Refactor : Using DistilBert instead of Bert

Dockerfile

@@ -18,7 +18,7 @@ ENV HF_HOME /code/.cache/huggingface
 RUN mkdir -p $HF_HOME && chmod -R 777 $HF_HOME
 
 # Copy the model files into the image
-COPY ./bert /code/bert
+COPY ./distilBert /code/distilBert
 
 # Copy the rest of the application files
 COPY . .

distilBert/DistilBert/label_encoder.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c74d910ccc2fd1e1627c256f2dfb626216eb2c19ff55fc4d910479c6fba064d1
+size 227

distilBert/DistilBert/saved_model/config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.0",
+  "vocab_size": 30522
+}

distilBert/DistilBert/saved_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68e27085fbfc0a8bb88ee9cc1dff8c6341938ea3e13c0e8bc93e94787e523dae
+size 267857176

distilBert/DistilBert/saved_tokenizer/special_tokens_map.json

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

distilBert/DistilBert/saved_tokenizer/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

helper_functions.py

@@ -6,13 +6,13 @@ from typing import Optional
 from torch import Tensor
 
 # Load the model
-model = BertForSequenceClassification.from_pretrained("bert/bertModel/saved_model")
+model = BertForSequenceClassification.from_pretrained("distilBert/DistilBert/saved_model")
 
 # Load the tokenizer
-tokenizer = BertTokenizer.from_pretrained("bert/bertModel/saved_tokenizer")
+tokenizer = BertTokenizer.from_pretrained("distilBert/DistilBert/saved_tokenizer")
 
 # Charger le label encoder
-with open("bert/bertModel/label_encoder.pkl", "rb") as f:
+with open("distilBert/DistilBert/label_encoder.pkl", "rb") as f:
     label_encoder = pickle.load(f)
 
 class_labels = {