Upload 7 files

config.json

@@ -0,0 +1,93 @@
+{
+  "_name_or_path": "/users/ylabrak/DrBERT/models_partager/DrBERT_512_7GB_77740/",
+  "architectures": [
+    "CamembertForTokenClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "ABR",
+    "1": "ADJ",
+    "10": "PRO:DEM",
+    "11": "PRO:IND",
+    "12": "PRO:PER",
+    "13": "PRO:REL",
+    "14": "PRP",
+    "15": "PRP:det",
+    "16": "PUN",
+    "17": "PUN:cit",
+    "18": "SENT",
+    "19": "SYM",
+    "2": "ADV",
+    "20": "VER:con",
+    "21": "VER:cond",
+    "22": "VER:futu",
+    "23": "VER:impf",
+    "24": "VER:infi",
+    "25": "VER:pper",
+    "26": "VER:ppre",
+    "27": "VER:pres",
+    "28": "VER:simp",
+    "29": "VER:subi",
+    "3": "DET:ART",
+    "30": "VER:subp",
+    "4": "DET:POS",
+    "5": "INT",
+    "6": "KON",
+    "7": "NAM",
+    "8": "NOM",
+    "9": "NUM"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "ABR": "0",
+    "ADJ": "1",
+    "ADV": "2",
+    "DET:ART": "3",
+    "DET:POS": "4",
+    "INT": "5",
+    "KON": "6",
+    "NAM": "7",
+    "NOM": "8",
+    "NUM": "9",
+    "PRO:DEM": "10",
+    "PRO:IND": "11",
+    "PRO:PER": "12",
+    "PRO:REL": "13",
+    "PRP": "14",
+    "PRP:det": "15",
+    "PUN": "16",
+    "PUN:cit": "17",
+    "SENT": "18",
+    "SYM": "19",
+    "VER:con": "20",
+    "VER:cond": "21",
+    "VER:futu": "22",
+    "VER:impf": "23",
+    "VER:infi": "24",
+    "VER:pper": "25",
+    "VER:ppre": "26",
+    "VER:pres": "27",
+    "VER:simp": "28",
+    "VER:subi": "29",
+    "VER:subp": "30"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 514,
+  "model_type": "camembert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "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 sha256:5e741384ce8dde43ae88c3d2c5a8620b87b7ed2878182aa218837082b8da8e81
+size 440291825

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:701a6bfe3db86b7bc1f4174e54f11bc24da195751c04a3ccea354a599de5c43b
+size 791347

special_tokens_map.json

@@ -0,0 +1,19 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,26 @@
+{
+  "additional_special_tokens": [
+    "<s>NOTUSED",
+    "</s>NOTUSED"
+  ],
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "max_len": 512,
+  "model_max_length": 512,
+  "name_or_path": "/users/ylabrak/DrBERT/models_partager/DrBERT_512_7GB_77740/",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "./TokenizerFromScratchMLM/DrBERT_8GB_MLM/special_tokens_map.json",
+  "tokenizer_class": "CamembertTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b36d0e62449b56b415b86e46d5c7c26e723ab639f35a79c9079bfa7a876f53e9
+size 3567