Hugging Face's logo

smeintadmin
/
image_intents

Text Classification
Transformers
PyTorch
TensorBoard
Safetensors
English
roberta
text-embeddings-inference
Model card Files
xet
 Metrics Community
2
smeintadmin commited on
Commit
e1f66c5
·
1 Parent(s): 0cfa69a

Upload 9 files

Browse files
Files changed (8) hide show
  1. config.json +14 -13
  2. merges.txt +0 -0
  3. pytorch_model.bin +2 -2
  4. special_tokens_map.json +13 -5
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +11 -9
  7. training_args.bin +1 -1
  8. vocab.json +0 -0
config.json CHANGED
@@ -1,27 +1,28 @@
1
  {
2
- "_name_or_path": "bert-base-uncased",
3
  "architectures": [
4
- "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
 
7
  "classifier_dropout": null,
8
- "gradient_checkpointing": false,
9
  "hidden_act": "gelu",
10
  "hidden_dropout_prob": 0.1,
11
- "hidden_size": 768,
12
  "initializer_range": 0.02,
13
- "intermediate_size": 3072,
14
- "layer_norm_eps": 1e-12,
15
- "max_position_embeddings": 512,
16
- "model_type": "bert",
17
- "num_attention_heads": 12,
18
- "num_hidden_layers": 12,
19
- "pad_token_id": 0,
20
  "position_embedding_type": "absolute",
21
  "problem_type": "single_label_classification",
22
  "torch_dtype": "float32",
23
  "transformers_version": "4.31.0",
24
- "type_vocab_size": 2,
25
  "use_cache": true,
26
- "vocab_size": 30522
27
  }
 
1
  {
2
+ "_name_or_path": "roberta-large",
3
  "architectures": [
4
+ "RobertaForSequenceClassification"
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": 1024,
13
  "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 514,
17
+ "model_type": "roberta",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
20
+ "pad_token_id": 1,
21
  "position_embedding_type": "absolute",
22
  "problem_type": "single_label_classification",
23
  "torch_dtype": "float32",
24
  "transformers_version": "4.31.0",
25
+ "type_vocab_size": 1,
26
  "use_cache": true,
27
+ "vocab_size": 50265
28
  }
merges.txt ADDED
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 sha256:333b4012abb87dd6e0fa5cc4e6bb730d0ac61490e13b7be42258c11f1e09b064
3
- size 438003505
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e43cd6f658ac5d4d453169fc5e4509588c3acc013b48492521709449c0b77a7f
3
+ size 1421582769
special_tokens_map.json CHANGED
@@ -1,7 +1,15 @@
1
  {
2
- "cls_token": "[CLS]",
3
- "mask_token": "[MASK]",
4
- "pad_token": "[PAD]",
5
- "sep_token": "[SEP]",
6
- "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
7
  }
 
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
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,13 +1,15 @@
1
  {
 
 
2
  "clean_up_tokenization_spaces": true,
3
- "cls_token": "[CLS]",
4
- "do_lower_case": true,
5
- "mask_token": "[MASK]",
 
6
  "model_max_length": 512,
7
- "pad_token": "[PAD]",
8
- "sep_token": "[SEP]",
9
- "strip_accents": null,
10
- "tokenize_chinese_chars": true,
11
- "tokenizer_class": "BertTokenizer",
12
- "unk_token": "[UNK]"
13
  }
 
1
  {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
  "clean_up_tokenization_spaces": true,
5
+ "cls_token": "<s>",
6
+ "eos_token": "</s>",
7
+ "errors": "replace",
8
+ "mask_token": "<mask>",
9
  "model_max_length": 512,
10
+ "pad_token": "<pad>",
11
+ "sep_token": "</s>",
12
+ "tokenizer_class": "RobertaTokenizer",
13
+ "trim_offsets": true,
14
+ "unk_token": "<unk>"
 
15
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a88d363e6020b0f369c0067fd822896878b89d05d12713e219273a0289e2a12b
3
  size 3899
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53cdb1246db55b9fb55de790b904e4a5072317b091b5a8c8f700888f99c43ee9
3
  size 3899
vocab.json ADDED
The diff for this file is too large to render. See raw diff