Load model and tokenizer
Browse files- config.json +75 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- sentencepiece.bpe.model +3 -0
- special_tokens_map.json +13 -0
- tokenizer.json +0 -0
- tokenizer_config.json +25 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "HueyNemud/das22-10-camembert_pretrained",
|
3 |
+
"architectures": [
|
4 |
+
"CamembertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 5,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 6,
|
10 |
+
"gradient_checkpointing": false,
|
11 |
+
"hidden_act": "gelu",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
+
"id2label": {
|
15 |
+
"0": "O",
|
16 |
+
"1": "I-PER",
|
17 |
+
"2": "I-DESC",
|
18 |
+
"3": "I-TITRE",
|
19 |
+
"4": "I-SPAT",
|
20 |
+
"5": "I-TITREH",
|
21 |
+
"6": "I-TITREP",
|
22 |
+
"7": "I-ACT",
|
23 |
+
"8": "I-LOC",
|
24 |
+
"9": "I-CARDINAL",
|
25 |
+
"10": "I-FT",
|
26 |
+
"11": "B-PER",
|
27 |
+
"12": "B-DESC",
|
28 |
+
"13": "B-TITRE",
|
29 |
+
"14": "B-SPAT",
|
30 |
+
"15": "B-TITREH",
|
31 |
+
"16": "B-TITREP",
|
32 |
+
"17": "B-ACT",
|
33 |
+
"18": "B-LOC",
|
34 |
+
"19": "B-CARDINAL",
|
35 |
+
"20": "B-FT"
|
36 |
+
},
|
37 |
+
"initializer_range": 0.02,
|
38 |
+
"intermediate_size": 3072,
|
39 |
+
"label2id": {
|
40 |
+
"B-ACT": 17,
|
41 |
+
"B-CARDINAL": 19,
|
42 |
+
"B-DESC": 12,
|
43 |
+
"B-FT": 20,
|
44 |
+
"B-LOC": 18,
|
45 |
+
"B-PER": 11,
|
46 |
+
"B-SPAT": 14,
|
47 |
+
"B-TITRE": 13,
|
48 |
+
"B-TITREH": 15,
|
49 |
+
"B-TITREP": 16,
|
50 |
+
"I-ACT": 7,
|
51 |
+
"I-CARDINAL": 9,
|
52 |
+
"I-DESC": 2,
|
53 |
+
"I-FT": 10,
|
54 |
+
"I-LOC": 8,
|
55 |
+
"I-PER": 1,
|
56 |
+
"I-SPAT": 4,
|
57 |
+
"I-TITRE": 3,
|
58 |
+
"I-TITREH": 5,
|
59 |
+
"I-TITREP": 6,
|
60 |
+
"O": 0
|
61 |
+
},
|
62 |
+
"layer_norm_eps": 1e-05,
|
63 |
+
"max_position_embeddings": 514,
|
64 |
+
"model_type": "camembert",
|
65 |
+
"num_attention_heads": 12,
|
66 |
+
"num_hidden_layers": 12,
|
67 |
+
"output_past": true,
|
68 |
+
"pad_token_id": 1,
|
69 |
+
"position_embedding_type": "absolute",
|
70 |
+
"torch_dtype": "float32",
|
71 |
+
"transformers_version": "4.25.1",
|
72 |
+
"type_vocab_size": 1,
|
73 |
+
"use_cache": true,
|
74 |
+
"vocab_size": 32005
|
75 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:905c7f69d73d80dc36a7f1c1b114483ef9c156ed410ea65ca5fbba18c189cfa7
|
3 |
+
size 880495461
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4412608aa3d5102c28580444c1b929829ff6a514ade30f7a9e858e93d85d2d7d
|
3 |
+
size 440261105
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2da5f066abf0edfceff34565a9ac08c2ee77acf97c5436c5dbf78277fde1ef48
|
3 |
+
size 14503
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49b57bc5172463fef07fc294451bc054e3a77eb4220472a8f5c71745e477f749
|
3 |
+
size 623
|
sentencepiece.bpe.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
|
3 |
+
size 810912
|
special_tokens_map.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s>NOTUSED",
|
4 |
+
"</s>NOTUSED"
|
5 |
+
],
|
6 |
+
"bos_token": "<s>",
|
7 |
+
"cls_token": "<s>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"mask_token": "<mask>",
|
10 |
+
"pad_token": "<pad>",
|
11 |
+
"sep_token": "</s>",
|
12 |
+
"unk_token": "<unk>"
|
13 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<s>NOTUSED",
|
4 |
+
"</s>NOTUSED"
|
5 |
+
],
|
6 |
+
"bos_token": "<s>",
|
7 |
+
"cls_token": "<s>",
|
8 |
+
"eos_token": "</s>",
|
9 |
+
"mask_token": {
|
10 |
+
"__type": "AddedToken",
|
11 |
+
"content": "<mask>",
|
12 |
+
"lstrip": true,
|
13 |
+
"normalized": true,
|
14 |
+
"rstrip": false,
|
15 |
+
"single_word": false
|
16 |
+
},
|
17 |
+
"model_max_length": 512,
|
18 |
+
"name_or_path": "HueyNemud/das22-10-camembert_pretrained",
|
19 |
+
"pad_token": "<pad>",
|
20 |
+
"sep_token": "</s>",
|
21 |
+
"sp_model_kwargs": {},
|
22 |
+
"special_tokens_map_file": "/lrde/home2/jchazalo/.cache/huggingface/transformers/fe0e213c44079a9ee091098f81fff2941484006e9ba3001a9bf1ee9f87537599.cb3ec3a6c1200d181228d8825ae9767572abca54efa1bbb37fd83d721b2ef323",
|
23 |
+
"tokenizer_class": "CamembertTokenizer",
|
24 |
+
"unk_token": "<unk>"
|
25 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7ff505c447faca4d325b57f79b62daa2da3c646e921a59d3b5ccdce616673e6
|
3 |
+
size 3503
|