Hugging Face's logo

Xenova
/
llama2.c-stories110M

Text Generation
Transformers.js
PyTorch
ONNX
Transformers
llama
Model card Files Community
Xenova HF staff commited on
Commit
41b5565
•
1 Parent(s): f4947f4

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. config.json +2 -2
  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 +107 -0
  10. special_tokens_map.json +23 -0
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "Xenova/llama2.c",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
@@ -8,7 +8,7 @@
8
  "hidden_act": "silu",
9
  "hidden_size": 768,
10
  "initializer_range": 0.02,
11
- "intermediate_size": 768,
12
  "max_position_embeddings": 1024,
13
  "model_type": "llama",
14
  "num_attention_heads": 12,
 
1
  {
2
+ "_name_or_path": "../llama2.c-stories110M",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
8
  "hidden_act": "silu",
9
  "hidden_size": 768,
10
  "initializer_range": 0.02,
11
+ "intermediate_size": 2048,
12
  "max_position_embeddings": 1024,
13
  "model_type": "llama",
14
  "num_attention_heads": 12,
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.32.0.dev0"
6
+ }
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5e2b243114cc61be8bf88035c2ad85b879a298177bdb31c98582e4d8e8fa222
3
+ size 537368189
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:868aa85e2ef1c5021cbf43c57a4bab855047f917cf73de5861a27c2992c66fd9
3
+ size 538320735
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2526b5fbf36a866575131e95cf2c0a75fe7a03948e32eba5a05c25cdc1814dc2
3
+ size 137148580
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e17c1ec579472eab18b12e182816011631dc488f1f03b4da1318300b0e4e43b
3
+ size 135970716
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e8a33b0ab5193433d1ed4660a27337421bbbfdf28f1ad92517dfa7c772a5b0f
3
+ size 537375208
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aff8a3d2b8d73fbadbe90c4e86c575a0560b6b9b6fd664a163abde6622aa5209
3
+ size 135979037
quantize_config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "decoder_model_merged": {
6
+ "op_types": [
7
+ "Slice",
8
+ "Sqrt",
9
+ "ConstantOfShape",
10
+ "Softmax",
11
+ "Sigmoid",
12
+ "Equal",
13
+ "Pow",
14
+ "Unsqueeze",
15
+ "Concat",
16
+ "Sub",
17
+ "Div",
18
+ "Constant",
19
+ "Expand",
20
+ "Cast",
21
+ "Range",
22
+ "Reshape",
23
+ "If",
24
+ "Where",
25
+ "Transpose",
26
+ "Identity",
27
+ "Mul",
28
+ "Shape",
29
+ "Add",
30
+ "ReduceMean",
31
+ "MatMul",
32
+ "Less",
33
+ "Gather",
34
+ "Neg",
35
+ "Squeeze"
36
+ ],
37
+ "weight_type": "QInt8"
38
+ },
39
+ "decoder_with_past_model": {
40
+ "op_types": [
41
+ "Slice",
42
+ "Sqrt",
43
+ "Squeeze",
44
+ "Softmax",
45
+ "Sigmoid",
46
+ "Equal",
47
+ "Pow",
48
+ "Unsqueeze",
49
+ "Concat",
50
+ "Sub",
51
+ "Div",
52
+ "Constant",
53
+ "Expand",
54
+ "Cast",
55
+ "Range",
56
+ "Reshape",
57
+ "Where",
58
+ "If",
59
+ "Transpose",
60
+ "Identity",
61
+ "Mul",
62
+ "Shape",
63
+ "Add",
64
+ "ReduceMean",
65
+ "MatMul",
66
+ "Gather",
67
+ "Neg",
68
+ "ConstantOfShape"
69
+ ],
70
+ "weight_type": "QInt8"
71
+ },
72
+ "decoder_model": {
73
+ "op_types": [
74
+ "Slice",
75
+ "Sqrt",
76
+ "ConstantOfShape",
77
+ "Softmax",
78
+ "Sigmoid",
79
+ "Equal",
80
+ "Pow",
81
+ "Unsqueeze",
82
+ "Concat",
83
+ "Sub",
84
+ "Div",
85
+ "Constant",
86
+ "Expand",
87
+ "Range",
88
+ "Cast",
89
+ "Reshape",
90
+ "Where",
91
+ "If",
92
+ "Transpose",
93
+ "Identity",
94
+ "Mul",
95
+ "Shape",
96
+ "Add",
97
+ "ReduceMean",
98
+ "MatMul",
99
+ "Less",
100
+ "Gather",
101
+ "Neg",
102
+ "Squeeze"
103
+ ],
104
+ "weight_type": "QInt8"
105
+ }
106
+ }
107
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }