Hugging Face's logo

dmmagdal
/
gpt2-onnx-js-quantized

Text Generation
Transformers
ONNX
gpt2
Model card Files
xet
 Community
dmmagdal commited on
Commit
82616e6
·
1 Parent(s): aca6652

Uploaded model files (quantized)

Browse files
Files changed (14) hide show
  1. config.json +38 -0
  2. generation_config.json +6 -0
  3. merges.txt +0 -0
  4. onnx/decoder_model.onnx +3 -0
  5. onnx/decoder_model_merged.onnx +3 -0
  6. onnx/decoder_model_merged_quantized.onnx +3 -0
  7. onnx/decoder_model_quantized.onnx +3 -0
  8. onnx/decoder_with_past_model.onnx +3 -0
  9. onnx/decoder_with_past_model_quantized.onnx +3 -0
  10. quantize_config.json +97 -0
  11. special_tokens_map.json +5 -0
  12. tokenizer.json +0 -0
  13. tokenizer_config.json +9 -0
  14. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "transformers_version": "4.33.2",
36
+ "use_cache": true,
37
+ "vocab_size": 50257
38
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.33.2"
6
+ }
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:c94740c16ec5eb29ed49e62db616e575a247317057fe1ee01fca01beca3e7e2a
3
+ size 499275977
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22092d481c713ac0667299449f3ed7db64f0d3559a3d765ca27ba5cdec17a37d
3
+ size 500799139
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e315d7a15feb3459be8b7060d8aae663252f9b8cab3edbc64171653b669136ab
3
+ size 128315766
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8b4fb35b7ddea9f62465d1c1b9b26ba8556edbc2efcd2d9ed1a22b9447b77c9
3
+ size 126556881
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dae500b8e8f1badc33e42797378a8ff306e6c6af7052306ab2c38d7faf2540a8
3
+ size 499282783
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f88684ce8f3e846fe86e34302c41cf7eebf25fa3be4d1a013396cc43f125fda2
3
+ size 126565929
quantize_config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_with_past_model": {
6
+ "op_types": [
7
+ "Shape",
8
+ "Reshape",
9
+ "Gather",
10
+ "ConstantOfShape",
11
+ "Squeeze",
12
+ "Range",
13
+ "Where",
14
+ "Concat",
15
+ "ReduceMean",
16
+ "Constant",
17
+ "Tanh",
18
+ "Softmax",
19
+ "Slice",
20
+ "Add",
21
+ "Split",
22
+ "Sub",
23
+ "Cast",
24
+ "Div",
25
+ "Transpose",
26
+ "Unsqueeze",
27
+ "MatMul",
28
+ "Pow",
29
+ "Mul",
30
+ "Sqrt",
31
+ "Gemm"
32
+ ],
33
+ "weight_type": "QInt8"
34
+ },
35
+ "decoder_model": {
36
+ "op_types": [
37
+ "Shape",
38
+ "Reshape",
39
+ "Gather",
40
+ "ConstantOfShape",
41
+ "Squeeze",
42
+ "Range",
43
+ "Where",
44
+ "Concat",
45
+ "ReduceMean",
46
+ "Constant",
47
+ "Tanh",
48
+ "Softmax",
49
+ "Slice",
50
+ "Add",
51
+ "Split",
52
+ "Sub",
53
+ "Cast",
54
+ "Div",
55
+ "Transpose",
56
+ "Unsqueeze",
57
+ "MatMul",
58
+ "Pow",
59
+ "Mul",
60
+ "Sqrt",
61
+ "Gemm"
62
+ ],
63
+ "weight_type": "QInt8"
64
+ },
65
+ "decoder_model_merged": {
66
+ "op_types": [
67
+ "Shape",
68
+ "Reshape",
69
+ "Gather",
70
+ "ConstantOfShape",
71
+ "Squeeze",
72
+ "Range",
73
+ "Where",
74
+ "Concat",
75
+ "ReduceMean",
76
+ "Constant",
77
+ "Tanh",
78
+ "Softmax",
79
+ "Slice",
80
+ "Add",
81
+ "Split",
82
+ "Sub",
83
+ "Cast",
84
+ "Div",
85
+ "Transpose",
86
+ "Unsqueeze",
87
+ "MatMul",
88
+ "If",
89
+ "Pow",
90
+ "Mul",
91
+ "Sqrt",
92
+ "Gemm"
93
+ ],
94
+ "weight_type": "QInt8"
95
+ }
96
+ }
97
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 1024,
7
+ "tokenizer_class": "GPT2Tokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff