Hugging Face's logo

Felladrin
/
onnx-GPT2-Medium-Alpaca-355m

Text Generation
Transformers.js
ONNX
gpt2
Model card Files Community
Felladrin commited on
Commit
300f192
•
1 Parent(s): fd29d7a

Add model files

Browse files
Files changed (14) hide show
  1. config.json +40 -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 +6 -0
  12. tokenizer.json +0 -0
  13. tokenizer_config.json +14 -0
  14. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "linkanjarad/GPT2-Medium-Alpaca-355m",
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": 1024,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 24,
19
+ "n_positions": 1024,
20
+ "n_special": 0,
21
+ "predict_special_tokens": true,
22
+ "reorder_and_upcast_attn": false,
23
+ "resid_pdrop": 0.1,
24
+ "scale_attn_by_inverse_layer_idx": false,
25
+ "scale_attn_weights": true,
26
+ "summary_activation": null,
27
+ "summary_first_dropout": 0.1,
28
+ "summary_proj_to_labels": true,
29
+ "summary_type": "cls_index",
30
+ "summary_use_proj": true,
31
+ "task_specific_params": {
32
+ "text-generation": {
33
+ "do_sample": true,
34
+ "max_length": 50
35
+ }
36
+ },
37
+ "transformers_version": "4.33.2",
38
+ "use_cache": true,
39
+ "vocab_size": 50257
40
+ }
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 sha256:77fb0d4de3de356c68a785c36a39631f1aae9fd7397bf15318e0d2e0b972b426
3
+ size 1421277493
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18aedea7f14aedd20c1df9f7d700ddeacde971dff166a5e9f0aa0751a5b48fd1
3
+ size 1423274137
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1f20bee06cd84cece66b86d93795b0715a06bca568db8d46bb99582e99cd782
3
+ size 360712204
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dac1fb2fa4209f3220ad9228b494e6be16963ef7761a4273130e9e2679ccd3d
3
+ size 358244774
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51ed332adbb01017b0cce28b9e8442ac69273e110f593641afebc0439027e993
3
+ size 1421290281
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43c8457b241fb0bb17e5ae5a3a25c1c010f27ce4885b6d870315c1f21e3e6dd3
3
+ size 358261703
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
+ "Concat",
8
+ "Div",
9
+ "Mul",
10
+ "MatMul",
11
+ "Transpose",
12
+ "Slice",
13
+ "Where",
14
+ "Range",
15
+ "Reshape",
16
+ "Softmax",
17
+ "Unsqueeze",
18
+ "ReduceMean",
19
+ "ConstantOfShape",
20
+ "Split",
21
+ "Add",
22
+ "Cast",
23
+ "Tanh",
24
+ "Gemm",
25
+ "Gather",
26
+ "Sqrt",
27
+ "Sub",
28
+ "Shape",
29
+ "Pow",
30
+ "Squeeze",
31
+ "Constant"
32
+ ],
33
+ "weight_type": "QInt8"
34
+ },
35
+ "decoder_model": {
36
+ "op_types": [
37
+ "Concat",
38
+ "Div",
39
+ "Mul",
40
+ "MatMul",
41
+ "Transpose",
42
+ "Slice",
43
+ "Where",
44
+ "Range",
45
+ "Reshape",
46
+ "Softmax",
47
+ "Unsqueeze",
48
+ "ReduceMean",
49
+ "ConstantOfShape",
50
+ "Split",
51
+ "Add",
52
+ "Cast",
53
+ "Tanh",
54
+ "Gemm",
55
+ "Gather",
56
+ "Sqrt",
57
+ "Sub",
58
+ "Shape",
59
+ "Pow",
60
+ "Squeeze",
61
+ "Constant"
62
+ ],
63
+ "weight_type": "QInt8"
64
+ },
65
+ "decoder_model_merged": {
66
+ "op_types": [
67
+ "If",
68
+ "Concat",
69
+ "Div",
70
+ "Mul",
71
+ "MatMul",
72
+ "Transpose",
73
+ "Slice",
74
+ "Where",
75
+ "Range",
76
+ "Reshape",
77
+ "Softmax",
78
+ "Unsqueeze",
79
+ "ReduceMean",
80
+ "ConstantOfShape",
81
+ "Split",
82
+ "Add",
83
+ "Cast",
84
+ "Tanh",
85
+ "Gemm",
86
+ "Gather",
87
+ "Sqrt",
88
+ "Sub",
89
+ "Shape",
90
+ "Pow",
91
+ "Squeeze",
92
+ "Constant"
93
+ ],
94
+ "weight_type": "QInt8"
95
+ }
96
+ }
97
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "max_length": null,
7
+ "model_max_length": 1024,
8
+ "pad_to_multiple_of": null,
9
+ "pad_token": "<|endoftext|>",
10
+ "pad_token_type_id": 0,
11
+ "padding_side": "right",
12
+ "tokenizer_class": "GPT2Tokenizer",
13
+ "unk_token": "<|endoftext|>"
14
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff