Hugging Face's logo

hf-tiny-model-private
/
tiny-random-BigBirdPegasusForCausalLM

Text Generation
Transformers
PyTorch
bigbird_pegasus
Inference Endpoints
Model card Files Community
hf-transformers-bot commited on
Commit
7a3e64f
•
1 Parent(s): 9a11548

Upload tiny models for BigBirdPegasusForCausalLM

Browse files
Files changed (7) hide show
  1. config.json +38 -0
  2. generation_config.json +8 -0
  3. pytorch_model.bin +3 -0
  4. special_tokens_map.json +51 -0
  5. spiece.model +3 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +59 -0
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "BigBirdPegasusForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "attention_type": "block_sparse",
9
+ "block_size": 16,
10
+ "bos_token_id": 2,
11
+ "classifier_dropout": 0.0,
12
+ "d_model": 32,
13
+ "decoder_attention_heads": 4,
14
+ "decoder_ffn_dim": 31,
15
+ "decoder_layerdrop": 0.0,
16
+ "decoder_layers": 2,
17
+ "decoder_start_token_id": 2,
18
+ "dropout": 0.1,
19
+ "encoder_attention_heads": 4,
20
+ "encoder_ffn_dim": 31,
21
+ "encoder_layerdrop": 0.0,
22
+ "encoder_layers": 2,
23
+ "eos_token_id": 1,
24
+ "init_std": 0.02,
25
+ "is_decoder": true,
26
+ "is_encoder_decoder": false,
27
+ "max_position_embeddings": 260,
28
+ "model_type": "bigbird_pegasus",
29
+ "num_hidden_layers": 2,
30
+ "num_random_blocks": 3,
31
+ "pad_token_id": 0,
32
+ "scale_embedding": true,
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.28.0.dev0",
35
+ "use_bias": false,
36
+ "use_cache": true,
37
+ "vocab_size": 96103
38
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": 1,
6
+ "pad_token_id": 0,
7
+ "transformers_version": "4.28.0.dev0"
8
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5bae95d8a386d2c44dfc68216c3c7179c32fa22d3a27ccc5fa6bcb6b24f0838
3
+ size 12430953
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:fe1b40df7e8825709c0172639c47338a68d5622e9e3b6cc0fae516537cae738b
3
+ size 1915455
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [],
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "[CLS]",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "mask_token": "[MASK]",
29
+ "mask_token_sent": null,
30
+ "model_max_length": 260,
31
+ "offset": 0,
32
+ "pad_token": {
33
+ "__type": "AddedToken",
34
+ "content": "<pad>",
35
+ "lstrip": false,
36
+ "normalized": true,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ },
40
+ "sep_token": {
41
+ "__type": "AddedToken",
42
+ "content": "[SEP]",
43
+ "lstrip": false,
44
+ "normalized": true,
45
+ "rstrip": false,
46
+ "single_word": false
47
+ },
48
+ "sp_model_kwargs": {},
49
+ "special_tokens_map_file": "/home/patrick/.cache/huggingface/transformers/b548e984b09823ed5cea0e622c0ec194a7e07b3c5d2e6b48a7cde84bd179cc7c.4eda581f816a0a941629106f0338c957910ce4839ecf7e3e743bb79523bf7249",
50
+ "tokenizer_class": "PegasusTokenizer",
51
+ "unk_token": {
52
+ "__type": "AddedToken",
53
+ "content": "<unk>",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ }
59
+ }