Hugging Face's logo

Xenova
/
ipt-350m

Text Generation
Transformers.js
ONNX
mpt
custom_code
Model card Files Community
Xenova HF staff commited on
Commit
293d33e
•
1 Parent(s): 5d7686f

Upload folder using huggingface_hub

Browse files
Files changed (10) hide show
  1. config.json +1 -1
  2. generation_config.json +1 -1
  3. onnx/decoder_model.onnx +2 -2
  4. onnx/decoder_model_merged.onnx +2 -2
  5. onnx/decoder_model_merged_quantized.onnx +2 -2
  6. onnx/decoder_model_quantized.onnx +2 -2
  7. onnx/decoder_with_past_model.onnx +2 -2
  8. onnx/decoder_with_past_model_quantized.onnx +2 -2
  9. quantize_config.json +62 -62
  10. tokenizer.json +1 -0
config.json CHANGED
@@ -37,7 +37,7 @@
37
  "no_bias": true,
38
  "norm_type": "low_precision_layernorm",
39
  "resid_pdrop": 0.0,
40
- "transformers_version": "4.32.1",
41
  "use_cache": false,
42
  "verbose": 0,
43
  "vocab_size": 50432
 
37
  "no_bias": true,
38
  "norm_type": "low_precision_layernorm",
39
  "resid_pdrop": 0.0,
40
+ "transformers_version": "4.33.0.dev0",
41
  "use_cache": false,
42
  "verbose": 0,
43
  "vocab_size": 50432
generation_config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
  "_from_model_config": true,
3
- "transformers_version": "4.32.1",
4
  "use_cache": false
5
  }
 
1
  {
2
  "_from_model_config": true,
3
+ "transformers_version": "4.33.0.dev0",
4
  "use_cache": false
5
  }
onnx/decoder_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e434ce50a6b81fd4b234c5d4b1d29bdd0c48e1dca27c435d3f76b5d0f6f030f
3
- size 1621899428
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ef3885afff8c3a3e0a7f10a662556410b3059f14faa89961e166e51ef63c4e2
3
+ size 1415330022
onnx/decoder_model_merged.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3d5e8f131d5aac51c90315ce723147eb7b7d875fb7d7c7fdd7eb98123ce13bb
3
- size 1622503619
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e16283f568a32bd8e9f8716e21a5af318e6ba5438b82d76a13265a4661494fc
3
+ size 1415934308
onnx/decoder_model_merged_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:620cfd14fb3e3618226e8468406c55a17b2a11ee417e47a18855d4fb264589f7
3
- size 408595992
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95fdbeec3fc8c6116c41b2153af4de72ca014a3466fa24b1edbf8904af9bae39
3
+ size 356700610
onnx/decoder_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a7a2ecfd618b43a6a816381bcb400696104217c1f541b8db7f891504337cd84c
3
- size 407714462
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:54baba9918925344934e39d5ccc30d10bba3da938240fed4a09e072c6323549d
3
+ size 355819455
onnx/decoder_with_past_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:54d7dc2514a0deceb5f70fd54c8e6f4a2a8bc5e78030f3f501fdc72985a8fd00
3
- size 1621900820
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:923d582c0e52660c047cae978a5288e45bab47ac4bd60829130ef68129d228d8
3
+ size 1415331414
onnx/decoder_with_past_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c636d0f47f3a5fc2b99b2a8c613bcafc7fa4fb2790a87b198ea94daaf4ebe9da
3
- size 407715249
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b26ef4475e8a6e5fff3fc6c76ca1a3fc84b7fff75734969f52c83055ce2ff5d
3
+ size 355820242
quantize_config.json CHANGED
@@ -2,99 +2,99 @@
2
  "per_channel": true,
3
  "reduce_range": true,
4
  "per_model_config": {
5
- "decoder_model_merged": {
6
  "op_types": [
7
- "Range",
8
- "If",
9
- "Concat",
10
- "Equal",
11
- "ReduceMean",
12
- "Sub",
13
- "Cast",
14
- "Mul",
15
- "Reshape",
16
  "ConstantOfShape",
17
- "MatMul",
 
 
18
  "Erf",
19
- "Gather",
20
- "Unsqueeze",
21
- "Expand",
22
- "Not",
23
- "Less",
24
  "Constant",
25
- "Slice",
26
  "ScatterND",
 
 
 
 
 
 
 
 
 
27
  "Div",
 
 
 
28
  "Shape",
29
- "Add",
30
- "Pow",
31
- "Softmax",
32
  "Sqrt",
33
- "Where",
34
- "Or",
35
- "Transpose"
36
  ],
37
  "weight_type": "QInt8"
38
  },
39
- "decoder_model": {
40
  "op_types": [
41
- "Range",
42
- "Concat",
43
- "Equal",
44
- "ReduceMean",
45
- "Sub",
46
- "Cast",
47
- "Mul",
48
- "Reshape",
49
  "ConstantOfShape",
50
- "MatMul",
 
 
51
  "Erf",
52
- "Gather",
53
- "Unsqueeze",
54
- "Expand",
55
- "Not",
56
- "Less",
57
  "Constant",
58
- "Slice",
59
  "ScatterND",
 
 
 
 
 
 
 
 
 
60
  "Div",
 
 
 
61
  "Shape",
62
- "Add",
63
- "Pow",
64
- "Softmax",
65
  "Sqrt",
66
- "Where",
67
- "Or",
68
- "Transpose"
69
  ],
70
  "weight_type": "QInt8"
71
  },
72
  "decoder_with_past_model": {
73
  "op_types": [
74
- "Concat",
75
- "Equal",
76
- "ReduceMean",
77
- "Sub",
78
- "Cast",
79
- "Mul",
80
- "Reshape",
81
  "ConstantOfShape",
82
- "MatMul",
 
 
83
  "Erf",
84
- "Gather",
 
 
 
85
  "Unsqueeze",
 
 
 
 
 
 
 
86
  "Expand",
87
  "Not",
88
- "Constant",
89
- "Slice",
90
- "Div",
91
  "Shape",
92
- "Add",
93
- "Pow",
94
- "Softmax",
95
  "Sqrt",
96
- "Where",
97
- "Transpose"
98
  ],
99
  "weight_type": "QInt8"
100
  }
 
2
  "per_channel": true,
3
  "reduce_range": true,
4
  "per_model_config": {
5
+ "decoder_model": {
6
  "op_types": [
7
+ "Or",
8
+ "Pow",
 
 
 
 
 
 
 
9
  "ConstantOfShape",
10
+ "Mul",
11
+ "Slice",
12
+ "Transpose",
13
  "Erf",
14
+ "MatMul",
15
+ "Cast",
 
 
 
16
  "Constant",
 
17
  "ScatterND",
18
+ "Sub",
19
+ "Unsqueeze",
20
+ "Range",
21
+ "Add",
22
+ "Equal",
23
+ "Concat",
24
+ "ReduceMean",
25
+ "Where",
26
+ "Less",
27
  "Div",
28
+ "Expand",
29
+ "Reshape",
30
+ "Not",
31
  "Shape",
32
+ "Gather",
 
 
33
  "Sqrt",
34
+ "Softmax"
 
 
35
  ],
36
  "weight_type": "QInt8"
37
  },
38
+ "decoder_model_merged": {
39
  "op_types": [
40
+ "Or",
41
+ "Pow",
 
 
 
 
 
 
42
  "ConstantOfShape",
43
+ "Mul",
44
+ "Slice",
45
+ "Transpose",
46
  "Erf",
47
+ "MatMul",
48
+ "Cast",
 
 
 
49
  "Constant",
 
50
  "ScatterND",
51
+ "Sub",
52
+ "Unsqueeze",
53
+ "Range",
54
+ "Add",
55
+ "Equal",
56
+ "Concat",
57
+ "ReduceMean",
58
+ "Where",
59
+ "Less",
60
  "Div",
61
+ "Expand",
62
+ "Reshape",
63
+ "Not",
64
  "Shape",
65
+ "If",
66
+ "Gather",
 
67
  "Sqrt",
68
+ "Softmax"
 
 
69
  ],
70
  "weight_type": "QInt8"
71
  },
72
  "decoder_with_past_model": {
73
  "op_types": [
74
+ "Pow",
 
 
 
 
 
 
75
  "ConstantOfShape",
76
+ "Mul",
77
+ "Slice",
78
+ "Transpose",
79
  "Erf",
80
+ "MatMul",
81
+ "Cast",
82
+ "Constant",
83
+ "Sub",
84
  "Unsqueeze",
85
+ "Add",
86
+ "Equal",
87
+ "Concat",
88
+ "ReduceMean",
89
+ "Where",
90
+ "Div",
91
+ "Reshape",
92
  "Expand",
93
  "Not",
 
 
 
94
  "Shape",
95
+ "Gather",
 
 
96
  "Sqrt",
97
+ "Softmax"
 
98
  ],
99
  "weight_type": "QInt8"
100
  }
tokenizer.json CHANGED
@@ -50,6 +50,7 @@
50
  "continuing_subword_prefix": null,
51
  "end_of_word_suffix": null,
52
  "fuse_unk": false,
 
53
  "vocab": {
54
  "<|endoftext|>": 0,
55
  "<|padding|>": 1,
 
50
  "continuing_subword_prefix": null,
51
  "end_of_word_suffix": null,
52
  "fuse_unk": false,
53
+ "byte_fallback": false,
54
  "vocab": {
55
  "<|endoftext|>": 0,
56
  "<|padding|>": 1,