Hugging Face's logo

grammarly
/
brain_query_to_pack_classifier

Safetensors
roberta
Model card Files
xet
Community
ke-lly-d commited on
Commit
de51a6b
·
1 Parent(s): 42d6781

roberta model

Browse files
Files changed (10) hide show
  1. __pycache__/handler.cpython-311.pyc +0 -0
  2. added_tokens.json +0 -3
  3. config.json +12 -21
  4. merges.txt +0 -0
  5. model.safetensors +2 -2
  6. special_tokens_map.json +11 -11
  7. spm.model +0 -3
  8. tokenizer.json +0 -0
  9. tokenizer_config.json +22 -23
  10. vocab.json +0 -0
__pycache__/handler.cpython-311.pyc ADDED
Binary file (3.31 kB). View file
 
added_tokens.json DELETED
@@ -1,3 +0,0 @@
1
- {
2
- "[MASK]": 128000
3
- }
 
 
 
 
config.json CHANGED
@@ -1,8 +1,11 @@
1
  {
2
  "architectures": [
3
- "DebertaV2ForSequenceClassification"
4
  ],
5
  "attention_probs_dropout_prob": 0.1,
 
 
 
6
  "hidden_act": "gelu",
7
  "hidden_dropout_prob": 0.1,
8
  "hidden_size": 768,
@@ -32,28 +35,16 @@
32
  "Miro": 8,
33
  "Slack": 9
34
  },
35
- "layer_norm_eps": 1e-07,
36
- "legacy": true,
37
- "max_position_embeddings": 512,
38
- "max_relative_positions": -1,
39
- "model_type": "deberta-v2",
40
- "norm_rel_ebd": "layer_norm",
41
  "num_attention_heads": 12,
42
  "num_hidden_layers": 12,
43
- "pad_token_id": 0,
44
- "pooler_dropout": 0,
45
- "pooler_hidden_act": "gelu",
46
- "pooler_hidden_size": 768,
47
- "pos_att_type": [
48
- "p2c",
49
- "c2p"
50
- ],
51
- "position_biased_input": false,
52
- "position_buckets": 256,
53
- "relative_attention": true,
54
- "share_att_key": true,
55
  "torch_dtype": "float32",
56
  "transformers_version": "4.52.4",
57
- "type_vocab_size": 0,
58
- "vocab_size": 128100
 
59
  }
 
1
  {
2
  "architectures": [
3
+ "RobertaForSequenceClassification"
4
  ],
5
  "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
11
  "hidden_size": 768,
 
35
  "Miro": 8,
36
  "Slack": 9
37
  },
38
+ "layer_norm_eps": 1e-05,
39
+ "max_position_embeddings": 514,
40
+ "model_type": "roberta",
 
 
 
41
  "num_attention_heads": 12,
42
  "num_hidden_layers": 12,
43
+ "pad_token_id": 1,
44
+ "position_embedding_type": "absolute",
 
 
 
 
 
 
 
 
 
 
45
  "torch_dtype": "float32",
46
  "transformers_version": "4.52.4",
47
+ "type_vocab_size": 1,
48
+ "use_cache": true,
49
+ "vocab_size": 50265
50
  }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f3ddb6c153ef500272ae7f39aee9d273f7a38aa988bce18752968f4e5e99de0
3
- size 737743888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbdde46f89932b681324e60721f9f1db7835df78d7b9fb22e3474d7265966d12
3
+ size 498637432
special_tokens_map.json CHANGED
@@ -1,15 +1,15 @@
1
  {
2
- "bos_token": "[CLS]",
3
- "cls_token": "[CLS]",
4
- "eos_token": "[SEP]",
5
- "mask_token": "[MASK]",
6
- "pad_token": "[PAD]",
7
- "sep_token": "[SEP]",
8
- "unk_token": {
9
- "content": "[UNK]",
10
- "lstrip": false,
11
- "normalized": true,
12
  "rstrip": false,
13
  "single_word": false
14
- }
 
 
 
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
  }
spm.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
- size 2464616
 
 
 
 
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,59 +1,58 @@
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
  "1": {
12
- "content": "[CLS]",
13
  "lstrip": false,
14
- "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
  "2": {
20
- "content": "[SEP]",
21
  "lstrip": false,
22
- "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
  "3": {
28
- "content": "[UNK]",
29
  "lstrip": false,
30
  "normalized": true,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
- "128000": {
36
- "content": "[MASK]",
37
- "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
  }
43
  },
44
- "bos_token": "[CLS]",
45
  "clean_up_tokenization_spaces": false,
46
- "cls_token": "[CLS]",
47
- "do_lower_case": false,
48
- "eos_token": "[SEP]",
49
  "extra_special_tokens": {},
50
- "mask_token": "[MASK]",
51
- "model_max_length": 1000000000000000019884624838656,
52
- "pad_token": "[PAD]",
53
- "sep_token": "[SEP]",
54
- "sp_model_kwargs": {},
55
- "split_by_punct": false,
56
- "tokenizer_class": "DebertaV2Tokenizer",
57
- "unk_token": "[UNK]",
58
- "vocab_type": "spm"
59
  }
 
1
  {
2
+ "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
5
+ "content": "<s>",
6
  "lstrip": false,
7
+ "normalized": true,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
  "1": {
13
+ "content": "<pad>",
14
  "lstrip": false,
15
+ "normalized": true,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
  },
20
  "2": {
21
+ "content": "</s>",
22
  "lstrip": false,
23
+ "normalized": true,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
27
  },
28
  "3": {
29
+ "content": "<unk>",
30
  "lstrip": false,
31
  "normalized": true,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
+ "50264": {
37
+ "content": "<mask>",
38
+ "lstrip": true,
39
  "normalized": false,
40
  "rstrip": false,
41
  "single_word": false,
42
  "special": true
43
  }
44
  },
45
+ "bos_token": "<s>",
46
  "clean_up_tokenization_spaces": false,
47
+ "cls_token": "<s>",
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
  "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 512,
53
+ "pad_token": "<pad>",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
 
 
58
  }
vocab.json ADDED
The diff for this file is too large to render. See raw diff