Upload folder using huggingface_hub
Browse files- config.json +1 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"architectures": ["BertForTokenClassification"], "attention_probs_dropout_prob": 0.1, "classifier_dropout": null, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": {"0": "B-AnatomicalStructure", "1": "B-Bacterium", "2": "B-BiologicFunction", "3": "B-BiomedicalOccupationOrDiscipline", "4": "B-BodySubstance", "5": "B-BodySystem", "6": "B-Chemical", "7": "B-ClinicalAttribute", "8": "B-Eukaryote", "9": "B-Finding", "10": "B-Food", "11": "B-HealthCareActivity", "12": "B-InjuryOrPoisoning", "13": "B-IntellectualProduct", "14": "B-MedicalDevice", "15": "B-Organization", "16": "B-PopulationGroup", "17": "B-ProfessionalOrOccupationalGroup", "18": "B-ResearchActivity", "19": "B-SpatialConcept", "20": "B-Virus", "21": "I-AnatomicalStructure", "22": "I-Bacterium", "23": "I-BiologicFunction", "24": "I-BiomedicalOccupationOrDiscipline", "25": "I-BodySubstance", "26": "I-BodySystem", "27": "I-Chemical", "28": "I-ClinicalAttribute", "29": "I-Eukaryote", "30": "I-Finding", "31": "I-Food", "32": "I-HealthCareActivity", "33": "I-InjuryOrPoisoning", "34": "I-IntellectualProduct", "35": "I-MedicalDevice", "36": "I-Organization", "37": "I-PopulationGroup", "38": "I-ProfessionalOrOccupationalGroup", "39": "I-ResearchActivity", "40": "I-SpatialConcept", "41": "I-Virus", "42": "O"}, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": {"B-AnatomicalStructure": "0", "B-Bacterium": "1", "B-BiologicFunction": "2", "B-BiomedicalOccupationOrDiscipline": "3", "B-BodySubstance": "4", "B-BodySystem": "5", "B-Chemical": "6", "B-ClinicalAttribute": "7", "B-Eukaryote": "8", "B-Finding": "9", "B-Food": "10", "B-HealthCareActivity": "11", "B-InjuryOrPoisoning": "12", "B-IntellectualProduct": "13", "B-MedicalDevice": "14", "B-Organization": "15", "B-PopulationGroup": "16", "B-ProfessionalOrOccupationalGroup": "17", "B-ResearchActivity": "18", "B-SpatialConcept": "19", "B-Virus": "20", "I-AnatomicalStructure": "21", "I-Bacterium": "22", "I-BiologicFunction": "23", "I-BiomedicalOccupationOrDiscipline": "24", "I-BodySubstance": "25", "I-BodySystem": "26", "I-Chemical": "27", "I-ClinicalAttribute": "28", "I-Eukaryote": "29", "I-Finding": "30", "I-Food": "31", "I-HealthCareActivity": "32", "I-InjuryOrPoisoning": "33", "I-IntellectualProduct": "34", "I-MedicalDevice": "35", "I-Organization": "36", "I-PopulationGroup": "37", "I-ProfessionalOrOccupationalGroup": "38", "I-ResearchActivity": "39", "I-SpatialConcept": "40", "I-Virus": "41", "O": "42"}, "layer_norm_eps": 1e-12, "max_position_embeddings": 512, "model_type": "bert", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 0, "position_embedding_type": "absolute", "torch_dtype": "float32", "transformers_version": "4.55.4", "type_vocab_size": 2, "use_cache": true, "vocab_size": 30522}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dc0f2b71262ba7219d6ea06f20c9f1b229fee823dbf6e79476413481bf67470e
|
| 3 |
+
size 435722204
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": true,
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
+
"mask_token": "[MASK]",
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"never_split": null,
|
| 52 |
+
"pad_token": "[PAD]",
|
| 53 |
+
"sep_token": "[SEP]",
|
| 54 |
+
"strip_accents": null,
|
| 55 |
+
"tokenize_chinese_chars": true,
|
| 56 |
+
"tokenizer_class": "BertTokenizer",
|
| 57 |
+
"unk_token": "[UNK]"
|
| 58 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|