Upload folder using huggingface_hub
Browse files- config.json +76 -0
- generation_config.json +16 -0
- merges.txt +0 -0
- onnx/decoder_model.onnx +3 -0
- onnx/decoder_model_merged.onnx +3 -0
- onnx/decoder_model_merged_quantized.onnx +3 -0
- onnx/decoder_model_quantized.onnx +3 -0
- onnx/decoder_with_past_model.onnx +3 -0
- onnx/decoder_with_past_model_quantized.onnx +3 -0
- onnx/encoder_model.onnx +3 -0
- onnx/encoder_model_quantized.onnx +3 -0
- quantize_config.json +125 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +64 -0
- vocab.json +0 -0
config.json
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "sshleifer/distilbart-cnn-12-6",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "gelu",
|
6 |
+
"add_bias_logits": false,
|
7 |
+
"add_final_layer_norm": false,
|
8 |
+
"architectures": [
|
9 |
+
"BartForConditionalGeneration"
|
10 |
+
],
|
11 |
+
"attention_dropout": 0.0,
|
12 |
+
"bos_token_id": 0,
|
13 |
+
"classif_dropout": 0.0,
|
14 |
+
"classifier_dropout": 0.0,
|
15 |
+
"d_model": 1024,
|
16 |
+
"decoder_attention_heads": 16,
|
17 |
+
"decoder_ffn_dim": 4096,
|
18 |
+
"decoder_layerdrop": 0.0,
|
19 |
+
"decoder_layers": 6,
|
20 |
+
"decoder_start_token_id": 2,
|
21 |
+
"dropout": 0.1,
|
22 |
+
"early_stopping": true,
|
23 |
+
"encoder_attention_heads": 16,
|
24 |
+
"encoder_ffn_dim": 4096,
|
25 |
+
"encoder_layerdrop": 0.0,
|
26 |
+
"encoder_layers": 12,
|
27 |
+
"eos_token_id": 2,
|
28 |
+
"extra_pos_embeddings": 2,
|
29 |
+
"force_bos_token_to_be_generated": true,
|
30 |
+
"forced_bos_token_id": 0,
|
31 |
+
"forced_eos_token_id": 2,
|
32 |
+
"gradient_checkpointing": false,
|
33 |
+
"id2label": {
|
34 |
+
"0": "LABEL_0",
|
35 |
+
"1": "LABEL_1",
|
36 |
+
"2": "LABEL_2"
|
37 |
+
},
|
38 |
+
"init_std": 0.02,
|
39 |
+
"is_encoder_decoder": true,
|
40 |
+
"label2id": {
|
41 |
+
"LABEL_0": 0,
|
42 |
+
"LABEL_1": 1,
|
43 |
+
"LABEL_2": 2
|
44 |
+
},
|
45 |
+
"length_penalty": 2.0,
|
46 |
+
"max_length": 142,
|
47 |
+
"max_position_embeddings": 1024,
|
48 |
+
"min_length": 56,
|
49 |
+
"model_type": "bart",
|
50 |
+
"no_repeat_ngram_size": 3,
|
51 |
+
"normalize_before": false,
|
52 |
+
"normalize_embedding": true,
|
53 |
+
"num_beams": 4,
|
54 |
+
"num_hidden_layers": 12,
|
55 |
+
"output_past": true,
|
56 |
+
"pad_token_id": 1,
|
57 |
+
"prefix": " ",
|
58 |
+
"replacing_rate": 0,
|
59 |
+
"scale_embedding": false,
|
60 |
+
"static_position_embeddings": false,
|
61 |
+
"student_decoder_layers": null,
|
62 |
+
"student_encoder_layers": null,
|
63 |
+
"task_specific_params": {
|
64 |
+
"summarization": {
|
65 |
+
"early_stopping": true,
|
66 |
+
"length_penalty": 2.0,
|
67 |
+
"max_length": 142,
|
68 |
+
"min_length": 56,
|
69 |
+
"no_repeat_ngram_size": 3,
|
70 |
+
"num_beams": 4
|
71 |
+
}
|
72 |
+
},
|
73 |
+
"transformers_version": "4.34.0.dev0",
|
74 |
+
"use_cache": true,
|
75 |
+
"vocab_size": 50264
|
76 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 2,
|
5 |
+
"early_stopping": true,
|
6 |
+
"eos_token_id": 2,
|
7 |
+
"forced_bos_token_id": 0,
|
8 |
+
"forced_eos_token_id": 2,
|
9 |
+
"length_penalty": 2.0,
|
10 |
+
"max_length": 142,
|
11 |
+
"min_length": 56,
|
12 |
+
"no_repeat_ngram_size": 3,
|
13 |
+
"num_beams": 4,
|
14 |
+
"pad_token_id": 1,
|
15 |
+
"transformers_version": "4.34.0.dev0"
|
16 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
onnx/decoder_model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:308af3b5c09b95008aaf95706dd1120d684531b9f8b7a1d3b93fd8123f6bdb86
|
3 |
+
size 613700175
|
onnx/decoder_model_merged.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d2f6475bbe7847d67b7dde0dab833f9b4a195df8ee939a1bf435ec89583bb287
|
3 |
+
size 613946766
|
onnx/decoder_model_merged_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:499b39e68467a8e3f8f7174e3ef27e7d10ad7faf60a382b01be3198f9fa676a0
|
3 |
+
size 155102167
|
onnx/decoder_model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53a8dfd15e78b4e13e7507e39b23232babf49ac25abc46e5e58cce526cc0cf60
|
3 |
+
size 154715574
|
onnx/decoder_with_past_model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a38bd30798882479b68fc62001fb48bc742bfd164ee369356be6b83d3bdca5d
|
3 |
+
size 563276824
|
onnx/decoder_with_past_model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c542fdb306a7b343503e4b194873fc3ac52f365c8940667e3fb2ffb4b26adcba
|
3 |
+
size 141952254
|
onnx/encoder_model.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7b0f1c0a7de98749bbafc2360fba831736a20af875a208307a28745f2dc51ed
|
3 |
+
size 814942257
|
onnx/encoder_model_quantized.onnx
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:859513ea514dc9b43d975efca26f5b40b4c529eb874ab9e4df9165b50dc6f3d1
|
3 |
+
size 205100092
|
quantize_config.json
ADDED
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"per_channel": true,
|
3 |
+
"reduce_range": true,
|
4 |
+
"per_model_config": {
|
5 |
+
"decoder_model": {
|
6 |
+
"op_types": [
|
7 |
+
"Where",
|
8 |
+
"Less",
|
9 |
+
"Concat",
|
10 |
+
"Erf",
|
11 |
+
"Constant",
|
12 |
+
"Softmax",
|
13 |
+
"Expand",
|
14 |
+
"Equal",
|
15 |
+
"Mul",
|
16 |
+
"ReduceMean",
|
17 |
+
"Sub",
|
18 |
+
"Squeeze",
|
19 |
+
"Gather",
|
20 |
+
"Pow",
|
21 |
+
"Reshape",
|
22 |
+
"Unsqueeze",
|
23 |
+
"Sqrt",
|
24 |
+
"Add",
|
25 |
+
"Transpose",
|
26 |
+
"Slice",
|
27 |
+
"Shape",
|
28 |
+
"MatMul",
|
29 |
+
"Div",
|
30 |
+
"ConstantOfShape",
|
31 |
+
"Range",
|
32 |
+
"Cast"
|
33 |
+
],
|
34 |
+
"weight_type": "QInt8"
|
35 |
+
},
|
36 |
+
"encoder_model": {
|
37 |
+
"op_types": [
|
38 |
+
"Where",
|
39 |
+
"Concat",
|
40 |
+
"Erf",
|
41 |
+
"Constant",
|
42 |
+
"Softmax",
|
43 |
+
"Expand",
|
44 |
+
"Equal",
|
45 |
+
"Mul",
|
46 |
+
"ReduceMean",
|
47 |
+
"Sub",
|
48 |
+
"Pow",
|
49 |
+
"Gather",
|
50 |
+
"Reshape",
|
51 |
+
"Unsqueeze",
|
52 |
+
"Sqrt",
|
53 |
+
"Add",
|
54 |
+
"Transpose",
|
55 |
+
"Shape",
|
56 |
+
"MatMul",
|
57 |
+
"Div",
|
58 |
+
"ConstantOfShape",
|
59 |
+
"Range",
|
60 |
+
"Cast"
|
61 |
+
],
|
62 |
+
"weight_type": "QInt8"
|
63 |
+
},
|
64 |
+
"decoder_model_merged": {
|
65 |
+
"op_types": [
|
66 |
+
"Where",
|
67 |
+
"Less",
|
68 |
+
"Concat",
|
69 |
+
"Erf",
|
70 |
+
"Constant",
|
71 |
+
"Softmax",
|
72 |
+
"Expand",
|
73 |
+
"Equal",
|
74 |
+
"Mul",
|
75 |
+
"ReduceMean",
|
76 |
+
"Sub",
|
77 |
+
"Squeeze",
|
78 |
+
"Gather",
|
79 |
+
"Pow",
|
80 |
+
"Reshape",
|
81 |
+
"Unsqueeze",
|
82 |
+
"Sqrt",
|
83 |
+
"Add",
|
84 |
+
"Transpose",
|
85 |
+
"If",
|
86 |
+
"Slice",
|
87 |
+
"Shape",
|
88 |
+
"MatMul",
|
89 |
+
"Div",
|
90 |
+
"ConstantOfShape",
|
91 |
+
"Range",
|
92 |
+
"Cast"
|
93 |
+
],
|
94 |
+
"weight_type": "QInt8"
|
95 |
+
},
|
96 |
+
"decoder_with_past_model": {
|
97 |
+
"op_types": [
|
98 |
+
"Where",
|
99 |
+
"Concat",
|
100 |
+
"Erf",
|
101 |
+
"Constant",
|
102 |
+
"Softmax",
|
103 |
+
"Expand",
|
104 |
+
"Equal",
|
105 |
+
"Mul",
|
106 |
+
"ReduceMean",
|
107 |
+
"Sub",
|
108 |
+
"Pow",
|
109 |
+
"Gather",
|
110 |
+
"Reshape",
|
111 |
+
"Unsqueeze",
|
112 |
+
"Sqrt",
|
113 |
+
"Add",
|
114 |
+
"Transpose",
|
115 |
+
"Shape",
|
116 |
+
"MatMul",
|
117 |
+
"Div",
|
118 |
+
"ConstantOfShape",
|
119 |
+
"Range",
|
120 |
+
"Cast"
|
121 |
+
],
|
122 |
+
"weight_type": "QInt8"
|
123 |
+
}
|
124 |
+
}
|
125 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"cls_token": {
|
10 |
+
"content": "<s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"eos_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"mask_token": {
|
24 |
+
"content": "<mask>",
|
25 |
+
"lstrip": true,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"pad_token": {
|
31 |
+
"content": "<pad>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"sep_token": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false
|
43 |
+
},
|
44 |
+
"unk_token": {
|
45 |
+
"content": "<unk>",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false
|
50 |
+
}
|
51 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": {
|
4 |
+
"__type": "AddedToken",
|
5 |
+
"content": "<s>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false
|
10 |
+
},
|
11 |
+
"clean_up_tokenization_spaces": true,
|
12 |
+
"cls_token": {
|
13 |
+
"__type": "AddedToken",
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"eos_token": {
|
21 |
+
"__type": "AddedToken",
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"errors": "replace",
|
29 |
+
"mask_token": {
|
30 |
+
"__type": "AddedToken",
|
31 |
+
"content": "<mask>",
|
32 |
+
"lstrip": true,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
},
|
37 |
+
"model_max_length": 1024,
|
38 |
+
"pad_token": {
|
39 |
+
"__type": "AddedToken",
|
40 |
+
"content": "<pad>",
|
41 |
+
"lstrip": false,
|
42 |
+
"normalized": true,
|
43 |
+
"rstrip": false,
|
44 |
+
"single_word": false
|
45 |
+
},
|
46 |
+
"sep_token": {
|
47 |
+
"__type": "AddedToken",
|
48 |
+
"content": "</s>",
|
49 |
+
"lstrip": false,
|
50 |
+
"normalized": true,
|
51 |
+
"rstrip": false,
|
52 |
+
"single_word": false
|
53 |
+
},
|
54 |
+
"tokenizer_class": "BartTokenizer",
|
55 |
+
"trim_offsets": true,
|
56 |
+
"unk_token": {
|
57 |
+
"__type": "AddedToken",
|
58 |
+
"content": "<unk>",
|
59 |
+
"lstrip": false,
|
60 |
+
"normalized": true,
|
61 |
+
"rstrip": false,
|
62 |
+
"single_word": false
|
63 |
+
}
|
64 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|