Xenova HF staff commited on
Commit
fbe0a88
1 Parent(s): ab86fd8

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "heegyu/kogpt-j-350m",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTJForCausalLM"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 1,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 2,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gptj",
15
+ "n_embd": 1024,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 20,
19
+ "n_positions": 1024,
20
+ "pad_token_id": 0,
21
+ "resid_pdrop": 0.0,
22
+ "rotary_dim": 32,
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
+ "tie_word_embeddings": false,
30
+ "tokenizer_class": "GPT2Tokenizer",
31
+ "transformers_version": "4.33.0.dev0",
32
+ "unk_token_id": 5,
33
+ "use_cache": true,
34
+ "vocab_size": 51200
35
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.33.0.dev0"
7
+ }
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:f089b2b64ef39ff5496c353a3def3d13ca0f2ccf3858d3a01b843f356146b48c
3
+ size 1428685394
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ef17a57e398535acc8a84aa4adf7be535b539ac973dec0e65dd043e285e96f8
3
+ size 1430533475
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e28525c7f9f0410abd6a6a3cf915cb91c42c566834ff6ec2b90bcf266305bf4b
3
+ size 362871962
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44914eb07c7846a8dae1f417a1fcecb5a16156514c0231bd81c2965196b9513d
3
+ size 360670405
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23b7411c3d1d6e53da5b740cfa9d3d389384bee6a0039884d493baecbb5a9a32
3
+ size 1428696529
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f359b74a559af46b6314e817c4b2843182ff0fb8b890c10b55f073354fd5517c
3
+ size 360683921
quantize_config.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Equal",
8
+ "Cast",
9
+ "SequenceAt",
10
+ "Tile",
11
+ "SplitToSequence",
12
+ "Div",
13
+ "Split",
14
+ "Range",
15
+ "Where",
16
+ "Constant",
17
+ "Expand",
18
+ "Add",
19
+ "Gather",
20
+ "Sqrt",
21
+ "Pow",
22
+ "Tanh",
23
+ "Reshape",
24
+ "Slice",
25
+ "Loop",
26
+ "SequenceEmpty",
27
+ "MatMul",
28
+ "Mul",
29
+ "ConcatFromSequence",
30
+ "SequenceInsert",
31
+ "ReduceMean",
32
+ "Transpose",
33
+ "GatherElements",
34
+ "Shape",
35
+ "Squeeze",
36
+ "Sub",
37
+ "Unsqueeze",
38
+ "Concat",
39
+ "Neg",
40
+ "Softmax",
41
+ "ConstantOfShape"
42
+ ],
43
+ "weight_type": "QInt8"
44
+ },
45
+ "decoder_model_merged": {
46
+ "op_types": [
47
+ "Equal",
48
+ "Cast",
49
+ "SequenceAt",
50
+ "Tile",
51
+ "SplitToSequence",
52
+ "Div",
53
+ "Split",
54
+ "Range",
55
+ "Where",
56
+ "Constant",
57
+ "Expand",
58
+ "Add",
59
+ "Gather",
60
+ "Sqrt",
61
+ "Pow",
62
+ "Tanh",
63
+ "Reshape",
64
+ "Slice",
65
+ "Loop",
66
+ "SequenceEmpty",
67
+ "MatMul",
68
+ "Mul",
69
+ "ConcatFromSequence",
70
+ "SequenceInsert",
71
+ "If",
72
+ "ReduceMean",
73
+ "Transpose",
74
+ "GatherElements",
75
+ "Shape",
76
+ "Squeeze",
77
+ "Sub",
78
+ "Unsqueeze",
79
+ "Concat",
80
+ "Neg",
81
+ "Softmax",
82
+ "ConstantOfShape"
83
+ ],
84
+ "weight_type": "QInt8"
85
+ },
86
+ "decoder_with_past_model": {
87
+ "op_types": [
88
+ "Equal",
89
+ "Cast",
90
+ "SequenceAt",
91
+ "Tile",
92
+ "SplitToSequence",
93
+ "Div",
94
+ "Split",
95
+ "Range",
96
+ "Where",
97
+ "Constant",
98
+ "Expand",
99
+ "Add",
100
+ "Gather",
101
+ "Sqrt",
102
+ "Pow",
103
+ "Tanh",
104
+ "Reshape",
105
+ "Slice",
106
+ "Loop",
107
+ "SequenceEmpty",
108
+ "MatMul",
109
+ "Mul",
110
+ "ConcatFromSequence",
111
+ "SequenceInsert",
112
+ "ReduceMean",
113
+ "Transpose",
114
+ "GatherElements",
115
+ "Shape",
116
+ "Squeeze",
117
+ "Sub",
118
+ "Unsqueeze",
119
+ "Concat",
120
+ "Neg",
121
+ "Softmax",
122
+ "ConstantOfShape"
123
+ ],
124
+ "weight_type": "QInt8"
125
+ }
126
+ }
127
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "<pad>",
5
+ "unk_token": "<unk>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": null,
24
+ "tokenizer_class": "GPT2Tokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff