Hugging Face's logo

Xenova
/
pythia-410m

Text Generation
Transformers.js
ONNX
gpt_neox
Model card Files
xet
Community
1
Xenova HF Staff commited on
Commit
3f16be1
·
1 Parent(s): f86c4fd

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",
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 sha256:06f1691dc6a6643db0154af12b8480d644f250ee3585a8718e16dbc0a49e0b3c
3
+ size 1627120429
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09740cdf7731e301ee2022d1e31426e5192b49a26cb415ec425cf4f6f841352a
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:c4dfbeb316620f92a60de598cfaa6edfc51718a260842be726cf943a67342ee0
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:f1b385729deeb2435efcb77acd5df3f8064c0d575510c291b0fa1fe6ecf89028
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:ca1dc0cba13021deda0a392b37e3ff95082834ca0d2ea88b956467c724ed9865
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 sha256:85d6ea340eaef5da8b89349a9354b78fd0f1c16f9797f2117b73b630656c3f3a
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
+ "Div",
8
+ "Neg",
9
+ "Shape",
10
+ "ConstantOfShape",
11
+ "Tile",
12
+ "Range",
13
+ "Gather",
14
+ "Softmax",
15
+ "Expand",
16
+ "Add",
17
+ "Squeeze",
18
+ "MatMul",
19
+ "Unsqueeze",
20
+ "Constant",
21
+ "Cast",
22
+ "Sub",
23
+ "GatherElements",
24
+ "Where",
25
+ "Pow",
26
+ "ReduceMean",
27
+ "Reshape",
28
+ "Concat",
29
+ "Transpose",
30
+ "Erf",
31
+ "Slice",
32
+ "Mul",
33
+ "Sqrt"
34
+ ],
35
+ "weight_type": "QInt8"
36
+ },
37
+ "decoder_model_merged": {
38
+ "op_types": [
39
+ "Div",
40
+ "Neg",
41
+ "If",
42
+ "Shape",
43
+ "ConstantOfShape",
44
+ "Tile",
45
+ "Range",
46
+ "Gather",
47
+ "Softmax",
48
+ "Expand",
49
+ "Add",
50
+ "Squeeze",
51
+ "MatMul",
52
+ "Unsqueeze",
53
+ "Constant",
54
+ "Cast",
55
+ "Sub",
56
+ "GatherElements",
57
+ "Where",
58
+ "Pow",
59
+ "ReduceMean",
60
+ "Reshape",
61
+ "Concat",
62
+ "Transpose",
63
+ "Erf",
64
+ "Slice",
65
+ "Mul",
66
+ "Sqrt"
67
+ ],
68
+ "weight_type": "QInt8"
69
+ },
70
+ "decoder_with_past_model": {
71
+ "op_types": [
72
+ "Div",
73
+ "Neg",
74
+ "Shape",
75
+ "ConstantOfShape",
76
+ "Tile",
77
+ "Range",
78
+ "Gather",
79
+ "Softmax",
80
+ "Expand",
81
+ "Add",
82
+ "Squeeze",
83
+ "MatMul",
84
+ "Unsqueeze",
85
+ "Constant",
86
+ "Cast",
87
+ "Sub",
88
+ "GatherElements",
89
+ "Where",
90
+ "Pow",
91
+ "ReduceMean",
92
+ "Reshape",
93
+ "Concat",
94
+ "Transpose",
95
+ "Erf",
96
+ "Slice",
97
+ "Mul",
98
+ "Sqrt"
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
+ }