kais-radwan
commited on
Commit
•
7070d93
1
Parent(s):
bf3eccc
Upload 8 files
Browse files- README.md +1 -3
- config.json +26 -0
- model.onnx +3 -0
- ort_config.json +39 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +62 -0
- vocab.txt +0 -0
README.md
CHANGED
@@ -1,3 +1 @@
|
|
1 |
-
|
2 |
-
license: mit
|
3 |
-
---
|
|
|
1 |
+
This is a fork from https://huggingface.co/thenlper/gte-base that was optimized using Optimum and ONNX for better performance.
|
|
|
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "onnx",
|
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 |
+
"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 |
+
"torch_dtype": "float16",
|
22 |
+
"transformers_version": "4.38.1",
|
23 |
+
"type_vocab_size": 2,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 30522
|
26 |
+
}
|
model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55409d4a76f6e3c21c556bfe18245d8bf19da7d4ad5973fc8fc931aee4f373d1
|
3 |
+
size 435601576
|
ort_config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"one_external_file": true,
|
3 |
+
"opset": null,
|
4 |
+
"optimization": {
|
5 |
+
"disable_attention": null,
|
6 |
+
"disable_attention_fusion": false,
|
7 |
+
"disable_bias_gelu": null,
|
8 |
+
"disable_bias_gelu_fusion": false,
|
9 |
+
"disable_bias_skip_layer_norm": null,
|
10 |
+
"disable_bias_skip_layer_norm_fusion": false,
|
11 |
+
"disable_embed_layer_norm": true,
|
12 |
+
"disable_embed_layer_norm_fusion": true,
|
13 |
+
"disable_gelu": null,
|
14 |
+
"disable_gelu_fusion": false,
|
15 |
+
"disable_group_norm_fusion": true,
|
16 |
+
"disable_layer_norm": null,
|
17 |
+
"disable_layer_norm_fusion": false,
|
18 |
+
"disable_packed_kv": true,
|
19 |
+
"disable_rotary_embeddings": false,
|
20 |
+
"disable_shape_inference": false,
|
21 |
+
"disable_skip_layer_norm": null,
|
22 |
+
"disable_skip_layer_norm_fusion": false,
|
23 |
+
"enable_gelu_approximation": false,
|
24 |
+
"enable_gemm_fast_gelu_fusion": false,
|
25 |
+
"enable_transformers_specific_optimizations": true,
|
26 |
+
"fp16": false,
|
27 |
+
"no_attention_mask": false,
|
28 |
+
"optimization_level": 99,
|
29 |
+
"optimize_for_gpu": false,
|
30 |
+
"optimize_with_onnxruntime_only": null,
|
31 |
+
"use_mask_index": false,
|
32 |
+
"use_multi_head_attention": false,
|
33 |
+
"use_raw_attention_mask": false
|
34 |
+
},
|
35 |
+
"optimum_version": "1.17.1",
|
36 |
+
"quantization": {},
|
37 |
+
"transformers_version": "4.38.1",
|
38 |
+
"use_external_data_format": false
|
39 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"max_length": 128,
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_to_multiple_of": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"pad_token_type_id": 0,
|
53 |
+
"padding_side": "right",
|
54 |
+
"sep_token": "[SEP]",
|
55 |
+
"stride": 0,
|
56 |
+
"strip_accents": null,
|
57 |
+
"tokenize_chinese_chars": true,
|
58 |
+
"tokenizer_class": "BertTokenizer",
|
59 |
+
"truncation_side": "right",
|
60 |
+
"truncation_strategy": "longest_first",
|
61 |
+
"unk_token": "[UNK]"
|
62 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|