hf-transformers-bot
commited on
Commit
•
69db815
1
Parent(s):
94557ac
Upload tiny models for BigBirdModel
Browse files- config.json +32 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +51 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +63 -0
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"BigBirdModel"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"attention_type": "block_sparse",
|
7 |
+
"block_size": 8,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"classifier_dropout": null,
|
10 |
+
"eos_token_id": 2,
|
11 |
+
"hidden_act": "gelu_new",
|
12 |
+
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 32,
|
14 |
+
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 37,
|
16 |
+
"layer_norm_eps": 1e-12,
|
17 |
+
"max_position_embeddings": 256,
|
18 |
+
"model_type": "big_bird",
|
19 |
+
"num_attention_heads": 4,
|
20 |
+
"num_hidden_layers": 2,
|
21 |
+
"num_random_blocks": 3,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"position_embedding_type": "absolute",
|
24 |
+
"rescale_embeddings": false,
|
25 |
+
"sep_token_id": 66,
|
26 |
+
"torch_dtype": "float32",
|
27 |
+
"transformers_version": "4.28.0.dev0",
|
28 |
+
"type_vocab_size": 16,
|
29 |
+
"use_bias": true,
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 50358
|
32 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a646270f6b5dd5c17a988f7644c1826e45305847bff7e79b9d657dce04992153
|
3 |
+
size 6553897
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "</s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "[CLS]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "<s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "[MASK]",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "[SEP]",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fdc81e1fc9d42e0c08b86d5b280d05d7c5e9747c4231c648f2b56b8e1d893c82
|
3 |
+
size 845731
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"__type": "AddedToken",
|
4 |
+
"content": "</s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
"clean_up_tokenization_spaces": true,
|
11 |
+
"cls_token": {
|
12 |
+
"__type": "AddedToken",
|
13 |
+
"content": "[CLS]",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"eos_token": {
|
20 |
+
"__type": "AddedToken",
|
21 |
+
"content": "<s>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"mask_token": {
|
28 |
+
"__type": "AddedToken",
|
29 |
+
"content": "[MASK]",
|
30 |
+
"lstrip": true,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
},
|
35 |
+
"model_max_length": 256,
|
36 |
+
"pad_token": {
|
37 |
+
"__type": "AddedToken",
|
38 |
+
"content": "<pad>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"sep_token": {
|
45 |
+
"__type": "AddedToken",
|
46 |
+
"content": "[SEP]",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": true,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false
|
51 |
+
},
|
52 |
+
"sp_model_kwargs": {},
|
53 |
+
"special_tokens_map_file": "/home/runner/.cache/huggingface/hub/models--google--bigbird-roberta-base/snapshots/5a145f7852cba9bd431386a58137bf8a29903b90/special_tokens_map.json",
|
54 |
+
"tokenizer_class": "BigBirdTokenizer",
|
55 |
+
"unk_token": {
|
56 |
+
"__type": "AddedToken",
|
57 |
+
"content": "<unk>",
|
58 |
+
"lstrip": false,
|
59 |
+
"normalized": true,
|
60 |
+
"rstrip": false,
|
61 |
+
"single_word": false
|
62 |
+
}
|
63 |
+
}
|