Hugging Face's logo

Felladrin
/
onnx-megatron-gpt2-345m-evol_instruct_v2

Text Generation
Transformers.js
ONNX
gpt2
Model card Files Community
Felladrin commited on
Commit
967fe74
•
1 Parent(s): c32d1e8

Add model files

Browse files
Files changed (14) hide show
  1. config.json +33 -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 +9 -0
  14. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "KnutJaegersberg/megatron-gpt2-345m-evol_instruct_v2",
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
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 1024,
17
+ "n_head": 16,
18
+ "n_inner": 4096,
19
+ "n_layer": 24,
20
+ "n_positions": 1024,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "transformers_version": "4.33.2",
31
+ "use_cache": false,
32
+ "vocab_size": 50257
33
+ }
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:ed06cdd07ff4c8444f2a23c5f4c8d70c054f764628185195eb9322a4f8b3d02d
3
+ size 1421277493
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fcb37a32ad34c24d685b7a3d6e5ca7c465d368c91dbc873fb720058acb28aa5
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 sha256:613a62afe86b2b204e2ec63238dc49fcb2fbb7ca8aa6d25c05e7a47f3f46e0c5
3
+ size 360712205
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a0384ed66ca52bbf8ec35160ae953afadced595b9541d22386237c3e475d62d
3
+ size 358244775
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8820a37f16241e58965c26b355f7bf62756a3a433453223982ba7fc296a688f0
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:c301a5d538272adf48278b52f7cbd5ad6723027db40faf143e22d75ac35f0847
3
+ size 358261704
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
+ "Slice",
8
+ "Reshape",
9
+ "Where",
10
+ "Tanh",
11
+ "ReduceMean",
12
+ "Pow",
13
+ "Cast",
14
+ "Add",
15
+ "Constant",
16
+ "Div",
17
+ "Mul",
18
+ "ConstantOfShape",
19
+ "Concat",
20
+ "Range",
21
+ "MatMul",
22
+ "Unsqueeze",
23
+ "Shape",
24
+ "Gather",
25
+ "Softmax",
26
+ "Squeeze",
27
+ "Gemm",
28
+ "Split",
29
+ "Transpose",
30
+ "Sqrt",
31
+ "Sub"
32
+ ],
33
+ "weight_type": "QInt8"
34
+ },
35
+ "decoder_model": {
36
+ "op_types": [
37
+ "Slice",
38
+ "Reshape",
39
+ "Where",
40
+ "Tanh",
41
+ "ReduceMean",
42
+ "Pow",
43
+ "Cast",
44
+ "Add",
45
+ "Constant",
46
+ "Div",
47
+ "Mul",
48
+ "ConstantOfShape",
49
+ "Concat",
50
+ "Range",
51
+ "MatMul",
52
+ "Unsqueeze",
53
+ "Shape",
54
+ "Gather",
55
+ "Softmax",
56
+ "Squeeze",
57
+ "Gemm",
58
+ "Split",
59
+ "Transpose",
60
+ "Sqrt",
61
+ "Sub"
62
+ ],
63
+ "weight_type": "QInt8"
64
+ },
65
+ "decoder_model_merged": {
66
+ "op_types": [
67
+ "Slice",
68
+ "Reshape",
69
+ "Where",
70
+ "Tanh",
71
+ "ReduceMean",
72
+ "Pow",
73
+ "Cast",
74
+ "Add",
75
+ "Constant",
76
+ "Div",
77
+ "Mul",
78
+ "ConstantOfShape",
79
+ "Concat",
80
+ "Range",
81
+ "MatMul",
82
+ "Unsqueeze",
83
+ "Shape",
84
+ "If",
85
+ "Gather",
86
+ "Softmax",
87
+ "Squeeze",
88
+ "Gemm",
89
+ "Split",
90
+ "Transpose",
91
+ "Sqrt",
92
+ "Sub"
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 +1,9 @@
 
 
 
 
 
 
 
 
 
 
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