Hugging Face's logo

Xenova
/
gpt2-large-conversational

Text Generation
Transformers.js
ONNX
gpt2
Model card Files Community
1
Xenova HF staff commited on
Commit
9f30f78
•
1 Parent(s): 80693ee

Upload folder using huggingface_hub

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 +6 -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 +11 -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.onnx_data filter=lfs diff=lfs merge=lfs -text
39
+ onnx/decoder_model_merged.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 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "<|ASSISTANT|>": 50257,
3
+ "<|SYSTEM|>": 50259,
4
+ "<|USER|>": 50258,
5
+ "[PAD]": 50260
6
+ }
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "Locutusque/gpt2-large-conversational",
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": "4.34.0.dev0",
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": "4.34.0.dev0"
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:b1680214930fcee9705886f8c4a96d5b06d8e7a9dcb7f95b3de5750c691dd337
3
+ size 2649672
onnx/decoder_model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffbbdd9ba0f5e25dd2c6b7ac1f8b29cfe850e178d89cba28a8faa2ac4dabdd5b
3
+ size 3096135680
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:542e5011e4267eb5ba0ca23392243174ae09bff2bb1cc12a95f4e26ec271cc8f
3
+ size 5288464
onnx/decoder_model_merged.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffbbdd9ba0f5e25dd2c6b7ac1f8b29cfe850e178d89cba28a8faa2ac4dabdd5b
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:e6da274ef18bdefafa72a9e70ab070d19dfc0b7a9cd893fe7de6722b59e6c7e5
3
+ size 782507015
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7b4f82db7c1298b692ce516a61dc31def8e80e3ec3b369d20a5ad905ca77213
3
+ size 779165370
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81879932dce3cbd15909fb212d73ccfc66e348800f288a30148f8480c27244f3
3
+ size 2673105
onnx/decoder_with_past_model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffbbdd9ba0f5e25dd2c6b7ac1f8b29cfe850e178d89cba28a8faa2ac4dabdd5b
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 sha256:85a5f3136c8b60b3b40b1f0544edbecbd3c065588a8ed5822757a0b3050cd928
3
+ size 779190320
quantize_config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_model_merged": {
6
+ "op_types": [
7
+ "Sub",
8
+ "Shape",
9
+ "Gather",
10
+ "Unsqueeze",
11
+ "Transpose",
12
+ "Pow",
13
+ "ReduceMean",
14
+ "Div",
15
+ "Reshape",
16
+ "Split",
17
+ "Constant",
18
+ "Range",
19
+ "Gemm",
20
+ "Squeeze",
21
+ "Mul",
22
+ "If",
23
+ "MatMul",
24
+ "Where",
25
+ "Softmax",
26
+ "Concat",
27
+ "Sqrt",
28
+ "Cast",
29
+ "ConstantOfShape",
30
+ "Tanh",
31
+ "Slice",
32
+ "Add"
33
+ ],
34
+ "weight_type": "QInt8"
35
+ },
36
+ "decoder_with_past_model": {
37
+ "op_types": [
38
+ "Sub",
39
+ "Shape",
40
+ "Gather",
41
+ "Unsqueeze",
42
+ "Transpose",
43
+ "Pow",
44
+ "ReduceMean",
45
+ "Div",
46
+ "Reshape",
47
+ "Split",
48
+ "Constant",
49
+ "Range",
50
+ "Gemm",
51
+ "Mul",
52
+ "Squeeze",
53
+ "MatMul",
54
+ "Where",
55
+ "Softmax",
56
+ "Concat",
57
+ "Sqrt",
58
+ "Cast",
59
+ "ConstantOfShape",
60
+ "Tanh",
61
+ "Slice",
62
+ "Add"
63
+ ],
64
+ "weight_type": "QInt8"
65
+ },
66
+ "decoder_model": {
67
+ "op_types": [
68
+ "Sub",
69
+ "Shape",
70
+ "Gather",
71
+ "Unsqueeze",
72
+ "Transpose",
73
+ "Pow",
74
+ "ReduceMean",
75
+ "Div",
76
+ "Reshape",
77
+ "Split",
78
+ "Constant",
79
+ "Range",
80
+ "Gemm",
81
+ "Squeeze",
82
+ "Mul",
83
+ "MatMul",
84
+ "Where",
85
+ "Softmax",
86
+ "Concat",
87
+ "Sqrt",
88
+ "Cast",
89
+ "ConstantOfShape",
90
+ "Tanh",
91
+ "Slice",
92
+ "Add"
93
+ ],
94
+ "weight_type": "QInt8"
95
+ }
96
+ }
97
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|ASSISTANT|>",
4
+ "<|USER|>",
5
+ "<|SYSTEM|>"
6
+ ],
7
+ "bos_token": "<|endoftext|>",
8
+ "eos_token": "<|endoftext|>",
9
+ "pad_token": "[PAD]",
10
+ "unk_token": "<|endoftext|>"
11
+ }
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