Hugging Face's logo

Xenova
/
pythia-410m-deduped

Text Generation
Transformers.js
ONNX
gpt_neox
Model card Files Community
Xenova HF staff commited on
Commit
b87db57
•
1 Parent(s): 94dee0e

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-410m-deduped",
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": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 2048,
17
+ "model_type": "gpt_neox",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 24,
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:a0bece2d2ffe9746acc106090dc9ec1a1468f9f4e09272e5cee67dfaa6543c15
3
+ size 1627120429
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2d0659393b03ce6eaae11c98eebd1f07d9a964fdb63e9796e570b69f825c727
3
+ size 1632932561
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7db236d6ac9abd19b0859900ccc87d40e184890c1c623330f86a3396f533716e
3
+ size 419075399
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bea4445a931ed87b1b735828e1b236ed26febf6d8324e30ff36438ae932fb9f0
3
+ size 412669991
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e227075ae7994c5c7440041409be7db623c5cb0a84a0e3419d05822af66bc987
3
+ size 1627150291
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57ce7365e98b28099fae41664f17ef583b196c72338a078ec5264d3eaaf2037d
3
+ size 412708298
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
+ "MatMul",
8
+ "Slice",
9
+ "ConstantOfShape",
10
+ "Neg",
11
+ "ReduceMean",
12
+ "Squeeze",
13
+ "Erf",
14
+ "Add",
15
+ "Where",
16
+ "Range",
17
+ "Softmax",
18
+ "Cast",
19
+ "Transpose",
20
+ "Mul",
21
+ "Tile",
22
+ "Reshape",
23
+ "Sqrt",
24
+ "Expand",
25
+ "GatherElements",
26
+ "Concat",
27
+ "Div",
28
+ "Gather",
29
+ "Pow",
30
+ "Constant",
31
+ "Shape",
32
+ "Sub",
33
+ "Unsqueeze"
34
+ ],
35
+ "weight_type": "QInt8"
36
+ },
37
+ "decoder_model_merged": {
38
+ "op_types": [
39
+ "MatMul",
40
+ "Slice",
41
+ "ConstantOfShape",
42
+ "Neg",
43
+ "ReduceMean",
44
+ "Squeeze",
45
+ "Erf",
46
+ "Add",
47
+ "Where",
48
+ "If",
49
+ "Range",
50
+ "Softmax",
51
+ "Cast",
52
+ "Transpose",
53
+ "Mul",
54
+ "Tile",
55
+ "Reshape",
56
+ "Sqrt",
57
+ "Expand",
58
+ "GatherElements",
59
+ "Concat",
60
+ "Div",
61
+ "Gather",
62
+ "Pow",
63
+ "Constant",
64
+ "Shape",
65
+ "Sub",
66
+ "Unsqueeze"
67
+ ],
68
+ "weight_type": "QInt8"
69
+ },
70
+ "decoder_with_past_model": {
71
+ "op_types": [
72
+ "MatMul",
73
+ "Slice",
74
+ "ConstantOfShape",
75
+ "Neg",
76
+ "ReduceMean",
77
+ "Squeeze",
78
+ "Erf",
79
+ "Add",
80
+ "Where",
81
+ "Range",
82
+ "Softmax",
83
+ "Cast",
84
+ "Transpose",
85
+ "Mul",
86
+ "Tile",
87
+ "Reshape",
88
+ "Sqrt",
89
+ "Expand",
90
+ "GatherElements",
91
+ "Concat",
92
+ "Div",
93
+ "Gather",
94
+ "Pow",
95
+ "Constant",
96
+ "Shape",
97
+ "Sub",
98
+ "Unsqueeze"
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
+ }