Andrija commited on
Commit
eb4da0b
1 Parent(s): ee8a470

Update to v3 base model

Browse files
Files changed (7) hide show
  1. config.json +26 -26
  2. merges.txt +0 -0
  3. pytorch_model.bin +2 -2
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +1 -1
  6. training_args.bin +1 -1
  7. vocab.json +0 -0
config.json CHANGED
@@ -11,43 +11,43 @@
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
13
  "id2label": {
14
- "0": "I-org",
15
- "1": "B-misc",
16
- "2": "B-per",
17
- "3": "B-deriv-per",
18
- "4": "B-org",
19
- "5": "B-loc",
20
- "6": "I-deriv-per",
21
- "7": "I-misc",
22
- "8": "I-loc",
23
- "9": "I-per",
24
- "10": "O"
25
  },
26
  "initializer_range": 0.02,
27
  "intermediate_size": 3072,
28
  "label2id": {
29
- "I-org": 0,
30
- "B-misc": 1,
31
- "O": 10,
32
- "B-per": 2,
33
- "B-deriv-per": 3,
34
- "B-org": 4,
35
- "B-loc": 5,
36
- "I-deriv-per": 6,
37
- "I-misc": 7,
38
- "I-loc": 8,
39
- "I-per": 9
40
  },
41
- "layer_norm_eps": 1e-05,
42
  "max_position_embeddings": 514,
43
  "model_type": "roberta",
44
  "num_attention_heads": 12,
45
- "num_hidden_layers": 12,
46
  "pad_token_id": 1,
47
  "position_embedding_type": "absolute",
48
  "torch_dtype": "float32",
49
- "transformers_version": "4.9.1",
50
  "type_vocab_size": 1,
51
  "use_cache": true,
52
- "vocab_size": 50265
53
  }
 
11
  "hidden_dropout_prob": 0.1,
12
  "hidden_size": 768,
13
  "id2label": {
14
+ "0": "LABEL_0",
15
+ "1": "LABEL_1",
16
+ "2": "LABEL_2",
17
+ "3": "LABEL_3",
18
+ "4": "LABEL_4",
19
+ "5": "LABEL_5",
20
+ "6": "LABEL_6",
21
+ "7": "LABEL_7",
22
+ "8": "LABEL_8",
23
+ "9": "LABEL_9",
24
+ "10": "LABEL_10"
25
  },
26
  "initializer_range": 0.02,
27
  "intermediate_size": 3072,
28
  "label2id": {
29
+ "LABEL_0": 0,
30
+ "LABEL_1": 1,
31
+ "LABEL_10": 10,
32
+ "LABEL_2": 2,
33
+ "LABEL_3": 3,
34
+ "LABEL_4": 4,
35
+ "LABEL_5": 5,
36
+ "LABEL_6": 6,
37
+ "LABEL_7": 7,
38
+ "LABEL_8": 8,
39
+ "LABEL_9": 9
40
  },
41
+ "layer_norm_eps": 1e-12,
42
  "max_position_embeddings": 514,
43
  "model_type": "roberta",
44
  "num_attention_heads": 12,
45
+ "num_hidden_layers": 6,
46
  "pad_token_id": 1,
47
  "position_embedding_type": "absolute",
48
  "torch_dtype": "float32",
49
+ "transformers_version": "4.9.2",
50
  "type_vocab_size": 1,
51
  "use_cache": true,
52
+ "vocab_size": 48000
53
  }
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8d207bddf7078c7b66afd0f25fbbe7632654c98f189a2728588eb7200a4e8ff
3
- size 496338673
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fa8c4c7d8d3144728c9d78b41aaa637b23fe45e8042e30220bdc885168e59e6
3
+ size 319232369
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": true, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 514, "special_tokens_map_file": null, "name_or_path": "Andrija/SRoBERTaFastBPE-2", "tokenizer_class": "RobertaTokenizer"}
 
1
+ {"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": true, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "Andrija/SRoBERTa-base", "tokenizer_class": "RobertaTokenizer"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df794c7f4998edb501b243e95afb20a6a5bcde4e7916c890eec7d3859bb74839
3
  size 2607
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee521c993c63d39d5a1b1b9fdcd29fcf7e34dea1756bea7060792e4fd9daad0d
3
  size 2607
vocab.json CHANGED
The diff for this file is too large to render. See raw diff