Hugging Face's logo

gstaff
/
gpt2-magic-card-web

Text Generation
Transformers
ONNX
gpt2
text-generation-inference
Inference Endpoints
Model card Files Community
gstaff commited on
Commit
28ea93b
•
1 Parent(s): 937957d

Upload files for transformers.js

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-magic-card",
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": "4.33.0.dev0",
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": "4.33.0.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 sha256:203088c58b43ed3d529666bd1e8b7abf84c8c4bc33a929b181cce280776b5bd2
3
+ size 499275976
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33238cfce1785c347e0ac7134f2500fadfa7f5af6e537a7bb2a769d9e4217260
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:da6257be48d422fe7b0a71e2be74b1cec2f1d7637d9ec552c8f9e5ea4102de32
3
+ size 128730727
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fc84ac6c0b3de482208b865e23c05f718d116587abeca70cee52bc607c78db8
3
+ size 126971841
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bccf364af191d522910eac476249a8f386489fe79287e9b30de307420129275b
3
+ size 499282782
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4a108612c823b5ad4c00257dc6937fe3beca7ef4494944761360e080f563ef9
3
+ size 126980889
quantize_config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Shape",
8
+ "Pow",
9
+ "Concat",
10
+ "Div",
11
+ "Add",
12
+ "Cast",
13
+ "Slice",
14
+ "Sub",
15
+ "Gather",
16
+ "ConstantOfShape",
17
+ "MatMul",
18
+ "Reshape",
19
+ "Where",
20
+ "Unsqueeze",
21
+ "Tanh",
22
+ "Transpose",
23
+ "Squeeze",
24
+ "Softmax",
25
+ "ReduceMean",
26
+ "Constant",
27
+ "Mul",
28
+ "Split",
29
+ "Sqrt",
30
+ "Range",
31
+ "Gemm"
32
+ ],
33
+ "weight_type": "QInt8"
34
+ },
35
+ "decoder_model_merged": {
36
+ "op_types": [
37
+ "Shape",
38
+ "Pow",
39
+ "If",
40
+ "Concat",
41
+ "Div",
42
+ "Add",
43
+ "Cast",
44
+ "Slice",
45
+ "Sub",
46
+ "Gather",
47
+ "ConstantOfShape",
48
+ "MatMul",
49
+ "Reshape",
50
+ "Where",
51
+ "Unsqueeze",
52
+ "Tanh",
53
+ "Transpose",
54
+ "Squeeze",
55
+ "Softmax",
56
+ "ReduceMean",
57
+ "Constant",
58
+ "Mul",
59
+ "Split",
60
+ "Sqrt",
61
+ "Range",
62
+ "Gemm"
63
+ ],
64
+ "weight_type": "QInt8"
65
+ },
66
+ "decoder_with_past_model": {
67
+ "op_types": [
68
+ "Shape",
69
+ "Pow",
70
+ "Concat",
71
+ "Div",
72
+ "Add",
73
+ "Cast",
74
+ "Slice",
75
+ "Sub",
76
+ "Gather",
77
+ "ConstantOfShape",
78
+ "MatMul",
79
+ "Reshape",
80
+ "Where",
81
+ "Unsqueeze",
82
+ "Tanh",
83
+ "Transpose",
84
+ "Squeeze",
85
+ "Softmax",
86
+ "ReduceMean",
87
+ "Constant",
88
+ "Mul",
89
+ "Split",
90
+ "Sqrt",
91
+ "Range",
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": 1000000000000000019884624838656,
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