Hugging Face's logo

Xenova
/
pythia-70m-deduped

Text Generation
Transformers.js
ONNX
gpt_neox
Model card Files Community
Xenova HF staff commited on
Commit
b98bbd9
•
1 Parent(s): 7063482

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-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": 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 sha256:46cc63be2c9a71483d46f4061f3054606a1bdd6b77d1eeac926216ba057068a2
3
+ size 286484420
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:240d7de72ef81ebde27319c1f3b8ecf6172d54147802357af9f329819a6913d2
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 sha256:61a91eb5dc1194aebe8d068e9ab44165e3b636f19757349b9264274c86c5ba52
3
+ size 80425929
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16dea5731b5d07f50f744ef0f86e2df5f99ec4e46833b54d8ffdbbccc0817e0a
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:e6d7c0d870dc0d48fdb47b0167de5440cb307d9f89de5e4e401e0b3302ff0cdb
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:d170a6b5eeaced849402cca416d22242b2feb29192797a632745a66a2f8c8a0f
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
+ "ConstantOfShape",
8
+ "Tile",
9
+ "Div",
10
+ "Transpose",
11
+ "MatMul",
12
+ "Shape",
13
+ "Unsqueeze",
14
+ "Mul",
15
+ "Concat",
16
+ "Erf",
17
+ "Where",
18
+ "Gather",
19
+ "Squeeze",
20
+ "Constant",
21
+ "Slice",
22
+ "Reshape",
23
+ "Softmax",
24
+ "GatherElements",
25
+ "Sub",
26
+ "Identity",
27
+ "ReduceMean",
28
+ "Pow",
29
+ "Neg",
30
+ "Cast",
31
+ "Expand",
32
+ "Add",
33
+ "Range",
34
+ "Sqrt"
35
+ ],
36
+ "weight_type": "QInt8"
37
+ },
38
+ "decoder_model_merged": {
39
+ "op_types": [
40
+ "ConstantOfShape",
41
+ "Tile",
42
+ "Div",
43
+ "Transpose",
44
+ "MatMul",
45
+ "Shape",
46
+ "Unsqueeze",
47
+ "Mul",
48
+ "Concat",
49
+ "Erf",
50
+ "Where",
51
+ "Gather",
52
+ "Squeeze",
53
+ "Constant",
54
+ "Slice",
55
+ "Reshape",
56
+ "Softmax",
57
+ "If",
58
+ "Sub",
59
+ "GatherElements",
60
+ "Identity",
61
+ "ReduceMean",
62
+ "Pow",
63
+ "Neg",
64
+ "Cast",
65
+ "Expand",
66
+ "Add",
67
+ "Range",
68
+ "Sqrt"
69
+ ],
70
+ "weight_type": "QInt8"
71
+ },
72
+ "decoder_with_past_model": {
73
+ "op_types": [
74
+ "ConstantOfShape",
75
+ "Tile",
76
+ "Div",
77
+ "Transpose",
78
+ "MatMul",
79
+ "Shape",
80
+ "Unsqueeze",
81
+ "Mul",
82
+ "Concat",
83
+ "Erf",
84
+ "Where",
85
+ "Gather",
86
+ "Squeeze",
87
+ "Constant",
88
+ "Slice",
89
+ "Reshape",
90
+ "Softmax",
91
+ "GatherElements",
92
+ "Sub",
93
+ "Identity",
94
+ "ReduceMean",
95
+ "Pow",
96
+ "Neg",
97
+ "Cast",
98
+ "Expand",
99
+ "Add",
100
+ "Range",
101
+ "Sqrt"
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
+ }