Ajout du modèle et du tokenizer

config.json

@@ -1,52 +1,57 @@
 {
-  "_name_or_path": "almanach/camembertv2-base",
+  "_name_or_path": "almanach/camembertav2-base",
   "architectures": [
-    "RobertaForTokenClassification"
+    "DebertaV2ForTokenClassification"
   ],
   "attention_probs_dropout_prob": 0.1,
   "bos_token_id": 1,
-  "classifier_dropout": null,
+  "conv_act": "gelu",
+  "conv_kernel_size": 0,
   "embedding_size": 768,
   "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "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"
+    "0": "O",
+    "1": "LOC",
+    "2": "PER",
+    "3": "MISC",
+    "4": "ORG",
+    "5": "DATE"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "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
+    "DATE": 5,
+    "LOC": 1,
+    "MISC": 3,
+    "O": 0,
+    "ORG": 4,
+    "PER": 2
   },
   "layer_norm_eps": 1e-07,
-  "max_position_embeddings": 1025,
-  "model_name": "camembertv2-base",
-  "model_type": "roberta",
+  "max_position_embeddings": 1024,
+  "max_relative_positions": -1,
+  "model_name": "camembertav2-base",
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
   "pad_token_id": 0,
-  "position_biased_input": true,
-  "position_embedding_type": "absolute",
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 768,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "relative_attention": true,
+  "share_att_key": true,
   "torch_dtype": "float32",
   "transformers_version": "4.46.2",
-  "type_vocab_size": 1,
-  "use_cache": true,
+  "type_vocab_size": 0,
   "vocab_size": 32768
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0efe413590205ded30196138b6e4d09575443b2c0eeec57406bbcc82606eff86
-size 444090780
+oid sha256:c24c62ec70fe60773bc19a0bef33d9f21e6ca2e51673a06f8af3fcfbe4bc7418
+size 442509128

tokenizer.json

@@ -1,7 +1,21 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 128,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": {
+      "Fixed": 128
+    },
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "[PAD]"
+  },
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -48,7 +48,7 @@
   "eos_token": "[SEP]",
   "errors": "replace",
   "mask_token": "[MASK]",
-  "model_max_length": 1024,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "[PAD]",
   "sep_token": "[SEP]",
   "tokenizer_class": "RobertaTokenizer",