Xenova HF staff commited on
Commit
e28f8d8
1 Parent(s): 44ed04f

Upload folder using huggingface_hub

Browse files
config.json CHANGED
@@ -32,7 +32,7 @@
32
  "max_length": 50
33
  }
34
  },
35
- "transformers_version": "4.29.2",
36
  "use_cache": false,
37
  "vocab_size": 50258
38
  }
 
32
  "max_length": 50
33
  }
34
  },
35
+ "transformers_version": "4.33.0.dev0",
36
  "use_cache": false,
37
  "vocab_size": 50258
38
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 50256,
4
  "eos_token_id": 50256,
5
- "transformers_version": "4.29.2"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 50256,
4
  "eos_token_id": 50256,
5
+ "transformers_version": "4.33.0.dev0"
6
  }
onnx/decoder_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:172330f94cca3e5bf5277001006fef7e8f6668b12c288bc3f7a29db3ff1d06c4
3
- size 653672944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1520a0c1c5906cc6b671c58ef1bc5176ff5cc71370a654177e9ba886299f25c7
3
+ size 499279048
onnx/decoder_model_merged.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6365e1a40457dfe4ba658f150e0084fb14509af8b9ee62257a778ef5e2062bf9
3
- size 654149001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e12b5a85ff73294f25424b586b2e30eb5ff624f5588f900e1842fd1548959d8
3
+ size 500802211
onnx/decoder_model_merged_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:797a697685dd90b6127f6650d21f4b75aca5acb9bd766d00c9f012ad32a935be
3
- size 166537607
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:681252b74d53cac63fa0f7d2587fc344a6a427fbf00c343afdda271e1b3dd3f0
3
+ size 128316534
onnx/decoder_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58c8c1442e9d35be65dc8983a0abfe8df0a2964a8883b6ab84f5c159bfcc46dc
3
- size 165824632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e712a0ca266106feedd5ba5d5f8ffca81d01dc96264b7bac1167c08bc4377ed3
3
+ size 126557648
onnx/decoder_with_past_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bcd9e2235e30e787bcb1b8c69dbb8737352a086aa1ae4fd7acbfea4083da907d
3
- size 653679752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c465a707b60f2884dfa9f050b987f8828e0710c39012e980ab20c618eb1291b
3
+ size 499285854
onnx/decoder_with_past_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1606821d81657dd5d3269318969dc34a801b9902177dc091f45e4933df997f6f
3
- size 165833682
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4697235e33836937afa8ec126f20dd02edae2746cb045d97fb02552b2fcfd88c
3
+ size 126566696
quantize_config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Softmax",
8
+ "Transpose",
9
+ "Cast",
10
+ "Where",
11
+ "Tanh",
12
+ "Gather",
13
+ "Constant",
14
+ "Range",
15
+ "Pow",
16
+ "Squeeze",
17
+ "Sqrt",
18
+ "Gemm",
19
+ "ConstantOfShape",
20
+ "Slice",
21
+ "Mul",
22
+ "Concat",
23
+ "Sub",
24
+ "Div",
25
+ "Unsqueeze",
26
+ "Reshape",
27
+ "Shape",
28
+ "Split",
29
+ "ReduceMean",
30
+ "MatMul",
31
+ "Add"
32
+ ],
33
+ "weight_type": "QInt8"
34
+ },
35
+ "decoder_model_merged": {
36
+ "op_types": [
37
+ "Softmax",
38
+ "Transpose",
39
+ "Cast",
40
+ "Where",
41
+ "Tanh",
42
+ "Gather",
43
+ "Constant",
44
+ "Range",
45
+ "Pow",
46
+ "Squeeze",
47
+ "Sqrt",
48
+ "Gemm",
49
+ "ConstantOfShape",
50
+ "Slice",
51
+ "Mul",
52
+ "Concat",
53
+ "Sub",
54
+ "Div",
55
+ "Unsqueeze",
56
+ "Reshape",
57
+ "Shape",
58
+ "Split",
59
+ "If",
60
+ "ReduceMean",
61
+ "MatMul",
62
+ "Add"
63
+ ],
64
+ "weight_type": "QInt8"
65
+ },
66
+ "decoder_with_past_model": {
67
+ "op_types": [
68
+ "Softmax",
69
+ "Transpose",
70
+ "Cast",
71
+ "Where",
72
+ "Tanh",
73
+ "Gather",
74
+ "Constant",
75
+ "Range",
76
+ "Pow",
77
+ "Squeeze",
78
+ "Sqrt",
79
+ "Gemm",
80
+ "ConstantOfShape",
81
+ "Slice",
82
+ "Mul",
83
+ "Concat",
84
+ "Sub",
85
+ "Div",
86
+ "Unsqueeze",
87
+ "Reshape",
88
+ "Shape",
89
+ "Split",
90
+ "ReduceMean",
91
+ "MatMul",
92
+ "Add"
93
+ ],
94
+ "weight_type": "QInt8"
95
+ }
96
+ }
97
+ }