Upload folder using huggingface_hub
Browse files- config.json +23 -0
- onnx/model.onnx +3 -0
- onnx/model_quantized.onnx +3 -0
- quantize_config.json +41 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +22 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "flax-sentence-embeddings/all_datasets_v3_mpnet-base",
|
3 |
+
"architectures": [
|
4 |
+
"MPNetForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
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-05,
|
15 |
+
"max_position_embeddings": 514,
|
16 |
+
"model_type": "mpnet",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 12,
|
19 |
+
"pad_token_id": 1,
|
20 |
+
"relative_attention_num_buckets": 32,
|
21 |
+
"transformers_version": "4.33.2",
|
22 |
+
"vocab_size": 30527
|
23 |
+
}
|
onnx/model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ead811bdfefeef4372cdc226e9539a6b74a05f65a767e3046f75624c9302014
|
3 |
+
size 435826547
|
onnx/model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d764e1e665269233fdf516a3350813ea22efe84523ce8b4dde3eac3297765d92
|
3 |
+
size 110086121
|
quantize_config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"per_channel": true,
|
3 |
+
"reduce_range": true,
|
4 |
+
"per_model_config": {
|
5 |
+
"model": {
|
6 |
+
"op_types": [
|
7 |
+
"Softmax",
|
8 |
+
"Log",
|
9 |
+
"Sub",
|
10 |
+
"Constant",
|
11 |
+
"Not",
|
12 |
+
"ConstantOfShape",
|
13 |
+
"Cast",
|
14 |
+
"CumSum",
|
15 |
+
"Range",
|
16 |
+
"Less",
|
17 |
+
"Abs",
|
18 |
+
"Add",
|
19 |
+
"Min",
|
20 |
+
"Gather",
|
21 |
+
"Pow",
|
22 |
+
"Where",
|
23 |
+
"Transpose",
|
24 |
+
"Div",
|
25 |
+
"Expand",
|
26 |
+
"ReduceMean",
|
27 |
+
"MatMul",
|
28 |
+
"Erf",
|
29 |
+
"Reshape",
|
30 |
+
"Mul",
|
31 |
+
"Neg",
|
32 |
+
"Shape",
|
33 |
+
"Sqrt",
|
34 |
+
"Concat",
|
35 |
+
"Equal",
|
36 |
+
"Unsqueeze"
|
37 |
+
],
|
38 |
+
"weight_type": "QInt8"
|
39 |
+
}
|
40 |
+
}
|
41 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "[UNK]"
|
15 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
+
"cls_token": "<s>",
|
5 |
+
"do_lower_case": true,
|
6 |
+
"eos_token": "</s>",
|
7 |
+
"mask_token": "<mask>",
|
8 |
+
"max_length": 128,
|
9 |
+
"model_max_length": 512,
|
10 |
+
"pad_to_multiple_of": null,
|
11 |
+
"pad_token": "<pad>",
|
12 |
+
"pad_token_type_id": 0,
|
13 |
+
"padding_side": "right",
|
14 |
+
"sep_token": "</s>",
|
15 |
+
"stride": 0,
|
16 |
+
"strip_accents": null,
|
17 |
+
"tokenize_chinese_chars": true,
|
18 |
+
"tokenizer_class": "MPNetTokenizer",
|
19 |
+
"truncation_side": "right",
|
20 |
+
"truncation_strategy": "longest_first",
|
21 |
+
"unk_token": "[UNK]"
|
22 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|