Upload 7 files
Browse files- config.json +50 -0
- model.safetensors +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +56 -0
- tokenizer.json +0 -0
- tokenizer_config.json +84 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "almanach/camembert-large",
|
3 |
+
"architectures": [
|
4 |
+
"CamembertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 1024,
|
13 |
+
"id2label": {
|
14 |
+
"0": "O",
|
15 |
+
"1": "B-DISO",
|
16 |
+
"2": "I-DISO",
|
17 |
+
"3": "B-PROC",
|
18 |
+
"4": "I-PROC",
|
19 |
+
"5": "B-ANAT",
|
20 |
+
"6": "I-ANAT",
|
21 |
+
"7": "B-CHEM",
|
22 |
+
"8": "I-CHEM"
|
23 |
+
},
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 4096,
|
26 |
+
"label2id": {
|
27 |
+
"B-ANAT": 5,
|
28 |
+
"B-CHEM": 7,
|
29 |
+
"B-DISO": 1,
|
30 |
+
"B-PROC": 3,
|
31 |
+
"I-ANAT": 6,
|
32 |
+
"I-CHEM": 8,
|
33 |
+
"I-DISO": 2,
|
34 |
+
"I-PROC": 4,
|
35 |
+
"O": 0
|
36 |
+
},
|
37 |
+
"layer_norm_eps": 1e-05,
|
38 |
+
"max_position_embeddings": 514,
|
39 |
+
"model_type": "camembert",
|
40 |
+
"num_attention_heads": 16,
|
41 |
+
"num_hidden_layers": 24,
|
42 |
+
"output_past": true,
|
43 |
+
"pad_token_id": 1,
|
44 |
+
"position_embedding_type": "absolute",
|
45 |
+
"torch_dtype": "float32",
|
46 |
+
"transformers_version": "4.41.2",
|
47 |
+
"type_vocab_size": 1,
|
48 |
+
"use_cache": true,
|
49 |
+
"vocab_size": 32005
|
50 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1183346c99490333102ae8259888ed34d5f8be04cdf630dd0e26b37a518b57d
|
3 |
+
size 1342532476
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f98f266fdc548c94216aaadc13ffaaafacf0c8793303e2195322d954549ea261
|
3 |
+
size 808767
|
special_tokens_map.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s>NOTUSED",
|
4 |
+
"</s>NOTUSED",
|
5 |
+
"<unk>NOTUSED"
|
6 |
+
],
|
7 |
+
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"cls_token": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"eos_token": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"mask_token": {
|
29 |
+
"content": "<mask>",
|
30 |
+
"lstrip": true,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
},
|
35 |
+
"pad_token": {
|
36 |
+
"content": "<pad>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false
|
41 |
+
},
|
42 |
+
"sep_token": {
|
43 |
+
"content": "</s>",
|
44 |
+
"lstrip": false,
|
45 |
+
"normalized": false,
|
46 |
+
"rstrip": false,
|
47 |
+
"single_word": false
|
48 |
+
},
|
49 |
+
"unk_token": {
|
50 |
+
"content": "<unk>",
|
51 |
+
"lstrip": false,
|
52 |
+
"normalized": false,
|
53 |
+
"rstrip": false,
|
54 |
+
"single_word": false
|
55 |
+
}
|
56 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>NOTUSED",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>NOTUSED",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "<unk>NOTUSED",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"5": {
|
44 |
+
"content": "<s>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"6": {
|
52 |
+
"content": "</s>",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"32004": {
|
60 |
+
"content": "<mask>",
|
61 |
+
"lstrip": true,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
}
|
67 |
+
},
|
68 |
+
"additional_special_tokens": [
|
69 |
+
"<s>NOTUSED",
|
70 |
+
"</s>NOTUSED",
|
71 |
+
"<unk>NOTUSED"
|
72 |
+
],
|
73 |
+
"bos_token": "<s>",
|
74 |
+
"clean_up_tokenization_spaces": true,
|
75 |
+
"cls_token": "<s>",
|
76 |
+
"eos_token": "</s>",
|
77 |
+
"mask_token": "<mask>",
|
78 |
+
"model_max_length": 512,
|
79 |
+
"pad_token": "<pad>",
|
80 |
+
"sep_token": "</s>",
|
81 |
+
"sp_model_kwargs": {},
|
82 |
+
"tokenizer_class": "CamembertTokenizer",
|
83 |
+
"unk_token": "<unk>"
|
84 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7f40187b6d15d770e8ed7709f7987934e6c9bc39cb62f6d6b88b87e9967c5f8
|
3 |
+
size 5112
|