Hugging Face's logo

Xenova
/
pythia-70m

Text Generation
Transformers.js
ONNX
gpt_neox
Model card Files Community
Xenova HF staff commited on
Commit
196025f
•
1 Parent(s): 1dfaef4

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 +106 -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-70m",
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": 512,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 2048,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 2048,
17
+ "model_type": "gpt_neox",
18
+ "num_attention_heads": 8,
19
+ "num_hidden_layers": 6,
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:b21dc46a79e29fd0d0f5ac656640c2a1a69527499429b538cca0251dc7b75e33
3
+ size 286484420
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f47f6a151c7d08f2b78325cdccdcccab38b24c804053aeb0e461d7a33af8d15e
3
+ size 291282435
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3331f28522b9fa13d93f24e9b31ba649dfb63fcd9a0d0cbc599c5cf36e258e46
3
+ size 80425929
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71bd49c67857a5cc16807ec555973d6a44f2488d30f5bfbf8dadc9d08221d715
3
+ size 75476752
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f16210beb90a49861d0bbab3c03b3efeabd2419dcb77a1900255c44ee424860b
3
+ size 286492426
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af9f258a1d4c015049ba2562d294b43f6f6b9cf58577e1fd4624d46940562e21
3
+ size 75486762
quantize_config.json ADDED
@@ -0,0 +1,106 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "GatherElements",
8
+ "Expand",
9
+ "Tile",
10
+ "ReduceMean",
11
+ "Cast",
12
+ "Sub",
13
+ "Constant",
14
+ "Concat",
15
+ "Gather",
16
+ "Identity",
17
+ "Erf",
18
+ "Where",
19
+ "Softmax",
20
+ "ConstantOfShape",
21
+ "Shape",
22
+ "Squeeze",
23
+ "Neg",
24
+ "Div",
25
+ "Unsqueeze",
26
+ "Pow",
27
+ "MatMul",
28
+ "Slice",
29
+ "Range",
30
+ "Mul",
31
+ "Add",
32
+ "Sqrt",
33
+ "Transpose",
34
+ "Reshape"
35
+ ],
36
+ "weight_type": "QInt8"
37
+ },
38
+ "decoder_model_merged": {
39
+ "op_types": [
40
+ "GatherElements",
41
+ "Expand",
42
+ "Tile",
43
+ "ReduceMean",
44
+ "Cast",
45
+ "Sub",
46
+ "Constant",
47
+ "Concat",
48
+ "Gather",
49
+ "Identity",
50
+ "Erf",
51
+ "Where",
52
+ "Softmax",
53
+ "ConstantOfShape",
54
+ "Shape",
55
+ "Squeeze",
56
+ "If",
57
+ "Neg",
58
+ "Div",
59
+ "Unsqueeze",
60
+ "Pow",
61
+ "MatMul",
62
+ "Slice",
63
+ "Range",
64
+ "Mul",
65
+ "Add",
66
+ "Sqrt",
67
+ "Transpose",
68
+ "Reshape"
69
+ ],
70
+ "weight_type": "QInt8"
71
+ },
72
+ "decoder_with_past_model": {
73
+ "op_types": [
74
+ "GatherElements",
75
+ "Expand",
76
+ "Tile",
77
+ "ReduceMean",
78
+ "Cast",
79
+ "Sub",
80
+ "Constant",
81
+ "Concat",
82
+ "Gather",
83
+ "Identity",
84
+ "Erf",
85
+ "Where",
86
+ "Softmax",
87
+ "ConstantOfShape",
88
+ "Shape",
89
+ "Squeeze",
90
+ "Neg",
91
+ "Div",
92
+ "Unsqueeze",
93
+ "Pow",
94
+ "MatMul",
95
+ "Slice",
96
+ "Range",
97
+ "Mul",
98
+ "Add",
99
+ "Sqrt",
100
+ "Transpose",
101
+ "Reshape"
102
+ ],
103
+ "weight_type": "QInt8"
104
+ }
105
+ }
106
+ }
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
+ }