Xenova HF staff commited on
Commit
8952e75
1 Parent(s): 8b3d0d7

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/pythia-14m",
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": 128,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 512,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 2048,
17
+ "model_type": "gpt_neox",
18
+ "num_attention_heads": 4,
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 sha256:4493588ab3607d8deee6cc89a8069b0c9a4fca7ec71c5e3c6457eb478d4005e4
3
+ size 60927797
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:981aa1bc03a43619dd17acf4d51b57f87047db3dd993ffddb97cacae2095fa27
3
+ size 65594546
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0ff0ab5739507c803e2c310da42b70e72061787ef16de8373edd42ae2fd751f
3
+ size 23722425
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7929b6dcb7dc117b1b56718ad8477bffc5fc748c405c56343d606317d90be6e2
3
+ size 18904628
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:495534129e110107b6bc7fd51bb2ee439740400e505300efc86257eec115c8a9
3
+ size 60935803
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:945f3e57b3190848e488540de312e0f0961a32d676d52db01493a6a5e15fa073
3
+ size 18914638
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
+ "Expand",
8
+ "Tile",
9
+ "Softmax",
10
+ "Neg",
11
+ "Concat",
12
+ "Range",
13
+ "Add",
14
+ "GatherElements",
15
+ "Shape",
16
+ "ConstantOfShape",
17
+ "Div",
18
+ "MatMul",
19
+ "Squeeze",
20
+ "Cast",
21
+ "Mul",
22
+ "Sqrt",
23
+ "ReduceMean",
24
+ "Transpose",
25
+ "Constant",
26
+ "Sub",
27
+ "Where",
28
+ "Erf",
29
+ "Pow",
30
+ "Reshape",
31
+ "Unsqueeze",
32
+ "Gather",
33
+ "Slice",
34
+ "Identity"
35
+ ],
36
+ "weight_type": "QInt8"
37
+ },
38
+ "decoder_model_merged": {
39
+ "op_types": [
40
+ "Expand",
41
+ "Tile",
42
+ "Softmax",
43
+ "Neg",
44
+ "Concat",
45
+ "Range",
46
+ "If",
47
+ "Add",
48
+ "GatherElements",
49
+ "Shape",
50
+ "ConstantOfShape",
51
+ "Div",
52
+ "MatMul",
53
+ "Squeeze",
54
+ "Cast",
55
+ "Mul",
56
+ "Sqrt",
57
+ "ReduceMean",
58
+ "Transpose",
59
+ "Constant",
60
+ "Sub",
61
+ "Where",
62
+ "Erf",
63
+ "Pow",
64
+ "Reshape",
65
+ "Unsqueeze",
66
+ "Gather",
67
+ "Slice",
68
+ "Identity"
69
+ ],
70
+ "weight_type": "QInt8"
71
+ },
72
+ "decoder_with_past_model": {
73
+ "op_types": [
74
+ "Expand",
75
+ "Tile",
76
+ "Softmax",
77
+ "Neg",
78
+ "Concat",
79
+ "Range",
80
+ "Add",
81
+ "GatherElements",
82
+ "Shape",
83
+ "ConstantOfShape",
84
+ "Div",
85
+ "MatMul",
86
+ "Squeeze",
87
+ "Cast",
88
+ "Mul",
89
+ "Sqrt",
90
+ "ReduceMean",
91
+ "Transpose",
92
+ "Constant",
93
+ "Sub",
94
+ "Where",
95
+ "Erf",
96
+ "Pow",
97
+ "Reshape",
98
+ "Unsqueeze",
99
+ "Gather",
100
+ "Slice",
101
+ "Identity"
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
+ }