Hugging Face's logo

Xenova
/
pythia-160m

Text Generation
Transformers.js
ONNX
gpt_neox
Model card Files
xet
Community
1
Xenova HF Staff commited on
Commit
8da07fb
·
1 Parent(s): d263ccb

Upload folder using huggingface_hub

Browse files
Files changed (12) hide show
  1. config.json +28 -0
  2. generation_config.json +6 -0
  3. onnx/decoder_model.onnx +3 -0
  4. onnx/decoder_model_merged.onnx +3 -0
  5. onnx/decoder_model_merged_quantized.onnx +3 -0
  6. onnx/decoder_model_quantized.onnx +3 -0
  7. onnx/decoder_with_past_model.onnx +3 -0
  8. onnx/decoder_with_past_model_quantized.onnx +3 -0
  9. quantize_config.json +103 -0
  10. special_tokens_map.json +5 -0
  11. tokenizer.json +0 -0
  12. tokenizer_config.json +9 -0
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-160m",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": 0.1,
9
+ "eos_token_id": 0,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout": 0.0,
12
+ "hidden_size": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 3072,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 2048,
17
+ "model_type": "gpt_neox",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "rope_scaling": null,
21
+ "rotary_emb_base": 10000,
22
+ "rotary_pct": 0.25,
23
+ "tie_word_embeddings": false,
24
+ "transformers_version": "4.34.0.dev0",
25
+ "use_cache": true,
26
+ "use_parallel_residual": true,
27
+ "vocab_size": 50304
28
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.34.0.dev0"
6
+ }
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70e60e56458294cc2f59b18a612971df8bc73f095b0d52ae1433fc0d739bcd64
3
+ size 654410647
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d33624a8d6354285a85155854fe9e8db5d84525091f6c1aa08ccda298209f864
3
+ size 659543749
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90b3a14444243ae5a16fc482e8d211a5d6878ccb734512253f648e6ee3253715
3
+ size 173530346
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:010f7d1c328da85f9ed9989862fb292de9843b668cc692b7a8b36752ba1426af
3
+ size 168099893
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e4e092051eee8b1addfb1925d9e2a57f385c8db248b89ed42651f042f3f64d8
3
+ size 654425869
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f13287d7ed4a8b5df6ca0cf3a3ec9f90257cd0b7bb5411a11d209d295bb5de92
3
+ size 168119246
quantize_config.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Cast",
8
+ "Slice",
9
+ "Sqrt",
10
+ "Constant",
11
+ "Softmax",
12
+ "Add",
13
+ "Mul",
14
+ "Unsqueeze",
15
+ "Pow",
16
+ "Tile",
17
+ "Shape",
18
+ "MatMul",
19
+ "GatherElements",
20
+ "Sub",
21
+ "Gather",
22
+ "Where",
23
+ "Transpose",
24
+ "Erf",
25
+ "ConstantOfShape",
26
+ "ReduceMean",
27
+ "Range",
28
+ "Expand",
29
+ "Neg",
30
+ "Reshape",
31
+ "Concat",
32
+ "Div",
33
+ "Squeeze"
34
+ ],
35
+ "weight_type": "QInt8"
36
+ },
37
+ "decoder_model_merged": {
38
+ "op_types": [
39
+ "Cast",
40
+ "Slice",
41
+ "Sqrt",
42
+ "Constant",
43
+ "Softmax",
44
+ "Add",
45
+ "Mul",
46
+ "Unsqueeze",
47
+ "Pow",
48
+ "Tile",
49
+ "Shape",
50
+ "MatMul",
51
+ "GatherElements",
52
+ "Sub",
53
+ "Gather",
54
+ "Where",
55
+ "Transpose",
56
+ "Erf",
57
+ "ConstantOfShape",
58
+ "ReduceMean",
59
+ "Range",
60
+ "Expand",
61
+ "Neg",
62
+ "Reshape",
63
+ "Concat",
64
+ "If",
65
+ "Div",
66
+ "Squeeze"
67
+ ],
68
+ "weight_type": "QInt8"
69
+ },
70
+ "decoder_with_past_model": {
71
+ "op_types": [
72
+ "Cast",
73
+ "Slice",
74
+ "Sqrt",
75
+ "Constant",
76
+ "Softmax",
77
+ "Add",
78
+ "Mul",
79
+ "Unsqueeze",
80
+ "Pow",
81
+ "Tile",
82
+ "Shape",
83
+ "MatMul",
84
+ "GatherElements",
85
+ "Sub",
86
+ "Gather",
87
+ "Where",
88
+ "Transpose",
89
+ "Erf",
90
+ "ConstantOfShape",
91
+ "ReduceMean",
92
+ "Range",
93
+ "Expand",
94
+ "Neg",
95
+ "Reshape",
96
+ "Concat",
97
+ "Div",
98
+ "Squeeze"
99
+ ],
100
+ "weight_type": "QInt8"
101
+ }
102
+ }
103
+ }
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": "GPTNeoXTokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }