Pretrained on pero-OCR, fine-tuned for NER on pero-OCR

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Jean-Baptiste/camembert-ner-with-dates",
+  "_name_or_path": "HueyNemud/das22-10-camembert_pretrained",
   "architectures": [
     "CamembertForTokenClassification"
   ],
@@ -17,22 +17,22 @@
     "2": "I-PER",
     "3": "I-MISC",
     "4": "I-ORG",
-    "5": "I-DATE",
-    "6": "I-CARDINAL",
-    "7": "I-ACT",
-    "8": "I-TITRE"
+    "5": "I-CARDINAL",
+    "6": "I-ACT",
+    "7": "I-TITRE",
+    "8": "I-FT"
   },
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "label2id": {
-    "I-ACT": 7,
-    "I-CARDINAL": 6,
-    "I-DATE": 5,
+    "I-ACT": 6,
+    "I-CARDINAL": 5,
+    "I-FT": 8,
     "I-LOC": 1,
     "I-MISC": 3,
     "I-ORG": 4,
     "I-PER": 2,
-    "I-TITRE": 8,
+    "I-TITRE": 7,
     "O": 0
   },
   "layer_norm_eps": 1e-05,
@@ -44,7 +44,7 @@
   "pad_token_id": 1,
   "position_embedding_type": "absolute",
   "torch_dtype": "float32",
-  "transformers_version": "4.12.3",
+  "transformers_version": "4.15.0",
   "type_vocab_size": 1,
   "use_cache": true,
   "vocab_size": 32005

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5e0a4e1052568dfd5331be9af89118d34f92a43fec3d0786b2629a11416443f
+oid sha256:10b4c449f459a1dd150bde11f8cf172d41be99a9f3b58800012ae433cc402cc2
 size 440237809

tokenizer_config.json

@@ -1 +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"}
+{"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": "HueyNemud/das22-10-camembert_pretrained", "special_tokens_map_file": "/lrde/home2/jchazalo/.cache/huggingface/transformers/fe0e213c44079a9ee091098f81fff2941484006e9ba3001a9bf1ee9f87537599.cb3ec3a6c1200d181228d8825ae9767572abca54efa1bbb37fd83d721b2ef323", "sp_model_kwargs": {}, "tokenizer_class": "CamembertTokenizer"}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbc2b74a3788d0e2bba1c1577a13274d5b2a7348bba0b710437d0b26469228fd
-size 2799
+oid sha256:31aeb7cf016b0e47597e331fa262b44873f81073521049d8a85dc46bd2004681
+size 3055