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
f2c6857
•
1 Parent(s): 08c1c9e

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 +64 -64
config.json CHANGED
@@ -1,4 +1,5 @@
1
  {
 
2
  "architectures": [
3
  "LlamaForCausalLM"
4
  ],
 
1
  {
2
+ "_name_or_path": "Xenova/llama2.c-stories42M",
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:e54c6f935c3f8cbe2c9eaf180f1cd18f3314d512261e3d9ffff8ccf4f7e0affd
3
  size 233102386
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57fecedae457d1811cd12abe22589f313aa15c1590e1e09bae3408052e6a74c7
3
  size 233102386
onnx/decoder_model_merged.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:680d2348fa9388e61979d8461735ad105d27e49bedb1601e6b25cd813ac38627
3
  size 233913496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46464ab95c2c94ad1e493d0ca7746763f367343fce80cdcf7d0036911947564c
3
  size 233913496
onnx/decoder_model_merged_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ecebda7e52b45e63820aba9fda9d9b285bff82c73c80f4ae828f3b6fd589e1de
3
  size 60022789
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afb16b73d5c4f6e825abedc3ce65298ecd567e29c75dc98cc7f7b8dbf9e00074
3
  size 60022789
onnx/decoder_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2127d1570779e6856453779104ef0fcf3115d10499e9a3d735cf8192f734c68
3
  size 59060350
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea09156167b318bfb6149e325a18c79e95e0948175dd3fb496da53ca0589f070
3
  size 59060350
onnx/decoder_with_past_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8337fdaae31edbf83ef8477c49374f4d7fba83cb72a3c335546ac85e73d5c82
3
  size 233104923
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47d1d207d61288f734b55448c70e5b344262c01087900f6c258b7805e0ed86a9
3
  size 233104923
onnx/decoder_with_past_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7feaf947dbef1d8a837620946880a29c64fae88b156d62434b785ead3e7c797a
3
  size 59062863
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca6889c5883f8686fd4ba12ee26e025b490d7ffcbe1408c8b92f766e3df6f199
3
  size 59062863
quantize_config.json CHANGED
@@ -4,102 +4,102 @@
4
  "per_model_config": {
5
  "decoder_model": {
6
  "op_types": [
7
- "Unsqueeze",
8
- "Concat",
9
- "Cast",
10
- "Identity",
11
- "Div",
12
- "Shape",
13
  "Softmax",
14
- "MatMul",
15
- "ConstantOfShape",
 
16
  "If",
17
- "Add",
 
 
18
  "Mul",
19
- "Less",
 
20
  "Slice",
21
- "Constant",
 
 
22
  "Range",
23
- "Sub",
24
- "Expand",
25
- "Pow",
 
 
26
  "Sigmoid",
27
  "Where",
28
- "Gather",
29
- "Neg",
30
  "Squeeze",
31
- "Equal",
32
- "ReduceMean",
33
- "Reshape",
34
- "Sqrt",
35
- "Transpose"
36
  ],
37
  "weight_type": "QInt8"
38
  },
39
- "decoder_model_merged": {
40
  "op_types": [
41
- "Unsqueeze",
42
- "Concat",
43
- "Cast",
44
- "Identity",
45
- "Div",
46
- "Shape",
47
  "Softmax",
48
- "MatMul",
49
- "ConstantOfShape",
 
50
  "If",
51
- "Add",
 
 
52
  "Mul",
53
- "Less",
 
54
  "Slice",
55
- "Constant",
 
56
  "Range",
57
- "Sub",
58
- "Expand",
59
- "Pow",
 
 
60
  "Sigmoid",
61
  "Where",
62
- "Gather",
63
- "Neg",
64
  "Squeeze",
65
- "Equal",
66
- "ReduceMean",
67
- "Reshape",
68
- "Sqrt",
69
- "Transpose"
70
  ],
71
  "weight_type": "QInt8"
72
  },
73
- "decoder_with_past_model": {
74
  "op_types": [
75
- "Unsqueeze",
76
- "Concat",
77
- "Cast",
78
- "Identity",
79
- "Div",
80
- "Shape",
81
  "Softmax",
82
- "MatMul",
83
- "ConstantOfShape",
 
84
  "If",
85
- "Add",
 
 
86
  "Mul",
 
 
87
  "Slice",
88
- "Constant",
 
 
89
  "Range",
90
- "Sub",
91
- "Expand",
92
- "Pow",
 
 
93
  "Sigmoid",
94
  "Where",
95
- "Gather",
96
- "Neg",
97
  "Squeeze",
98
- "Equal",
99
- "ReduceMean",
100
- "Reshape",
101
- "Sqrt",
102
- "Transpose"
103
  ],
104
  "weight_type": "QInt8"
105
  }
 
4
  "per_model_config": {
5
  "decoder_model": {
6
  "op_types": [
7
+ "Sub",
 
 
 
 
 
8
  "Softmax",
9
+ "Neg",
10
+ "Sqrt",
11
+ "Reshape",
12
  "If",
13
+ "Shape",
14
+ "Transpose",
15
+ "Pow",
16
  "Mul",
17
+ "MatMul",
18
+ "Gather",
19
  "Slice",
20
+ "Less",
21
+ "ReduceMean",
22
+ "Concat",
23
  "Range",
24
+ "Unsqueeze",
25
+ "Equal",
26
+ "Cast",
27
+ "ConstantOfShape",
28
+ "Add",
29
  "Sigmoid",
30
  "Where",
 
 
31
  "Squeeze",
32
+ "Constant",
33
+ "Identity",
34
+ "Div",
35
+ "Expand"
 
36
  ],
37
  "weight_type": "QInt8"
38
  },
39
+ "decoder_with_past_model": {
40
  "op_types": [
41
+ "Sub",
 
 
 
 
 
42
  "Softmax",
43
+ "Neg",
44
+ "Sqrt",
45
+ "Reshape",
46
  "If",
47
+ "Shape",
48
+ "Transpose",
49
+ "Pow",
50
  "Mul",
51
+ "MatMul",
52
+ "Gather",
53
  "Slice",
54
+ "ReduceMean",
55
+ "Concat",
56
  "Range",
57
+ "Unsqueeze",
58
+ "Equal",
59
+ "Cast",
60
+ "ConstantOfShape",
61
+ "Add",
62
  "Sigmoid",
63
  "Where",
 
 
64
  "Squeeze",
65
+ "Constant",
66
+ "Identity",
67
+ "Div",
68
+ "Expand"
 
69
  ],
70
  "weight_type": "QInt8"
71
  },
72
+ "decoder_model_merged": {
73
  "op_types": [
74
+ "Sub",
 
 
 
 
 
75
  "Softmax",
76
+ "Neg",
77
+ "Sqrt",
78
+ "Reshape",
79
  "If",
80
+ "Shape",
81
+ "Transpose",
82
+ "Pow",
83
  "Mul",
84
+ "MatMul",
85
+ "Gather",
86
  "Slice",
87
+ "Less",
88
+ "ReduceMean",
89
+ "Concat",
90
  "Range",
91
+ "Unsqueeze",
92
+ "Equal",
93
+ "Cast",
94
+ "ConstantOfShape",
95
+ "Add",
96
  "Sigmoid",
97
  "Where",
 
 
98
  "Squeeze",
99
+ "Constant",
100
+ "Identity",
101
+ "Div",
102
+ "Expand"
 
103
  ],
104
  "weight_type": "QInt8"
105
  }