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
9c1c58e
•
1 Parent(s): 2b0007b

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. config.json +1 -0
  2. generation_config.json +1 -1
  3. onnx/decoder_model.onnx +1 -1
  4. onnx/decoder_model_merged.onnx +1 -1
  5. onnx/decoder_model_merged_quantized.onnx +1 -1
  6. onnx/decoder_model_quantized.onnx +1 -1
  7. onnx/decoder_with_past_model.onnx +1 -1
  8. onnx/decoder_with_past_model_quantized.onnx +1 -1
  9. quantize_config.json +70 -70
config.json CHANGED
@@ -1,4 +1,5 @@
1
  {
 
2
  "architectures": [
3
  "LlamaForCausalLM"
4
  ],
 
1
  {
2
+ "_name_or_path": "Xenova/llama2.c-stories110M",
3
  "architectures": [
4
  "LlamaForCausalLM"
5
  ],
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
- "transformers_version": "4.33.0.dev0"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 1,
4
  "eos_token_id": 2,
5
+ "transformers_version": "4.34.0.dev0"
6
  }
onnx/decoder_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5e2b243114cc61be8bf88035c2ad85b879a298177bdb31c98582e4d8e8fa222
3
  size 537368189
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:518f877e2dccc56ad030d9720872f2ac692b61835e31e116ffb285582384c623
3
  size 537368189
onnx/decoder_model_merged.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c076e620480ce241d3a15e5271e6f7852d804190b0d52673449d5b9cf80052d7
3
  size 538320735
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d591ab765b32cfefa5586ac7a7b5577240195902b70e39c903d9bac4f1acd4b0
3
  size 538320735
onnx/decoder_model_merged_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33696a9f854ce32f34b0ec1bf033379514bf427258b6747eafb2da6e1798ccf2
3
  size 136511989
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4fb65533cebf47090f460b15dfadf306db447e9ec5bcf3735f6299e59a020ea
3
  size 136511989
onnx/decoder_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:969bc1893a6b71eeaaea45821666ff947e6260c867cb1da06e47cb6728f28948
3
  size 135334125
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ca251aacafd0bc97b73272fa713f888b84507269c83a85420f17af2fa595bd5
3
  size 135334125
onnx/decoder_with_past_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4e8a33b0ab5193433d1ed4660a27337421bbbfdf28f1ad92517dfa7c772a5b0f
3
  size 537375208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b700555c3d04fa980bd6a55518ed2474f47e7bd9dfb60ace122e9d61694a471
3
  size 537375208
onnx/decoder_with_past_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8fef387f70bb057d890c11585f1950c9bd5c633e60afa0ce380b1389cca267a9
3
  size 135342446
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:405c4a5918d015b814a8e94f4c19c31c6eee15579e71c9b23dd25bcaef48d75c
3
  size 135342446
quantize_config.json CHANGED
@@ -4,102 +4,102 @@
4
  "per_model_config": {
5
  "decoder_model": {
6
  "op_types": [
7
- "Unsqueeze",
8
- "Sub",
9
- "Sigmoid",
10
- "If",
11
- "Shape",
12
- "Transpose",
13
- "Slice",
14
- "ReduceMean",
15
  "Concat",
16
- "Reshape",
17
- "Range",
18
- "Mul",
19
- "Identity",
 
 
20
  "Softmax",
 
 
 
 
21
  "Pow",
22
- "Add",
23
- "Div",
24
  "Equal",
25
- "Neg",
26
- "Constant",
27
- "MatMul",
28
- "ConstantOfShape",
29
  "Gather",
30
- "Where",
 
 
 
31
  "Squeeze",
32
- "Cast",
33
- "Less",
34
- "Expand",
35
- "Sqrt"
36
  ],
37
  "weight_type": "QInt8"
38
  },
39
- "decoder_model_merged": {
40
  "op_types": [
41
- "Unsqueeze",
42
- "Sub",
43
- "Sigmoid",
44
- "If",
45
- "Shape",
46
- "Transpose",
47
- "Slice",
48
- "ReduceMean",
49
  "Concat",
50
- "Reshape",
51
- "Range",
52
- "Mul",
53
- "Identity",
 
54
  "Softmax",
 
 
 
 
55
  "Pow",
56
- "Add",
57
- "Div",
58
  "Equal",
59
- "Neg",
60
- "Constant",
61
- "MatMul",
62
- "ConstantOfShape",
63
  "Gather",
64
- "Where",
 
 
 
65
  "Squeeze",
66
- "Cast",
67
- "Less",
68
- "Expand",
69
- "Sqrt"
70
  ],
71
  "weight_type": "QInt8"
72
  },
73
- "decoder_with_past_model": {
74
  "op_types": [
75
- "Unsqueeze",
76
- "Sub",
77
- "Sigmoid",
78
- "If",
79
- "Shape",
80
- "Transpose",
81
- "Slice",
82
- "ReduceMean",
83
  "Concat",
84
- "Reshape",
85
- "Mul",
86
- "Identity",
 
 
 
87
  "Softmax",
 
 
 
 
88
  "Pow",
89
- "Add",
90
- "Div",
91
  "Equal",
92
- "Neg",
93
- "Constant",
94
- "MatMul",
95
- "ConstantOfShape",
96
  "Gather",
97
- "Where",
98
- "Squeeze",
99
- "Cast",
100
  "Range",
101
- "Expand",
102
- "Sqrt"
 
 
 
 
 
103
  ],
104
  "weight_type": "QInt8"
105
  }
 
4
  "per_model_config": {
5
  "decoder_model": {
6
  "op_types": [
 
 
 
 
 
 
 
 
7
  "Concat",
8
+ "Where",
9
+ "Less",
10
+ "ConstantOfShape",
11
+ "Neg",
12
+ "Sqrt",
13
+ "Div",
14
  "Softmax",
15
+ "MatMul",
16
+ "Slice",
17
+ "Reshape",
18
+ "Shape",
19
  "Pow",
20
+ "Cast",
 
21
  "Equal",
22
+ "Add",
23
+ "Expand",
24
+ "Mul",
25
+ "Sub",
26
  "Gather",
27
+ "Identity",
28
+ "Range",
29
+ "Transpose",
30
+ "Constant",
31
  "Squeeze",
32
+ "If",
33
+ "ReduceMean",
34
+ "Sigmoid",
35
+ "Unsqueeze"
36
  ],
37
  "weight_type": "QInt8"
38
  },
39
+ "decoder_with_past_model": {
40
  "op_types": [
 
 
 
 
 
 
 
 
41
  "Concat",
42
+ "Where",
43
+ "ConstantOfShape",
44
+ "Neg",
45
+ "Sqrt",
46
+ "Div",
47
  "Softmax",
48
+ "MatMul",
49
+ "Slice",
50
+ "Reshape",
51
+ "Shape",
52
  "Pow",
53
+ "Cast",
 
54
  "Equal",
55
+ "Add",
56
+ "Expand",
57
+ "Mul",
58
+ "Sub",
59
  "Gather",
60
+ "Identity",
61
+ "Range",
62
+ "Transpose",
63
+ "Constant",
64
  "Squeeze",
65
+ "If",
66
+ "ReduceMean",
67
+ "Sigmoid",
68
+ "Unsqueeze"
69
  ],
70
  "weight_type": "QInt8"
71
  },
72
+ "decoder_model_merged": {
73
  "op_types": [
 
 
 
 
 
 
 
 
74
  "Concat",
75
+ "Where",
76
+ "Less",
77
+ "ConstantOfShape",
78
+ "Neg",
79
+ "Sqrt",
80
+ "Div",
81
  "Softmax",
82
+ "MatMul",
83
+ "Slice",
84
+ "Reshape",
85
+ "Shape",
86
  "Pow",
87
+ "Cast",
 
88
  "Equal",
89
+ "Add",
90
+ "Expand",
91
+ "Mul",
92
+ "Sub",
93
  "Gather",
94
+ "Identity",
 
 
95
  "Range",
96
+ "Transpose",
97
+ "Constant",
98
+ "Squeeze",
99
+ "If",
100
+ "ReduceMean",
101
+ "Sigmoid",
102
+ "Unsqueeze"
103
  ],
104
  "weight_type": "QInt8"
105
  }