Upload 12 files
Browse files- .gitattributes +7 -32
- added_tokens.json +16 -0
- config.json +21 -0
- flax_model.msgpack +3 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +0 -0
- special_tokens_map.json +25 -0
- tf_model.h5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +62 -0
- vocab.txt +0 -0
.gitattributes
CHANGED
@@ -1,35 +1,10 @@
|
|
1 |
-
*.
|
2 |
-
*.
|
3 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
-
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
-
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
-
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
-
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
-
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
-
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
-
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
-
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
-
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
-
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
-
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
-
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
-
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
-
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
-
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
-
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
-
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
-
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
-
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
-
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
-
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
-
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
-
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
-
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
-
*.
|
31 |
-
*.
|
32 |
-
*.
|
33 |
-
*.
|
34 |
-
|
35 |
-
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
1 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
3 |
*.bin filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
4 |
*.h5 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
*.tflite filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.tar.gz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
10 |
+
optimizer.pt filter=lfs diff=lfs merge=lfs -text
|
|
added_tokens.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</FAC>": 50013,
|
3 |
+
"</GPE>": 50005,
|
4 |
+
"</LOC>": 50011,
|
5 |
+
"</ORG>": 50009,
|
6 |
+
"</PER>": 50001,
|
7 |
+
"</VEH>": 50003,
|
8 |
+
"</WEA>": 50007,
|
9 |
+
"<FAC>": 50012,
|
10 |
+
"<GPE>": 50004,
|
11 |
+
"<LOC>": 50010,
|
12 |
+
"<ORG>": 50008,
|
13 |
+
"<PER>": 50000,
|
14 |
+
"<VEH>": 50002,
|
15 |
+
"<WEA>": 50006
|
16 |
+
}
|
config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"attention_probs_dropout_prob": 0.1,
|
3 |
+
"directionality": "bidi",
|
4 |
+
"hidden_act": "gelu",
|
5 |
+
"hidden_dropout_prob": 0.1,
|
6 |
+
"hidden_size": 768,
|
7 |
+
"initializer_range": 0.02,
|
8 |
+
"intermediate_size": 3072,
|
9 |
+
"max_position_embeddings": 512,
|
10 |
+
"model_type": "bert",
|
11 |
+
"architectures": ["BertModel"],
|
12 |
+
"num_attention_heads": 12,
|
13 |
+
"num_hidden_layers": 12,
|
14 |
+
"pooler_fc_size": 768,
|
15 |
+
"pooler_num_attention_heads": 12,
|
16 |
+
"pooler_num_fc_layers": 3,
|
17 |
+
"pooler_size_per_head": 128,
|
18 |
+
"pooler_type": "first_token_transform",
|
19 |
+
"type_vocab_size": 2,
|
20 |
+
"vocab_size": 50000
|
21 |
+
}
|
flax_model.msgpack
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:775dcb30e9d0bc3f71f386809de67a324a2965b45e520185205f3ef87ab4ed9a
|
3 |
+
size 497772525
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:277f1bc63e56cf1af6265f17764d03c3635d0b30328d16b8c4314186ae561f2a
|
3 |
+
size 995776285
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:32f323a6421f6a5aae8976d52ca321195de5b008968b0da487a7aab8a3f25215
|
3 |
+
size 500388730
|
rng_state.pth
ADDED
Binary file (14.5 kB). View file
|
|
special_tokens_map.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<PER>",
|
4 |
+
"</PER>",
|
5 |
+
"<VEH>",
|
6 |
+
"</VEH>",
|
7 |
+
"<GPE>",
|
8 |
+
"</GPE>",
|
9 |
+
"<WEA>",
|
10 |
+
"</WEA>",
|
11 |
+
"<ORG>",
|
12 |
+
"</ORG>",
|
13 |
+
"<LOC>",
|
14 |
+
"</LOC>",
|
15 |
+
"<FAC>",
|
16 |
+
"</FAC>"
|
17 |
+
],
|
18 |
+
"bos_token": "[CLS]",
|
19 |
+
"cls_token": "[CLS]",
|
20 |
+
"eos_token": "[SEP]",
|
21 |
+
"mask_token": "[MASK]",
|
22 |
+
"pad_token": "[PAD]",
|
23 |
+
"sep_token": "[SEP]",
|
24 |
+
"unk_token": "[UNK]"
|
25 |
+
}
|
tf_model.h5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:300331f7f90ded4d185e3bf099dcec9b8fed82c97c056701d83b59b3bf5ba0a0
|
3 |
+
size 498100604
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
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_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"max_length": 512,
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_to_multiple_of": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"pad_token_type_id": 0,
|
53 |
+
"padding_side": "right",
|
54 |
+
"sep_token": "[SEP]",
|
55 |
+
"stride": 0,
|
56 |
+
"strip_accents": null,
|
57 |
+
"tokenize_chinese_chars": true,
|
58 |
+
"tokenizer_class": "BertTokenizer",
|
59 |
+
"truncation_side": "right",
|
60 |
+
"truncation_strategy": "longest_first",
|
61 |
+
"unk_token": "[UNK]"
|
62 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|