xinhe commited on
Commit
0764f41
1 Parent(s): d25bbaa

asym kl 2 fallback

Browse files
config.json CHANGED
@@ -1,36 +1,35 @@
1
  {
2
- "_name_or_path": "Intel/bert-base-uncased-mrpc",
3
  "architectures": [
4
- "BertForSequenceClassification"
5
  ],
6
- "attention_probs_dropout_prob": 0.1,
7
- "classifier_dropout": null,
8
- "finetuning_task": "mrpc",
9
- "gradient_checkpointing": false,
10
- "hidden_act": "gelu",
11
- "hidden_dropout_prob": 0.1,
 
 
 
 
12
  "hidden_size": 768,
13
- "id2label": {
14
- "0": 0,
15
- "1": 1
16
- },
17
  "initializer_range": 0.02,
 
18
  "intermediate_size": 3072,
19
- "label2id": {
20
- "0": 0,
21
- "1": 1
22
- },
23
  "layer_norm_eps": 1e-12,
24
  "max_position_embeddings": 512,
25
- "model_type": "bert",
 
26
  "num_attention_heads": 12,
 
27
  "num_hidden_layers": 12,
 
28
  "pad_token_id": 0,
29
  "position_embedding_type": "absolute",
30
  "problem_type": "single_label_classification",
31
- "torch_dtype": "float32",
32
  "transformers_version": "4.18.0",
33
  "type_vocab_size": 2,
34
- "use_cache": true,
35
- "vocab_size": 30522
36
  }
1
  {
2
+ "_name_or_path": "Alireza1044/albert-base-v2-sst2",
3
  "architectures": [
4
+ "AlbertForSequenceClassification"
5
  ],
6
+ "attention_probs_dropout_prob": 0,
7
+ "bos_token_id": 2,
8
+ "classifier_dropout_prob": 0.1,
9
+ "down_scale_factor": 1,
10
+ "embedding_size": 128,
11
+ "eos_token_id": 3,
12
+ "finetuning_task": "sst2",
13
+ "gap_size": 0,
14
+ "hidden_act": "gelu_new",
15
+ "hidden_dropout_prob": 0,
16
  "hidden_size": 768,
 
 
 
 
17
  "initializer_range": 0.02,
18
+ "inner_group_num": 1,
19
  "intermediate_size": 3072,
 
 
 
 
20
  "layer_norm_eps": 1e-12,
21
  "max_position_embeddings": 512,
22
+ "model_type": "albert",
23
+ "net_structure_type": 0,
24
  "num_attention_heads": 12,
25
+ "num_hidden_groups": 1,
26
  "num_hidden_layers": 12,
27
+ "num_memory_blocks": 0,
28
  "pad_token_id": 0,
29
  "position_embedding_type": "absolute",
30
  "problem_type": "single_label_classification",
31
+ "torch_dtype": "int8",
32
  "transformers_version": "4.18.0",
33
  "type_vocab_size": 2,
34
+ "vocab_size": 30000
 
35
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e4730f4d5dae798ea97c3831fb54c53e13c5ab93369b7a0e4acf144f2ecba2b
3
- size 438003309
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71529305e5145361f466d12f8bbb8b642d16cc1fe37df959c12dc560b0ea7571
3
+ size 26233409
special_tokens_map.json CHANGED
@@ -1 +1 @@
1
- {"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
1
+ {"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
tokenizer_config.json CHANGED
@@ -1 +1 @@
1
- {"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "Intel/bert-base-uncased-mrpc", "tokenizer_class": "BertTokenizer"}
1
+ {"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "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": "Alireza1044/albert-base-v2-sst2", "tokenizer_class": "AlbertTokenizer"}