npvinHnivqn
commited on
Commit
•
c1d2d68
1
Parent(s):
56916e8
Upload model
Browse files- config.json +31 -12
- model.safetensors +2 -2
config.json
CHANGED
@@ -1,25 +1,44 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"attention_probs_dropout_prob": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
"classifier_dropout": null,
|
8 |
"hidden_act": "gelu",
|
9 |
"hidden_dropout_prob": 0.1,
|
10 |
-
"hidden_size":
|
11 |
"initializer_range": 0.02,
|
12 |
-
"intermediate_size":
|
13 |
"layer_norm_eps": 1e-12,
|
14 |
-
"
|
15 |
-
"
|
|
|
|
|
|
|
16 |
"num_attention_heads": 12,
|
17 |
-
"num_hidden_layers":
|
|
|
18 |
"pad_token_id": 0,
|
19 |
-
"position_embedding_type": "
|
|
|
|
|
|
|
|
|
|
|
20 |
"torch_dtype": "float32",
|
21 |
"transformers_version": "4.41.1",
|
22 |
-
"type_vocab_size":
|
23 |
-
"
|
24 |
-
"
|
|
|
25 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "Alibaba-NLP/gte-base-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": 768,
|
20 |
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 3072,
|
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": 12,
|
29 |
+
"num_hidden_layers": 12,
|
30 |
+
"pack_qkv": true,
|
31 |
"pad_token_id": 0,
|
32 |
+
"position_embedding_type": "rope",
|
33 |
+
"rope_scaling": {
|
34 |
+
"factor": 2.0,
|
35 |
+
"type": "ntk"
|
36 |
+
},
|
37 |
+
"rope_theta": 500000,
|
38 |
"torch_dtype": "float32",
|
39 |
"transformers_version": "4.41.1",
|
40 |
+
"type_vocab_size": 0,
|
41 |
+
"unpad_inputs": false,
|
42 |
+
"use_memory_efficient_attention": false,
|
43 |
+
"vocab_size": 30528
|
44 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c30d96b914af1a141db13075863e666dee17daa5f844d506e07c88cd9ab12d2b
|
3 |
+
size 547119128
|