Hugging Face's logo

Xenova
/
transformers.js

ONNX
Model card Files Community
3
Joshua Lochner commited on
Commit
a2029ac
•
1 Parent(s): d5b753d

Add roberta-base and distilroberta-base models

Browse files
Files changed (28) hide show
  1. quantized/distilroberta-base/default/config.json +26 -0
  2. quantized/distilroberta-base/default/merges.txt +0 -0
  3. quantized/distilroberta-base/default/model.onnx +3 -0
  4. quantized/distilroberta-base/default/special_tokens_map.json +15 -0
  5. quantized/distilroberta-base/default/tokenizer.json +0 -0
  6. quantized/distilroberta-base/default/tokenizer_config.json +16 -0
  7. quantized/distilroberta-base/default/vocab.json +0 -0
  8. quantized/distilroberta-base/masked-lm/config.json +26 -0
  9. quantized/distilroberta-base/masked-lm/merges.txt +0 -0
  10. quantized/distilroberta-base/masked-lm/model.onnx +3 -0
  11. quantized/distilroberta-base/masked-lm/special_tokens_map.json +15 -0
  12. quantized/distilroberta-base/masked-lm/tokenizer.json +0 -0
  13. quantized/distilroberta-base/masked-lm/tokenizer_config.json +16 -0
  14. quantized/distilroberta-base/masked-lm/vocab.json +0 -0
  15. quantized/roberta-base/default/config.json +26 -0
  16. quantized/roberta-base/default/merges.txt +0 -0
  17. quantized/roberta-base/default/model.onnx +3 -0
  18. quantized/roberta-base/default/special_tokens_map.json +15 -0
  19. quantized/roberta-base/default/tokenizer.json +0 -0
  20. quantized/roberta-base/default/tokenizer_config.json +16 -0
  21. quantized/roberta-base/default/vocab.json +0 -0
  22. quantized/roberta-base/masked-lm/config.json +26 -0
  23. quantized/roberta-base/masked-lm/merges.txt +0 -0
  24. quantized/roberta-base/masked-lm/model.onnx +3 -0
  25. quantized/roberta-base/masked-lm/special_tokens_map.json +15 -0
  26. quantized/roberta-base/masked-lm/tokenizer.json +0 -0
  27. quantized/roberta-base/masked-lm/tokenizer_config.json +16 -0
  28. quantized/roberta-base/masked-lm/vocab.json +0 -0
quantized/distilroberta-base/default/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilroberta-base",
3
+ "architectures": [
4
+ "RobertaForMaskedLM"
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": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 6,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "transformers_version": "4.26.1",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 50265
26
+ }
quantized/distilroberta-base/default/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
quantized/distilroberta-base/default/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d79a1ad465d9bb289715326493394ca517aeab583647280932390e159dbad48a
3
+ size 84515593
quantized/distilroberta-base/default/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
quantized/distilroberta-base/default/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
quantized/distilroberta-base/default/tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 512,
9
+ "name_or_path": "distilroberta-base",
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "special_tokens_map_file": null,
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
quantized/distilroberta-base/default/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
quantized/distilroberta-base/masked-lm/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilroberta-base",
3
+ "architectures": [
4
+ "RobertaForMaskedLM"
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": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 6,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "transformers_version": "4.26.1",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 50265
26
+ }
quantized/distilroberta-base/masked-lm/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
quantized/distilroberta-base/masked-lm/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03f71930ca3b51c9e1b374df71d552889a7a77cbe730897f44c97ca7baa080c1
3
+ size 121846897
quantized/distilroberta-base/masked-lm/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
quantized/distilroberta-base/masked-lm/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
quantized/distilroberta-base/masked-lm/tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 512,
9
+ "name_or_path": "distilroberta-base",
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "special_tokens_map_file": null,
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
quantized/distilroberta-base/masked-lm/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
quantized/roberta-base/default/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForMaskedLM"
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": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "transformers_version": "4.26.1",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 50265
26
+ }
quantized/roberta-base/default/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
quantized/roberta-base/default/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c838a903600318b230dd72746c9a005e8c589bd35dee5110778d445a0ab31073
3
+ size 127650664
quantized/roberta-base/default/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
quantized/roberta-base/default/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
quantized/roberta-base/default/tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 512,
9
+ "name_or_path": "roberta-base",
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "special_tokens_map_file": null,
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
quantized/roberta-base/default/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
quantized/roberta-base/masked-lm/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "RobertaForMaskedLM"
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": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "transformers_version": "4.26.1",
23
+ "type_vocab_size": 1,
24
+ "use_cache": true,
25
+ "vocab_size": 50265
26
+ }
quantized/roberta-base/masked-lm/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
quantized/roberta-base/masked-lm/model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77365b0d3a4dd3086a7ce3dd851ecbd379e1367475bedc5e90500780cdca7952
3
+ size 165009540
quantized/roberta-base/masked-lm/special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
quantized/roberta-base/masked-lm/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
quantized/roberta-base/masked-lm/tokenizer_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "errors": "replace",
7
+ "mask_token": "<mask>",
8
+ "model_max_length": 512,
9
+ "name_or_path": "roberta-base",
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "special_tokens_map_file": null,
13
+ "tokenizer_class": "RobertaTokenizer",
14
+ "trim_offsets": true,
15
+ "unk_token": "<unk>"
16
+ }
quantized/roberta-base/masked-lm/vocab.json ADDED
The diff for this file is too large to render. See raw diff