Hugging Face's logo

teapotai
/
instruct-teapot

Text2Text Generation
Transformers
ONNX
t5
Inference Endpoints
Model card Files Community
Zakery Clarke commited on
Commit
c133a0b
·
1 Parent(s): 987f7e3

Flan Mini fine tuned

Browse files
Files changed (9) hide show
  1. README.md +7 -0
  2. config.json +1 -1
  3. generation_config.json +1 -1
  4. onnx/decoder_model.onnx +0 -3
  5. onnx/decoder_model_merged.onnx +0 -3
  6. onnx/decoder_with_past_model.onnx +0 -3
  7. onnx/encoder_model.onnx +0 -3
  8. quantize_config.json +139 -0
  9. spiece.model +0 -3
README.md ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers.js
3
+ ---
4
+
5
+ https://huggingface.co/MBZUAI/LaMini-Flan-T5-783M with ONNX weights to be compatible with Transformers.js.
6
+
7
+ Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using [🤗 Optimum](https://huggingface.co/docs/optimum/index) and structuring your repo like this one (with ONNX weights located in a subfolder named `onnx`).
config.json CHANGED
@@ -26,7 +26,7 @@
26
  "relative_attention_max_distance": 128,
27
  "relative_attention_num_buckets": 32,
28
  "tie_word_embeddings": false,
29
- "transformers_version": "4.33.2",
30
  "use_cache": true,
31
  "vocab_size": 32128
32
  }
 
26
  "relative_attention_max_distance": 128,
27
  "relative_attention_num_buckets": 32,
28
  "tie_word_embeddings": false,
29
+ "transformers_version": "4.34.0.dev0",
30
  "use_cache": true,
31
  "vocab_size": 32128
32
  }
generation_config.json CHANGED
@@ -3,5 +3,5 @@
3
  "decoder_start_token_id": 0,
4
  "eos_token_id": 1,
5
  "pad_token_id": 0,
6
- "transformers_version": "4.33.2"
7
  }
 
3
  "decoder_start_token_id": 0,
4
  "eos_token_id": 1,
5
  "pad_token_id": 0,
6
+ "transformers_version": "4.34.0.dev0"
7
  }
onnx/decoder_model.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0af2d5176759dac258e16aa9b5421584e608a20bb8d1234871df44bf7cf2ef05
3
- size 1899966097
 
 
 
 
onnx/decoder_model_merged.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:27a50e179d5d00261fd29170f82abd0545d7d6e8fc1c13d5f4d3115743c440d1
3
- size 1900612149
 
 
 
 
onnx/decoder_with_past_model.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:450dff530ac7190bac7689ecf04f1b5ba3cd484dee7ce073ca2a46009a4fdb2b
3
- size 1698575515
 
 
 
 
onnx/encoder_model.onnx DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c58209b472cdf3e7fea925f109fe7ee67d12d99368ccd8d18a18c75cce6a9e51
3
- size 1365283172
 
 
 
 
quantize_config.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Add",
8
+ "Less",
9
+ "ConstantOfShape",
10
+ "Mul",
11
+ "Pow",
12
+ "Gather",
13
+ "Shape",
14
+ "ReduceMean",
15
+ "MatMul",
16
+ "Range",
17
+ "Transpose",
18
+ "Neg",
19
+ "Expand",
20
+ "Sqrt",
21
+ "Min",
22
+ "Unsqueeze",
23
+ "Where",
24
+ "Div",
25
+ "Tile",
26
+ "Log",
27
+ "Concat",
28
+ "Cast",
29
+ "LessOrEqual",
30
+ "Reshape",
31
+ "Sub",
32
+ "Softmax",
33
+ "Tanh",
34
+ "Constant"
35
+ ],
36
+ "weight_type": "QInt8"
37
+ },
38
+ "encoder_model": {
39
+ "op_types": [
40
+ "Add",
41
+ "Abs",
42
+ "Less",
43
+ "ConstantOfShape",
44
+ "Mul",
45
+ "Pow",
46
+ "Gather",
47
+ "Shape",
48
+ "ReduceMean",
49
+ "MatMul",
50
+ "Range",
51
+ "Transpose",
52
+ "Sqrt",
53
+ "Min",
54
+ "Unsqueeze",
55
+ "Where",
56
+ "Div",
57
+ "Greater",
58
+ "Log",
59
+ "Concat",
60
+ "Cast",
61
+ "Reshape",
62
+ "Sub",
63
+ "Softmax",
64
+ "Tanh",
65
+ "Constant"
66
+ ],
67
+ "weight_type": "QInt8"
68
+ },
69
+ "decoder_model_merged": {
70
+ "op_types": [
71
+ "If",
72
+ "Add",
73
+ "Less",
74
+ "ConstantOfShape",
75
+ "Mul",
76
+ "Slice",
77
+ "Pow",
78
+ "Gather",
79
+ "Shape",
80
+ "ReduceMean",
81
+ "MatMul",
82
+ "Range",
83
+ "Transpose",
84
+ "Neg",
85
+ "Expand",
86
+ "Sqrt",
87
+ "Min",
88
+ "Unsqueeze",
89
+ "Where",
90
+ "Div",
91
+ "Tile",
92
+ "Log",
93
+ "Concat",
94
+ "Cast",
95
+ "LessOrEqual",
96
+ "Reshape",
97
+ "Sub",
98
+ "Softmax",
99
+ "Tanh",
100
+ "Constant"
101
+ ],
102
+ "weight_type": "QInt8"
103
+ },
104
+ "decoder_with_past_model": {
105
+ "op_types": [
106
+ "Add",
107
+ "Less",
108
+ "ConstantOfShape",
109
+ "Mul",
110
+ "Slice",
111
+ "Pow",
112
+ "Gather",
113
+ "Shape",
114
+ "ReduceMean",
115
+ "MatMul",
116
+ "Range",
117
+ "Transpose",
118
+ "Neg",
119
+ "Expand",
120
+ "Sqrt",
121
+ "Min",
122
+ "Unsqueeze",
123
+ "Where",
124
+ "Div",
125
+ "Tile",
126
+ "Log",
127
+ "Concat",
128
+ "Cast",
129
+ "LessOrEqual",
130
+ "Reshape",
131
+ "Sub",
132
+ "Softmax",
133
+ "Tanh",
134
+ "Constant"
135
+ ],
136
+ "weight_type": "QInt8"
137
+ }
138
+ }
139
+ }
spiece.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
3
- size 791656