Hugging Face's logo

Xenova
/
llama2.c-stories15M

Text Generation
Transformers.js
PyTorch
ONNX
Transformers
llama
Model card Files Community
2
Xenova HF staff commited on
Commit
1219d33
•
1 Parent(s): f014a9d

Upload 9 files

Browse files
Files changed (9) hide show
  1. generation_config.json +6 -0
  2. onnx/decoder_model.onnx +3 -0
  3. onnx/decoder_model_merged.onnx +3 -0
  4. onnx/decoder_model_merged_quantized.onnx +3 -0
  5. onnx/decoder_model_quantized.onnx +3 -0
  6. onnx/decoder_with_past_model.onnx +3 -0
  7. onnx/decoder_with_past_model_quantized.onnx +3 -0
  8. quantize_config.json +107 -0
  9. special_tokens_map.json +23 -0
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 sha256:0fff8a7fe61ffdacec9bfdc7f045bc60ee240c46d63e0c671dabab2a21944c46
3
+ size 97945098
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee3d45805b922adb525ec778db4b2692db680561df445eebc94fce85d88985e2
3
+ size 98260154
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ab44c99230849a428c3e3f7fb2e91b05f5b4642c19a1ec5d3877f8302cd1689
3
+ size 25528662
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a16c83ee7a1904271ba34b81d4f8e978cfd8cef34d99245e2453aff29d90c22
3
+ size 25098988
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62dc5b8e6580e7fff028c5bc2993598be53b0d8b28401206a648f3b75517bce8
3
+ size 97945415
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:652587ee72f73418d7816f093df492ad8005ddcf3fc970885f7658ade6a2bca8
3
+ size 25098621
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
+ "Unsqueeze",
8
+ "Sigmoid",
9
+ "Concat",
10
+ "Expand",
11
+ "Transpose",
12
+ "Shape",
13
+ "Range",
14
+ "Constant",
15
+ "Neg",
16
+ "If",
17
+ "Cast",
18
+ "Softmax",
19
+ "Gather",
20
+ "Add",
21
+ "Equal",
22
+ "Reshape",
23
+ "MatMul",
24
+ "ConstantOfShape",
25
+ "Div",
26
+ "Slice",
27
+ "Sub",
28
+ "Mul",
29
+ "Where",
30
+ "Less",
31
+ "Pow",
32
+ "ReduceMean",
33
+ "Sqrt",
34
+ "Squeeze",
35
+ "Identity"
36
+ ],
37
+ "weight_type": "QInt8"
38
+ },
39
+ "decoder_with_past_model": {
40
+ "op_types": [
41
+ "Unsqueeze",
42
+ "Sigmoid",
43
+ "Concat",
44
+ "Expand",
45
+ "Transpose",
46
+ "Shape",
47
+ "Range",
48
+ "Constant",
49
+ "Neg",
50
+ "If",
51
+ "Cast",
52
+ "Softmax",
53
+ "Gather",
54
+ "Add",
55
+ "Equal",
56
+ "Reshape",
57
+ "MatMul",
58
+ "ConstantOfShape",
59
+ "Div",
60
+ "Slice",
61
+ "Sub",
62
+ "Mul",
63
+ "Where",
64
+ "Pow",
65
+ "ReduceMean",
66
+ "Sqrt",
67
+ "Squeeze",
68
+ "Identity"
69
+ ],
70
+ "weight_type": "QInt8"
71
+ },
72
+ "decoder_model": {
73
+ "op_types": [
74
+ "Unsqueeze",
75
+ "Sigmoid",
76
+ "Concat",
77
+ "Expand",
78
+ "Transpose",
79
+ "Shape",
80
+ "Range",
81
+ "Constant",
82
+ "Neg",
83
+ "If",
84
+ "Cast",
85
+ "Softmax",
86
+ "Gather",
87
+ "Add",
88
+ "Equal",
89
+ "Reshape",
90
+ "MatMul",
91
+ "ConstantOfShape",
92
+ "Div",
93
+ "Slice",
94
+ "Sub",
95
+ "Mul",
96
+ "Where",
97
+ "Less",
98
+ "Pow",
99
+ "ReduceMean",
100
+ "Sqrt",
101
+ "Squeeze",
102
+ "Identity"
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
+ }