Hugging Face's logo

optimum
/
bge-base-en-v1.5-neuronx

Feature Extraction
Transformers
bert
text-embeddings-inference
Model card Files Community
Jingya HF Staff commited on
Commit
f2c9bff
·
verified ·
1 Parent(s): ba8d572

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +17 -12
config.json CHANGED
@@ -1,19 +1,21 @@
1
  {
2
- "_name_or_path": "/home/ubuntu/.cache/torch/sentence_transformers/BAAI_bge-base-en-v1.5/",
 
3
  "architectures": [
4
  "BertModel"
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
  "id2label": {
13
  "0": "LABEL_0"
14
  },
15
  "initializer_range": 0.02,
16
- "intermediate_size": 3072,
17
  "label2id": {
18
  "LABEL_0": 0
19
  },
@@ -21,16 +23,19 @@
21
  "max_position_embeddings": 512,
22
  "model_type": "bert",
23
  "neuron": {
24
- "auto_cast": null,
25
- "auto_cast_type": null,
26
  "compiler_type": "neuronx-cc",
27
- "compiler_version": "2.12.54.0+f631c2365",
 
 
28
  "dynamic_batch_size": false,
 
29
  "input_names": [
30
  "input_ids",
31
  "attention_mask"
32
  ],
33
- "model_type": "sentence-transformers-transformer",
34
  "optlevel": "2",
35
  "output_attentions": false,
36
  "output_hidden_states": false,
@@ -39,17 +44,17 @@
39
  "sentence_embedding"
40
  ],
41
  "static_batch_size": 1,
42
- "static_num_beams": 1,
43
- "static_sequence_length": 384
44
  },
45
- "num_attention_heads": 12,
46
- "num_hidden_layers": 12,
47
  "pad_token_id": 0,
48
  "position_embedding_type": "absolute",
49
  "task": "feature-extraction",
50
  "torch_dtype": "float32",
51
  "torchscript": true,
52
- "transformers_version": "4.36.2",
53
  "type_vocab_size": 2,
54
  "use_cache": true,
55
  "vocab_size": 30522
 
1
  {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "/tmp/tmp55lzbkct",
4
  "architectures": [
5
  "BertModel"
6
  ],
7
  "attention_probs_dropout_prob": 0.1,
8
  "classifier_dropout": null,
9
+ "export_model_type": "transformer",
10
  "gradient_checkpointing": false,
11
  "hidden_act": "gelu",
12
  "hidden_dropout_prob": 0.1,
13
+ "hidden_size": 1024,
14
  "id2label": {
15
  "0": "LABEL_0"
16
  },
17
  "initializer_range": 0.02,
18
+ "intermediate_size": 4096,
19
  "label2id": {
20
  "LABEL_0": 0
21
  },
 
23
  "max_position_embeddings": 512,
24
  "model_type": "bert",
25
  "neuron": {
26
+ "auto_cast": "matmul",
27
+ "auto_cast_type": "bf16",
28
  "compiler_type": "neuronx-cc",
29
+ "compiler_version": "2.16.372.0+4a9b2326",
30
+ "disable_fallback": false,
31
+ "disable_fast_relayout": false,
32
  "dynamic_batch_size": false,
33
+ "inline_weights_to_neff": true,
34
  "input_names": [
35
  "input_ids",
36
  "attention_mask"
37
  ],
38
+ "model_type": "transformer",
39
  "optlevel": "2",
40
  "output_attentions": false,
41
  "output_hidden_states": false,
 
44
  "sentence_embedding"
45
  ],
46
  "static_batch_size": 1,
47
+ "static_sequence_length": 384,
48
+ "tensor_parallel_size": 1
49
  },
50
+ "num_attention_heads": 16,
51
+ "num_hidden_layers": 24,
52
  "pad_token_id": 0,
53
  "position_embedding_type": "absolute",
54
  "task": "feature-extraction",
55
  "torch_dtype": "float32",
56
  "torchscript": true,
57
+ "transformers_version": "4.49.0",
58
  "type_vocab_size": 2,
59
  "use_cache": true,
60
  "vocab_size": 30522