Hugging Face's logo

Felladrin
/
onnx-gpt2-large-conversational-retrain

Text Generation
Transformers.js
ONNX
gpt2
Model card Files Community
1
Felladrin commited on
Commit
32abc3c
•
1 Parent(s): 9b5a3bb

Add model files

Browse files
Files changed (21) hide show
  1. .gitattributes +5 -0
  2. Constant_161_attr__value +3 -0
  3. Constant_171_attr__value +3 -0
  4. added_tokens.json +5 -0
  5. config.json +38 -0
  6. generation_config.json +6 -0
  7. merges.txt +0 -0
  8. onnx/decoder_model.onnx +3 -0
  9. onnx/decoder_model.onnx_data +3 -0
  10. onnx/decoder_model_merged.onnx +3 -0
  11. onnx/decoder_model_merged.onnx_data +3 -0
  12. onnx/decoder_model_merged_quantized.onnx +3 -0
  13. onnx/decoder_model_quantized.onnx +3 -0
  14. onnx/decoder_with_past_model.onnx +3 -0
  15. onnx/decoder_with_past_model.onnx_data +3 -0
  16. onnx/decoder_with_past_model_quantized.onnx +3 -0
  17. quantize_config.json +97 -0
  18. special_tokens_map.json +10 -0
  19. tokenizer.json +0 -0
  20. tokenizer_config.json +13 -0
  21. 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
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|ASSISTANT|>": 50258,
3
+ "<|USER|>": 50257,
4
+ "[PAD]": 50259
5
+ }
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Locutusque/gpt2-large-conversational-retrain",
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": 50260
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:a0224cf68d56b5b2c19457df34b3c82d73dd9adde9f5e1807c6b6811f039fa56
3
+ size 2649681
onnx/decoder_model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03c777cb481fc1cfb664acfc344b8548279b8d41035c1fadc1234ba38d8b2020
3
+ size 3096135680
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2547c809f15cf69e0c38cb1440c640130f2a2323cdfe6debaad2c03ba206aeb
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 sha256:03c777cb481fc1cfb664acfc344b8548279b8d41035c1fadc1234ba38d8b2020
3
+ size 3096135680
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79dc63216512f7ead451dc650eef551fb9eb5de88d471b70f302e3904bfa1ccd
3
+ size 782507045
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:524aafab763a484c5a08fa09dafa237c1f64980870397da1680680294e1aee83
3
+ size 779165383
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c2b1d0e51226eec01780ce801f40d3ea6f93a9121c8883176323ecb045b433a
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 sha256:03c777cb481fc1cfb664acfc344b8548279b8d41035c1fadc1234ba38d8b2020
3
+ size 3096135680
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2fa87aab7909a036cd724cf130621752f40547d6c679da073008fa4274effb8
3
+ size 779190339
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
+ "Where",
8
+ "Sqrt",
9
+ "Gather",
10
+ "Unsqueeze",
11
+ "Concat",
12
+ "Gemm",
13
+ "Tanh",
14
+ "Add",
15
+ "Shape",
16
+ "Cast",
17
+ "Div",
18
+ "Squeeze",
19
+ "Slice",
20
+ "Sub",
21
+ "ConstantOfShape",
22
+ "MatMul",
23
+ "Range",
24
+ "Pow",
25
+ "Reshape",
26
+ "Split",
27
+ "Mul",
28
+ "Constant",
29
+ "ReduceMean",
30
+ "Transpose",
31
+ "Softmax"
32
+ ],
33
+ "weight_type": "QInt8"
34
+ },
35
+ "decoder_model": {
36
+ "op_types": [
37
+ "Where",
38
+ "Sqrt",
39
+ "Gather",
40
+ "Unsqueeze",
41
+ "Concat",
42
+ "Gemm",
43
+ "Tanh",
44
+ "Add",
45
+ "Shape",
46
+ "Cast",
47
+ "Div",
48
+ "Squeeze",
49
+ "Sub",
50
+ "Slice",
51
+ "ConstantOfShape",
52
+ "MatMul",
53
+ "Range",
54
+ "Pow",
55
+ "Reshape",
56
+ "Split",
57
+ "Mul",
58
+ "Constant",
59
+ "ReduceMean",
60
+ "Transpose",
61
+ "Softmax"
62
+ ],
63
+ "weight_type": "QInt8"
64
+ },
65
+ "decoder_model_merged": {
66
+ "op_types": [
67
+ "Where",
68
+ "Sqrt",
69
+ "Gather",
70
+ "Unsqueeze",
71
+ "Concat",
72
+ "Gemm",
73
+ "Tanh",
74
+ "Add",
75
+ "Shape",
76
+ "Cast",
77
+ "Div",
78
+ "Squeeze",
79
+ "If",
80
+ "Sub",
81
+ "Slice",
82
+ "ConstantOfShape",
83
+ "MatMul",
84
+ "Range",
85
+ "Pow",
86
+ "Reshape",
87
+ "Split",
88
+ "Mul",
89
+ "Constant",
90
+ "ReduceMean",
91
+ "Transpose",
92
+ "Softmax"
93
+ ],
94
+ "weight_type": "QInt8"
95
+ }
96
+ }
97
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|USER|>",
4
+ "<|ASSISTANT|>"
5
+ ],
6
+ "bos_token": "<|endoftext|>",
7
+ "eos_token": "<|endoftext|>",
8
+ "pad_token": "[PAD]",
9
+ "unk_token": "<|endoftext|>"
10
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "max_length": 256,
7
+ "model_max_length": 1024,
8
+ "stride": 0,
9
+ "tokenizer_class": "GPT2Tokenizer",
10
+ "truncation_side": "right",
11
+ "truncation_strategy": "longest_first",
12
+ "unk_token": "<|endoftext|>"
13
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff