overflow": null,
438
+ "overflow_x": null,
439
+ "overflow_y": null,
440
+ "padding": null,
441
+ "right": null,
442
+ "top": null,
443
+ "visibility": null,
444
+ "width": null
445
+ }
446
+ },
447
+ "3dc315e087f44330badbb6749b0611a9": {
448
+ "model_module": "@jupyter-widgets/base",
449
+ "model_module_version": "1.2.0",
450
+ "model_name": "LayoutModel",
451
+ "state": {
452
+ "_model_module": "@jupyter-widgets/base",
453
+ "_model_module_version": "1.2.0",
454
+ "_model_name": "LayoutModel",
455
+ "_view_count": null,
456
+ "_view_module": "@jupyter-widgets/base",
457
+ "_view_module_version": "1.2.0",
458
+ "_view_name": "LayoutView",
459
+ "align_content": null,
460
+ "align_items": null,
461
+ "align_self": null,
462
+ "border": null,
463
+ "bottom": null,
464
+ "display": null,
465
+ "flex": null,
466
+ "flex_flow": null,
467
+ "grid_area": null,
468
+ "grid_auto_columns": null,
469
+ "grid_auto_flow": null,
470
+ "grid_auto_rows": null,
471
+ "grid_column": null,
472
+ "grid_gap": null,
473
+ "grid_row": null,
474
+ "grid_template_areas": null,
475
+ "grid_template_columns": null,
476
+ "grid_template_rows": null,
477
+ "height": null,
478
+ "justify_content": null,
479
+ "justify_items": null,
480
+ "left": null,
481
+ "margin": null,
482
+ "max_height": null,
483
+ "max_width": null,
484
+ "min_height": null,
485
+ "min_width": null,
486
+ "object_fit": null,
487
+ "object_position": null,
488
+ "order": null,
489
+ "overflow": null,
490
+ "overflow_x": null,
491
+ "overflow_y": null,
492
+ "padding": null,
493
+ "right": null,
494
+ "top": null,
495
+ "visibility": null,
496
+ "width": null
497
+ }
498
+ },
499
+ "475728820f8e4b6fa0c33a1e9989179a": {
500
+ "model_module": "@jupyter-widgets/controls",
501
+ "model_module_version": "1.5.0",
502
+ "model_name": "FloatProgressModel",
503
+ "state": {
504
+ "_dom_classes": [],
505
+ "_model_module": "@jupyter-widgets/controls",
506
+ "_model_module_version": "1.5.0",
507
+ "_model_name": "FloatProgressModel",
508
+ "_view_count": null,
509
+ "_view_module": "@jupyter-widgets/controls",
510
+ "_view_module_version": "1.5.0",
511
+ "_view_name": "ProgressView",
512
+ "bar_style": "success",
513
+ "description": "",
514
+ "description_tooltip": null,
515
+ "layout": "IPY_MODEL_3dc315e087f44330badbb6749b0611a9",
516
+ "max": 393,
517
+ "min": 0,
518
+ "orientation": "horizontal",
519
+ "style": "IPY_MODEL_bc6c346b95424eb881b793bf6fd2f53e",
520
+ "value": 393
521
+ }
522
+ },
523
+ "491f71a8889c4c7aa0042e99f374be79": {
524
+ "model_module": "@jupyter-widgets/controls",
525
+ "model_module_version": "1.5.0",
526
+ "model_name": "DescriptionStyleModel",
527
+ "state": {
528
+ "_model_module": "@jupyter-widgets/controls",
529
+ "_model_module_version": "1.5.0",
530
+ "_model_name": "DescriptionStyleModel",
531
+ "_view_count": null,
532
+ "_view_module": "@jupyter-widgets/base",
533
+ "_view_module_version": "1.2.0",
534
+ "_view_name": "StyleView",
535
+ "description_width": ""
536
+ }
537
+ },
538
+ "926c9a0562f3455b958c71bd0a138558": {
539
+ "model_module": "@jupyter-widgets/base",
540
+ "model_module_version": "1.2.0",
541
+ "model_name": "LayoutModel",
542
+ "state": {
543
+ "_model_module": "@jupyter-widgets/base",
544
+ "_model_module_version": "1.2.0",
545
+ "_model_name": "LayoutModel",
546
+ "_view_count": null,
547
+ "_view_module": "@jupyter-widgets/base",
548
+ "_view_module_version": "1.2.0",
549
+ "_view_name": "LayoutView",
550
+ "align_content": null,
551
+ "align_items": null,
552
+ "align_self": null,
553
+ "border": null,
554
+ "bottom": null,
555
+ "display": null,
556
+ "flex": null,
557
+ "flex_flow": null,
558
+ "grid_area": null,
559
+ "grid_auto_columns": null,
560
+ "grid_auto_flow": null,
561
+ "grid_auto_rows": null,
562
+ "grid_column": null,
563
+ "grid_gap": null,
564
+ "grid_row": null,
565
+ "grid_template_areas": null,
566
+ "grid_template_columns": null,
567
+ "grid_template_rows": null,
568
+ "height": null,
569
+ "justify_content": null,
570
+ "justify_items": null,
571
+ "left": null,
572
+ "margin": null,
573
+ "max_height": null,
574
+ "max_width": null,
575
+ "min_height": null,
576
+ "min_width": null,
577
+ "object_fit": null,
578
+ "object_position": null,
579
+ "order": null,
580
+ "overflow": null,
581
+ "overflow_x": null,
582
+ "overflow_y": null,
583
+ "padding": null,
584
+ "right": null,
585
+ "top": null,
586
+ "visibility": null,
587
+ "width": null
588
+ }
589
+ },
590
+ "9275c5cf7b314dc69419611128cb0c09": {
591
+ "model_module": "@jupyter-widgets/base",
592
+ "model_module_version": "1.2.0",
593
+ "model_name": "LayoutModel",
594
+ "state": {
595
+ "_model_module": "@jupyter-widgets/base",
596
+ "_model_module_version": "1.2.0",
597
+ "_model_name": "LayoutModel",
598
+ "_view_count": null,
599
+ "_view_module": "@jupyter-widgets/base",
600
+ "_view_module_version": "1.2.0",
601
+ "_view_name": "LayoutView",
602
+ "align_content": null,
603
+ "align_items": null,
604
+ "align_self": null,
605
+ "border": null,
606
+ "bottom": null,
607
+ "display": null,
608
+ "flex": null,
609
+ "flex_flow": null,
610
+ "grid_area": null,
611
+ "grid_auto_columns": null,
612
+ "grid_auto_flow": null,
613
+ "grid_auto_rows": null,
614
+ "grid_column": null,
615
+ "grid_gap": null,
616
+ "grid_row": null,
617
+ "grid_template_areas": null,
618
+ "grid_template_columns": null,
619
+ "grid_template_rows": null,
620
+ "height": null,
621
+ "justify_content": null,
622
+ "justify_items": null,
623
+ "left": null,
624
+ "margin": null,
625
+ "max_height": null,
626
+ "max_width": null,
627
+ "min_height": null,
628
+ "min_width": null,
629
+ "object_fit": null,
630
+ "object_position": null,
631
+ "order": null,
632
+ "overflow": null,
633
+ "overflow_x": null,
634
+ "overflow_y": null,
635
+ "padding": null,
636
+ "right": null,
637
+ "top": null,
638
+ "visibility": null,
639
+ "width": null
640
+ }
641
+ },
642
+ "9cba2384346645499516a7923ad6fcef": {
643
+ "model_module": "@jupyter-widgets/base",
644
+ "model_module_version": "1.2.0",
645
+ "model_name": "LayoutModel",
646
+ "state": {
647
+ "_model_module": "@jupyter-widgets/base",
648
+ "_model_module_version": "1.2.0",
649
+ "_model_name": "LayoutModel",
650
+ "_view_count": null,
651
+ "_view_module": "@jupyter-widgets/base",
652
+ "_view_module_version": "1.2.0",
653
+ "_view_name": "LayoutView",
654
+ "align_content": null,
655
+ "align_items": null,
656
+ "align_self": null,
657
+ "border": null,
658
+ "bottom": null,
659
+ "display": null,
660
+ "flex": null,
661
+ "flex_flow": null,
662
+ "grid_area": null,
663
+ "grid_auto_columns": null,
664
+ "grid_auto_flow": null,
665
+ "grid_auto_rows": null,
666
+ "grid_column": null,
667
+ "grid_gap": null,
668
+ "grid_row": null,
669
+ "grid_template_areas": null,
670
+ "grid_template_columns": null,
671
+ "grid_template_rows": null,
672
+ "height": null,
673
+ "justify_content": null,
674
+ "justify_items": null,
675
+ "left": null,
676
+ "margin": null,
677
+ "max_height": null,
678
+ "max_width": null,
679
+ "min_height": null,
680
+ "min_width": null,
681
+ "object_fit": null,
682
+ "object_position": null,
683
+ "order": null,
684
+ "overflow": null,
685
+ "overflow_x": null,
686
+ "overflow_y": null,
687
+ "padding": null,
688
+ "right": null,
689
+ "top": null,
690
+ "visibility": null,
691
+ "width": null
692
+ }
693
+ },
694
+ "9dda1a77133c4247bac106a9c4699153": {
695
+ "model_module": "@jupyter-widgets/controls",
696
+ "model_module_version": "1.5.0",
697
+ "model_name": "DescriptionStyleModel",
698
+ "state": {
699
+ "_model_module": "@jupyter-widgets/controls",
700
+ "_model_module_version": "1.5.0",
701
+ "_model_name": "DescriptionStyleModel",
702
+ "_view_count": null,
703
+ "_view_module": "@jupyter-widgets/base",
704
+ "_view_module_version": "1.2.0",
705
+ "_view_name": "StyleView",
706
+ "description_width": ""
707
+ }
708
+ },
709
+ "9f60072613d84754a0efe7813d853565": {
710
+ "model_module": "@jupyter-widgets/base",
711
+ "model_module_version": "1.2.0",
712
+ "model_name": "LayoutModel",
713
+ "state": {
714
+ "_model_module": "@jupyter-widgets/base",
715
+ "_model_module_version": "1.2.0",
716
+ "_model_name": "LayoutModel",
717
+ "_view_count": null,
718
+ "_view_module": "@jupyter-widgets/base",
719
+ "_view_module_version": "1.2.0",
720
+ "_view_name": "LayoutView",
721
+ "align_content": null,
722
+ "align_items": null,
723
+ "align_self": null,
724
+ "border": null,
725
+ "bottom": null,
726
+ "display": null,
727
+ "flex": null,
728
+ "flex_flow": null,
729
+ "grid_area": null,
730
+ "grid_auto_columns": null,
731
+ "grid_auto_flow": null,
732
+ "grid_auto_rows": null,
733
+ "grid_column": null,
734
+ "grid_gap": null,
735
+ "grid_row": null,
736
+ "grid_template_areas": null,
737
+ "grid_template_columns": null,
738
+ "grid_template_rows": null,
739
+ "height": null,
740
+ "justify_content": null,
741
+ "justify_items": null,
742
+ "left": null,
743
+ "margin": null,
744
+ "max_height": null,
745
+ "max_width": null,
746
+ "min_height": null,
747
+ "min_width": null,
748
+ "object_fit": null,
749
+ "object_position": null,
750
+ "order": null,
751
+ "overflow": null,
752
+ "overflow_x": null,
753
+ "overflow_y": null,
754
+ "padding": null,
755
+ "right": null,
756
+ "top": null,
757
+ "visibility": null,
758
+ "width": null
759
+ }
760
+ },
761
+ "bc6c346b95424eb881b793bf6fd2f53e": {
762
+ "model_module": "@jupyter-widgets/controls",
763
+ "model_module_version": "1.5.0",
764
+ "model_name": "ProgressStyleModel",
765
+ "state": {
766
+ "_model_module": "@jupyter-widgets/controls",
767
+ "_model_module_version": "1.5.0",
768
+ "_model_name": "ProgressStyleModel",
769
+ "_view_count": null,
770
+ "_view_module": "@jupyter-widgets/base",
771
+ "_view_module_version": "1.2.0",
772
+ "_view_name": "StyleView",
773
+ "bar_color": null,
774
+ "description_width": ""
775
+ }
776
+ },
777
+ "bf48a3e692ae4e6da5379152f51baa09": {
778
+ "model_module": "@jupyter-widgets/controls",
779
+ "model_module_version": "1.5.0",
780
+ "model_name": "ProgressStyleModel",
781
+ "state": {
782
+ "_model_module": "@jupyter-widgets/controls",
783
+ "_model_module_version": "1.5.0",
784
+ "_model_name": "ProgressStyleModel",
785
+ "_view_count": null,
786
+ "_view_module": "@jupyter-widgets/base",
787
+ "_view_module_version": "1.2.0",
788
+ "_view_name": "StyleView",
789
+ "bar_color": null,
790
+ "description_width": ""
791
+ }
792
+ },
793
+ "c26db3dd5a86405b81f510fd759c3af7": {
794
+ "model_module": "@jupyter-widgets/base",
795
+ "model_module_version": "1.2.0",
796
+ "model_name": "LayoutModel",
797
+ "state": {
798
+ "_model_module": "@jupyter-widgets/base",
799
+ "_model_module_version": "1.2.0",
800
+ "_model_name": "LayoutModel",
801
+ "_view_count": null,
802
+ "_view_module": "@jupyter-widgets/base",
803
+ "_view_module_version": "1.2.0",
804
+ "_view_name": "LayoutView",
805
+ "align_content": null,
806
+ "align_items": null,
807
+ "align_self": null,
808
+ "border": null,
809
+ "bottom": null,
810
+ "display": null,
811
+ "flex": null,
812
+ "flex_flow": null,
813
+ "grid_area": null,
814
+ "grid_auto_columns": null,
815
+ "grid_auto_flow": null,
816
+ "grid_auto_rows": null,
817
+ "grid_column": null,
818
+ "grid_gap": null,
819
+ "grid_row": null,
820
+ "grid_template_areas": null,
821
+ "grid_template_columns": null,
822
+ "grid_template_rows": null,
823
+ "height": null,
824
+ "justify_content": null,
825
+ "justify_items": null,
826
+ "left": null,
827
+ "margin": null,
828
+ "max_height": null,
829
+ "max_width": null,
830
+ "min_height": null,
831
+ "min_width": null,
832
+ "object_fit": null,
833
+ "object_position": null,
834
+ "order": null,
835
+ "overflow": null,
836
+ "overflow_x": null,
837
+ "overflow_y": null,
838
+ "padding": null,
839
+ "right": null,
840
+ "top": null,
841
+ "visibility": null,
842
+ "width": null
843
+ }
844
+ },
845
+ "c91d89b903ce4f02b635454d3bd87877": {
846
+ "model_module": "@jupyter-widgets/base",
847
+ "model_module_version": "1.2.0",
848
+ "model_name": "LayoutModel",
849
+ "state": {
850
+ "_model_module": "@jupyter-widgets/base",
851
+ "_model_module_version": "1.2.0",
852
+ "_model_name": "LayoutModel",
853
+ "_view_count": null,
854
+ "_view_module": "@jupyter-widgets/base",
855
+ "_view_module_version": "1.2.0",
856
+ "_view_name": "LayoutView",
857
+ "align_content": null,
858
+ "align_items": null,
859
+ "align_self": null,
860
+ "border": null,
861
+ "bottom": null,
862
+ "display": null,
863
+ "flex": null,
864
+ "flex_flow": null,
865
+ "grid_area": null,
866
+ "grid_auto_columns": null,
867
+ "grid_auto_flow": null,
868
+ "grid_auto_rows": null,
869
+ "grid_column": null,
870
+ "grid_gap": null,
871
+ "grid_row": null,
872
+ "grid_template_areas": null,
873
+ "grid_template_columns": null,
874
+ "grid_template_rows": null,
875
+ "height": null,
876
+ "justify_content": null,
877
+ "justify_items": null,
878
+ "left": null,
879
+ "margin": null,
880
+ "max_height": null,
881
+ "max_width": null,
882
+ "min_height": null,
883
+ "min_width": null,
884
+ "object_fit": null,
885
+ "object_position": null,
886
+ "order": null,
887
+ "overflow": null,
888
+ "overflow_x": null,
889
+ "overflow_y": null,
890
+ "padding": null,
891
+ "right": null,
892
+ "top": null,
893
+ "visibility": null,
894
+ "width": null
895
+ }
896
+ },
897
+ "cf5e926c8c004525b5aad36d821ef928": {
898
+ "model_module": "@jupyter-widgets/controls",
899
+ "model_module_version": "1.5.0",
900
+ "model_name": "HTMLModel",
901
+ "state": {
902
+ "_dom_classes": [],
903
+ "_model_module": "@jupyter-widgets/controls",
904
+ "_model_module_version": "1.5.0",
905
+ "_model_name": "HTMLModel",
906
+ "_view_count": null,
907
+ "_view_module": "@jupyter-widgets/controls",
908
+ "_view_module_version": "1.5.0",
909
+ "_view_name": "HTMLView",
910
+ "description": "",
911
+ "description_tooltip": null,
912
+ "layout": "IPY_MODEL_c26db3dd5a86405b81f510fd759c3af7",
913
+ "placeholder": "​",
914
+ "style": "IPY_MODEL_dae2b5afeee243e682322c1ecb8238e6",
915
+ "value": " 393/393 [00:01&lt;00:00, 353.83it/s, Materializing param=classifier.weight]"
916
+ }
917
+ },
918
+ "d6d7368c1c7b4a549d9a706ee1a62785": {
919
+ "model_module": "@jupyter-widgets/controls",
920
+ "model_module_version": "1.5.0",
921
+ "model_name": "HBoxModel",
922
+ "state": {
923
+ "_dom_classes": [],
924
+ "_model_module": "@jupyter-widgets/controls",
925
+ "_model_module_version": "1.5.0",
926
+ "_model_name": "HBoxModel",
927
+ "_view_count": null,
928
+ "_view_module": "@jupyter-widgets/controls",
929
+ "_view_module_version": "1.5.0",
930
+ "_view_name": "HBoxView",
931
+ "box_style": "",
932
+ "children": [
933
+ "IPY_MODEL_0e22f97db509402a9b4d4a2fa8c80fe0",
934
+ "IPY_MODEL_475728820f8e4b6fa0c33a1e9989179a",
935
+ "IPY_MODEL_cf5e926c8c004525b5aad36d821ef928"
936
+ ],
937
+ "layout": "IPY_MODEL_9275c5cf7b314dc69419611128cb0c09"
938
+ }
939
+ },
940
+ "dae2b5afeee243e682322c1ecb8238e6": {
941
+ "model_module": "@jupyter-widgets/controls",
942
+ "model_module_version": "1.5.0",
943
+ "model_name": "DescriptionStyleModel",
944
+ "state": {
945
+ "_model_module": "@jupyter-widgets/controls",
946
+ "_model_module_version": "1.5.0",
947
+ "_model_name": "DescriptionStyleModel",
948
+ "_view_count": null,
949
+ "_view_module": "@jupyter-widgets/base",
950
+ "_view_module_version": "1.2.0",
951
+ "_view_name": "StyleView",
952
+ "description_width": ""
953
+ }
954
+ },
955
+ "e7fd82b589eb49aaba73aeafcc340421": {
956
+ "model_module": "@jupyter-widgets/controls",
957
+ "model_module_version": "1.5.0",
958
+ "model_name": "FloatProgressModel",
959
+ "state": {
960
+ "_dom_classes": [],
961
+ "_model_module": "@jupyter-widgets/controls",
962
+ "_model_module_version": "1.5.0",
963
+ "_model_name": "FloatProgressModel",
964
+ "_view_count": null,
965
+ "_view_module": "@jupyter-widgets/controls",
966
+ "_view_module_version": "1.5.0",
967
+ "_view_name": "ProgressView",
968
+ "bar_style": "success",
969
+ "description": "",
970
+ "description_tooltip": null,
971
+ "layout": "IPY_MODEL_9f60072613d84754a0efe7813d853565",
972
+ "max": 393,
973
+ "min": 0,
974
+ "orientation": "horizontal",
975
+ "style": "IPY_MODEL_bf48a3e692ae4e6da5379152f51baa09",
976
+ "value": 393
977
+ }
978
+ },
979
+ "ef276c365d604dcc83b4a0133c6b7652": {
980
+ "model_module": "@jupyter-widgets/controls",
981
+ "model_module_version": "1.5.0",
982
+ "model_name": "DescriptionStyleModel",
983
+ "state": {
984
+ "_model_module": "@jupyter-widgets/controls",
985
+ "_model_module_version": "1.5.0",
986
+ "_model_name": "DescriptionStyleModel",
987
+ "_view_count": null,
988
+ "_view_module": "@jupyter-widgets/base",
989
+ "_view_module_version": "1.2.0",
990
+ "_view_name": "StyleView",
991
+ "description_width": ""
992
+ }
993
+ },
994
+ "f66e121a24e441c2a4cb32fb87d22632": {
995
+ "model_module": "@jupyter-widgets/controls",
996
+ "model_module_version": "1.5.0",
997
+ "model_name": "HBoxModel",
998
+ "state": {
999
+ "_dom_classes": [],
1000
+ "_model_module": "@jupyter-widgets/controls",
1001
+ "_model_module_version": "1.5.0",
1002
+ "_model_name": "HBoxModel",
1003
+ "_view_count": null,
1004
+ "_view_module": "@jupyter-widgets/controls",
1005
+ "_view_module_version": "1.5.0",
1006
+ "_view_name": "HBoxView",
1007
+ "box_style": "",
1008
+ "children": [
1009
+ "IPY_MODEL_1776c0895e7f400f85d3a2123cb573f1",
1010
+ "IPY_MODEL_e7fd82b589eb49aaba73aeafcc340421",
1011
+ "IPY_MODEL_210ec65a874a4f51ab9f059d3de804a9"
1012
+ ],
1013
+ "layout": "IPY_MODEL_c91d89b903ce4f02b635454d3bd87877"
1014
+ }
1015
+ }
1016
+ }
1017
+ }
1018
+ },
1019
+ "nbformat": 4,
1020
+ "nbformat_minor": 0
1021
+ }