Change best model to BIOELECTRA model

app.py

@@ -1,5 +1,5 @@
 from flask import Flask, request, render_template, send_file
-from transformers import AutoModelForTokenClassification, RobertaTokenizer, pipeline
+from transformers import AutoModelForTokenClassification, AutoTokenizer, pipeline
 from collections import Counter
 import datetime, json
 import os
@@ -8,8 +8,8 @@ app = Flask(__name__)
 
 try:
     # Load model from local files
-    model = AutoModelForTokenClassification.from_pretrained("roberta_model", local_files_only=True)
-    tokenizer = RobertaTokenizer.from_pretrained("roberta_model", local_files_only=True)
+    model = AutoModelForTokenClassification.from_pretrained("bioelectra_model", local_files_only=True)
+    tokenizer = AutoTokenizer.from_pretrained("bioelectra_model", local_files_only=True)
     nlp = pipeline("token-classification", model=model, tokenizer=tokenizer, aggregation_strategy="simple")
     print("Pipeline loaded successfully!")
 except Exception as e:

bioelectra_model/config.json

@@ -0,0 +1,41 @@
+{
+  "architectures": [
+    "ElectraForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "B-AC",
+    "1": "B-LF",
+    "2": "I-LF",
+    "3": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B-AC": 0,
+    "B-LF": 1,
+    "I-LF": 2,
+    "O": 3
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

bioelectra_model/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

bioelectra_model/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "unk_token": "[UNK]"
+}

roberta_model/config.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c46810bc1ab9c01c6d0161eec4da3d84b5a1ec6a48590b8dd6d93f0f6c0a8e3d
-size 810

roberta_model/merges.txt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1ce1664773c50f3e0cc8842619a93edc4624525b728b188a9e0be33b7726adc5
-size 456318

roberta_model/special_tokens_map.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:06e405a36dfe4b9604f484f6a1e619af1a7f7d09e34a8555eb0b77b66318067f
-size 280

roberta_model/tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5765a30438d50e6f698c3ac6f8a09125db725006ca376cf692056d9b9db40151
-size 3558906

roberta_model/tokenizer_config.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:38b4f61b73aab22f9c2bb01d0f2be28d745e1db57ef7fcfddfa33c6ac8265444
-size 1245

roberta_model/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:92e2a186efd310ad699b41d69c662674b2afe096fc60962964a6c63b2782b92e
-size 5240

roberta_model/vocab.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ed19656ea1707df69134c4af35c8ceda2cc9860bf2c3495026153a133670ab5e
-size 798293

templates/index.html

@@ -2,7 +2,7 @@
 <html lang="en">
 <head>
     <meta charset="UTF-8">
-    <title>RoBERTa Token Classification</title>
+    <title>BIOELECTRA Token Classification</title>
     <script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
     <style>
         body { font-family: Arial, sans-serif; padding: 20px; background-color: #f8f9fa; }
@@ -17,7 +17,7 @@
 </head>
 <body>
 
-    <h1>RoBERTa Token Classification Demo</h1>
+    <h1>BIOELECTRA Token Classification Demo</h1>
 
     <form method="post" action="/" enctype="application/x-www-form-urlencoded">
         <label for="input_text">Enter a sentence:</label><br>