Hugging Face's logo

dmmagdal
/
gpt2-large-onnx-js-quantized

Text Generation
Transformers
ONNX
gpt2
Inference Endpoints
Model card Files Community
dmmagdal commited on
Commit
7014d5d
·
1 Parent(s): 38f2070

Uploaded model flles (quantized)

Browse files
Files changed (20) hide show
  1. .gitattributes +5 -0
  2. Constant_161_attr__value +3 -0
  3. Constant_171_attr__value +3 -0
  4. config.json +38 -0
  5. generation_config.json +6 -0
  6. merges.txt +0 -0
  7. onnx/decoder_model.onnx +3 -0
  8. onnx/decoder_model.onnx_data +3 -0
  9. onnx/decoder_model_merged.onnx +3 -0
  10. onnx/decoder_model_merged.onnx_data +3 -0
  11. onnx/decoder_model_merged_quantized.onnx +3 -0
  12. onnx/decoder_model_quantized.onnx +3 -0
  13. onnx/decoder_with_past_model.onnx +3 -0
  14. onnx/decoder_with_past_model.onnx_data +3 -0
  15. onnx/decoder_with_past_model_quantized.onnx +3 -0
  16. quantize_config.json +97 -0
  17. special_tokens_map.json +5 -0
  18. tokenizer.json +0 -0
  19. tokenizer_config.json +9 -0
  20. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,8 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ Constant_161_attr__value filter=lfs diff=lfs merge=lfs -text
37
+ Constant_171_attr__value filter=lfs diff=lfs merge=lfs -text
38
+ onnx/decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
39
+ onnx/decoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text
40
+ onnx/decoder_with_past_model.onnx_data filter=lfs diff=lfs merge=lfs -text
Constant_161_attr__value ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae525b5c247f1f7b8310c42b37be7aed79adadb1806bb109d1e14c8c896fc319
3
+ size 1048576
Constant_171_attr__value ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae525b5c247f1f7b8310c42b37be7aed79adadb1806bb109d1e14c8c896fc319
3
+ size 1048576
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2-large",
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": 1280,
16
+ "n_head": 20,
17
+ "n_inner": null,
18
+ "n_layer": 36,
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 sha256:840c27bdee6eaff52b7fcd4b8a2b3ff99b1a63c48f7fb32c79b61b25e503d0cf
3
+ size 2649681
onnx/decoder_model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8036986831a21445c3cabc12e1a5fd2e438cfd8baffba3e83c74b7198d571e39
3
+ size 3096120320
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85e2cf3f1455fa89e993cc1aca0d3c80be01a84451fc93bd99704d8fad9cea29
3
+ size 5288484
onnx/decoder_model_merged.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8036986831a21445c3cabc12e1a5fd2e438cfd8baffba3e83c74b7198d571e39
3
+ size 3096120320
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2762937a0f695578043b001a4022ae6c2743fdb016f71ebfaf270ad403ecd572
3
+ size 782503206
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ee853c745fb456e2885ff1072090a5e96ea1ea1aa6cc66f00ecc6584fb73182
3
+ size 779161544
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13f2f3db8527876a6b14e69add328ab3dfa891bb9096693a5caef56ac612bf65
3
+ size 2673118
onnx/decoder_with_past_model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8036986831a21445c3cabc12e1a5fd2e438cfd8baffba3e83c74b7198d571e39
3
+ size 3096120320
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6897a5da8d1135fb9299f6d94174dc47ff25b735730b1c6ec0f265bc9834ff4a
3
+ size 779186500
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
+ "Cast",
8
+ "Tanh",
9
+ "Add",
10
+ "ConstantOfShape",
11
+ "Mul",
12
+ "Range",
13
+ "Constant",
14
+ "Reshape",
15
+ "Split",
16
+ "Softmax",
17
+ "Where",
18
+ "Slice",
19
+ "Squeeze",
20
+ "Unsqueeze",
21
+ "Shape",
22
+ "Concat",
23
+ "Transpose",
24
+ "Gather",
25
+ "Sub",
26
+ "Sqrt",
27
+ "Div",
28
+ "Gemm",
29
+ "ReduceMean",
30
+ "Pow",
31
+ "MatMul"
32
+ ],
33
+ "weight_type": "QInt8"
34
+ },
35
+ "decoder_model": {
36
+ "op_types": [
37
+ "Cast",
38
+ "Tanh",
39
+ "Add",
40
+ "ConstantOfShape",
41
+ "Mul",
42
+ "Range",
43
+ "Constant",
44
+ "Reshape",
45
+ "Split",
46
+ "Softmax",
47
+ "Where",
48
+ "Slice",
49
+ "Squeeze",
50
+ "Unsqueeze",
51
+ "Shape",
52
+ "Concat",
53
+ "Transpose",
54
+ "Gather",
55
+ "Sub",
56
+ "Sqrt",
57
+ "Div",
58
+ "Gemm",
59
+ "ReduceMean",
60
+ "Pow",
61
+ "MatMul"
62
+ ],
63
+ "weight_type": "QInt8"
64
+ },
65
+ "decoder_model_merged": {
66
+ "op_types": [
67
+ "Cast",
68
+ "Tanh",
69
+ "Add",
70
+ "ConstantOfShape",
71
+ "Mul",
72
+ "Range",
73
+ "Constant",
74
+ "Reshape",
75
+ "Split",
76
+ "Softmax",
77
+ "Where",
78
+ "Slice",
79
+ "Squeeze",
80
+ "Unsqueeze",
81
+ "If",
82
+ "Shape",
83
+ "Concat",
84
+ "Transpose",
85
+ "Gather",
86
+ "Sub",
87
+ "Sqrt",
88
+ "Div",
89
+ "Gemm",
90
+ "ReduceMean",
91
+ "Pow",
92
+ "MatMul"
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