Add model and tokenizer files

config.json

@@ -1,27 +1,33 @@
 {
-  "_name_or_path": "camembert-base",
+  "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
+  "activation": "gelu",
   "architectures": [
-    "CamembertForMaskedLM"
+    "DistilBertForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 5,
-  "classifier_dropout": null,
-  "eos_token_id": 6,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "finetuning_task": "sst-2",
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "NEGATIVE",
+    "1": "POSITIVE"
+  },
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "camembert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "label2id": {
+    "NEGATIVE": 0,
+    "POSITIVE": 1
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
   "output_past": true,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
+  "pad_token_id": 0,
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
   "transformers_version": "4.44.2",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 32005
+  "vocab_size": 30522
 }

special_tokens_map.json

@@ -1,20 +1,7 @@
 {
-  "additional_special_tokens": [
-    "<s>NOTUSED",
-    "</s>NOTUSED",
-    "<unk>NOTUSED"
-  ],
-  "bos_token": "<s>",
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": {
-    "content": "<mask>",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eea6ab38080c6af4583fb90ef0bba6f1991b1e376c008dba8052fff82b28dd7
-size 542808676
+oid sha256:2ae89159d429dd2433bb8a627d29e6ec84949a59a4707a79fa2f49cfed03cd98
+size 267955144

tokenizer_config.json

@@ -1,63 +1,39 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>NOTUSED",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<pad>",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>NOTUSED",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "4": {
-      "content": "<unk>",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "5": {
-      "content": "<s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "6": {
-      "content": "</s>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32004": {
-      "content": "<mask>",
-      "lstrip": true,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32005": {
-      "content": "<unk>NOTUSED",
+    "103": {
+      "content": "[MASK]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -65,19 +41,17 @@
       "special": true
     }
   },
-  "additional_special_tokens": [
-    "<s>NOTUSED",
-    "</s>NOTUSED",
-    "<unk>NOTUSED"
-  ],
-  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "cls_token": "<s>",
-  "eos_token": "</s>",
-  "mask_token": "<mask>",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
   "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "CamembertTokenizer",
-  "unk_token": "<unk>"
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
 }