PoC model

config.json

@@ -0,0 +1,51 @@
+{
+  "_name_or_path": "Jean-Baptiste/camembert-ner-with-dates",
+  "architectures": [
+    "CamembertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 5,
+  "classifier_dropout": null,
+  "eos_token_id": 6,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "I-LOC",
+    "2": "I-PER",
+    "3": "I-MISC",
+    "4": "I-ORG",
+    "5": "I-DATE",
+    "6": "I-CARDINAL",
+    "7": "I-ACT",
+    "8": "I-TITRE"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "I-ACT": 7,
+    "I-CARDINAL": 6,
+    "I-DATE": 5,
+    "I-LOC": 1,
+    "I-MISC": 3,
+    "I-ORG": 4,
+    "I-PER": 2,
+    "I-TITRE": 8,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 32005
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5e0a4e1052568dfd5331be9af89118d34f92a43fec3d0786b2629a11416443f
+size 440237809

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
+size 810912

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": "<mask>", "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "additional_special_tokens": ["<s>NOTUSED", "</s>NOTUSED"], "model_max_length": 512, "name_or_path": "Jean-Baptiste/camembert-ner-with-dates", "special_tokens_map_file": "models_data/models/camembert-base_forTokenCLassification\\special_tokens_map.json", "sp_model_kwargs": {}, "tokenizer_class": "CamembertTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbc2b74a3788d0e2bba1c1577a13274d5b2a7348bba0b710437d0b26469228fd
+size 2799