petricevich commited on
Commit
6e0e475
1 Parent(s): 83a17b1

Upload folder using huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +8 -12
config.json CHANGED
@@ -1,19 +1,17 @@
1
  {
2
- "_name_or_path": "Alibaba-NLP/gte-large-en-v1.5",
3
  "architectures": [
4
  "NewModel"
5
  ],
6
  "attention_probs_dropout_prob": 0.0,
7
  "auto_map": {
8
- "AutoConfig": "Alibaba-NLP/new-impl--configuration.NewConfig",
9
- "AutoModel": "Alibaba-NLP/new-impl--modeling.NewModel",
10
- "AutoModelForMaskedLM": "Alibaba-NLP/new-impl--modeling.NewForMaskedLM",
11
- "AutoModelForMultipleChoice": "Alibaba-NLP/new-impl--modeling.NewForMultipleChoice",
12
- "AutoModelForQuestionAnswering": "Alibaba-NLP/new-impl--modeling.NewForQuestionAnswering",
13
- "AutoModelForSequenceClassification": "Alibaba-NLP/new-impl--modeling.NewForSequenceClassification",
14
- "AutoModelForTokenClassification": "Alibaba-NLP/new-impl--modeling.NewForTokenClassification"
15
  },
16
- "classifier_dropout": null,
17
  "hidden_act": "gelu",
18
  "hidden_dropout_prob": 0.1,
19
  "hidden_size": 1024,
@@ -21,8 +19,6 @@
21
  "intermediate_size": 4096,
22
  "layer_norm_eps": 1e-12,
23
  "layer_norm_type": "layer_norm",
24
- "logn_attention_clip1": false,
25
- "logn_attention_scale": false,
26
  "max_position_embeddings": 8192,
27
  "model_type": "new",
28
  "num_attention_heads": 16,
@@ -36,7 +32,7 @@
36
  },
37
  "rope_theta": 160000,
38
  "torch_dtype": "float32",
39
- "transformers_version": "4.44.2",
40
  "type_vocab_size": 2,
41
  "unpad_inputs": false,
42
  "use_memory_efficient_attention": false,
 
1
  {
 
2
  "architectures": [
3
  "NewModel"
4
  ],
5
  "attention_probs_dropout_prob": 0.0,
6
  "auto_map": {
7
+ "AutoConfig": "configuration.NewConfig",
8
+ "AutoModel": "modeling.NewModel",
9
+ "AutoModelForMaskedLM": "modeling.NewForMaskedLM",
10
+ "AutoModelForMultipleChoice": "modeling.NewForMultipleChoice",
11
+ "AutoModelForQuestionAnswering": "modeling.NewForQuestionAnswering",
12
+ "AutoModelForSequenceClassification": "modeling.NewForSequenceClassification",
13
+ "AutoModelForTokenClassification": "modeling.NewForTokenClassification"
14
  },
 
15
  "hidden_act": "gelu",
16
  "hidden_dropout_prob": 0.1,
17
  "hidden_size": 1024,
 
19
  "intermediate_size": 4096,
20
  "layer_norm_eps": 1e-12,
21
  "layer_norm_type": "layer_norm",
 
 
22
  "max_position_embeddings": 8192,
23
  "model_type": "new",
24
  "num_attention_heads": 16,
 
32
  },
33
  "rope_theta": 160000,
34
  "torch_dtype": "float32",
35
+ "transformers_version": "4.39.1",
36
  "type_vocab_size": 2,
37
  "unpad_inputs": false,
38
  "use_memory_efficient_attention": false,