Hugging Face's logo

Xenova
/
llama2.c-stories42M

Text Generation
Transformers.js
PyTorch
ONNX
Transformers
llama
Model card Files Community
1
Xenova HF staff commited on
Commit
855721f
•
1 Parent(s): aebba98

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": 512,
10
  "initializer_range": 0.02,
11
- "intermediate_size": 768,
12
  "max_position_embeddings": 1024,
13
  "model_type": "llama",
14
  "num_attention_heads": 8,
 
1
  {
2
+ "_name_or_path": "../llama2.c-stories42M",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
 
8
  "hidden_act": "silu",
9
  "hidden_size": 512,
10
  "initializer_range": 0.02,
11
+ "intermediate_size": 1376,
12
  "max_position_embeddings": 1024,
13
  "model_type": "llama",
14
  "num_attention_heads": 8,
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:e54c6f935c3f8cbe2c9eaf180f1cd18f3314d512261e3d9ffff8ccf4f7e0affd
3
+ size 233102386
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:190cdba0b98ff17da3c0a78d1915e2f20fcb1dcda85534118dae98457a1bd096
3
+ size 233913496
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd282163cc50ff5ff40c1189b9a2fb62ee4dca855099fe24630499a7f64975a3
3
+ size 60395560
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e04d6800ef74d802667daae3848a11564e087c341e2002e4900b127eee3430c4
3
+ size 59433121
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8337fdaae31edbf83ef8477c49374f4d7fba83cb72a3c335546ac85e73d5c82
3
+ size 233104923
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49a1e8b52c690e3391bb86d143537a23fd9d35cfdf0a11e91c8a713c6c45c827
3
+ size 59435634
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
+ "Gather",
8
+ "Expand",
9
+ "Identity",
10
+ "Slice",
11
+ "MatMul",
12
+ "Softmax",
13
+ "Sqrt",
14
+ "Where",
15
+ "Constant",
16
+ "Range",
17
+ "Mul",
18
+ "Concat",
19
+ "Cast",
20
+ "Squeeze",
21
+ "Unsqueeze",
22
+ "ConstantOfShape",
23
+ "Sigmoid",
24
+ "Pow",
25
+ "Transpose",
26
+ "Reshape",
27
+ "Less",
28
+ "Div",
29
+ "Equal",
30
+ "Sub",
31
+ "If",
32
+ "Shape",
33
+ "ReduceMean",
34
+ "Neg",
35
+ "Add"
36
+ ],
37
+ "weight_type": "QInt8"
38
+ },
39
+ "decoder_with_past_model": {
40
+ "op_types": [
41
+ "Gather",
42
+ "Expand",
43
+ "Identity",
44
+ "MatMul",
45
+ "Slice",
46
+ "Softmax",
47
+ "Sqrt",
48
+ "Where",
49
+ "Constant",
50
+ "Range",
51
+ "Mul",
52
+ "Concat",
53
+ "Cast",
54
+ "Squeeze",
55
+ "Unsqueeze",
56
+ "ConstantOfShape",
57
+ "Sigmoid",
58
+ "Pow",
59
+ "Transpose",
60
+ "Reshape",
61
+ "Div",
62
+ "Equal",
63
+ "Sub",
64
+ "If",
65
+ "Shape",
66
+ "ReduceMean",
67
+ "Neg",
68
+ "Add"
69
+ ],
70
+ "weight_type": "QInt8"
71
+ },
72
+ "decoder_model": {
73
+ "op_types": [
74
+ "Gather",
75
+ "Expand",
76
+ "Identity",
77
+ "Slice",
78
+ "MatMul",
79
+ "Softmax",
80
+ "Sqrt",
81
+ "Where",
82
+ "Constant",
83
+ "Range",
84
+ "Mul",
85
+ "Concat",
86
+ "Cast",
87
+ "Squeeze",
88
+ "Unsqueeze",
89
+ "ConstantOfShape",
90
+ "Sigmoid",
91
+ "Pow",
92
+ "Transpose",
93
+ "Reshape",
94
+ "Less",
95
+ "Div",
96
+ "Equal",
97
+ "Sub",
98
+ "If",
99
+ "Shape",
100
+ "ReduceMean",
101
+ "Neg",
102
+ "Add"
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
+ }