Upload folder using huggingface_hub
Browse files- config.json +25 -0
- merges.txt +0 -0
- onnx/model.onnx +3 -0
- onnx/model_quantized.onnx +3 -0
- quantize_config.json +30 -0
- special_tokens_map.json +8 -0
- tokenizer.json +0 -0
- tokenizer_config.json +15 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "allegro/herbert-base-cased",
|
3 |
+
"architectures": [
|
4 |
+
"BertModel"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 3072,
|
13 |
+
"layer_norm_eps": 1e-12,
|
14 |
+
"max_position_embeddings": 514,
|
15 |
+
"model_type": "bert",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 12,
|
18 |
+
"pad_token_id": 1,
|
19 |
+
"position_embedding_type": "absolute",
|
20 |
+
"tokenizer_class": "HerbertTokenizerFast",
|
21 |
+
"transformers_version": "4.34.0.dev0",
|
22 |
+
"type_vocab_size": 2,
|
23 |
+
"use_cache": true,
|
24 |
+
"vocab_size": 50000
|
25 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
onnx/model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8cbd010bb7be0ef757b122d8045c5d4b85e1e47126563c9793a4dcc93d9be577
|
3 |
+
size 495654115
|
onnx/model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:316bef6e461df875d2df460f23c65b2f4d24598800a00750e88ada0e9fbe6749
|
3 |
+
size 125043994
|
quantize_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"per_channel": true,
|
3 |
+
"reduce_range": true,
|
4 |
+
"per_model_config": {
|
5 |
+
"model": {
|
6 |
+
"op_types": [
|
7 |
+
"Softmax",
|
8 |
+
"Sub",
|
9 |
+
"Shape",
|
10 |
+
"Mul",
|
11 |
+
"Slice",
|
12 |
+
"Unsqueeze",
|
13 |
+
"Transpose",
|
14 |
+
"Div",
|
15 |
+
"Gather",
|
16 |
+
"Concat",
|
17 |
+
"Erf",
|
18 |
+
"Add",
|
19 |
+
"Cast",
|
20 |
+
"Pow",
|
21 |
+
"ReduceMean",
|
22 |
+
"Reshape",
|
23 |
+
"MatMul",
|
24 |
+
"Constant",
|
25 |
+
"Sqrt"
|
26 |
+
],
|
27 |
+
"weight_type": "QInt8"
|
28 |
+
}
|
29 |
+
}
|
30 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"mask_token": "<mask>",
|
5 |
+
"pad_token": "<pad>",
|
6 |
+
"sep_token": "</s>",
|
7 |
+
"unk_token": "<unk>"
|
8 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [],
|
3 |
+
"bos_token": "<s>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"cls_token": "<s>",
|
6 |
+
"do_lowercase_and_remove_accent": false,
|
7 |
+
"id2lang": null,
|
8 |
+
"lang2id": null,
|
9 |
+
"mask_token": "<mask>",
|
10 |
+
"model_max_length": 512,
|
11 |
+
"pad_token": "<pad>",
|
12 |
+
"sep_token": "</s>",
|
13 |
+
"tokenizer_class": "HerbertTokenizer",
|
14 |
+
"unk_token": "<unk>"
|
15 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|