Hugging Face's logo

Xenova
/
LaMini-Neo-125M

Text Generation
Transformers.js
ONNX
gpt_neo
Model card Files Community
Xenova HF staff commited on
Commit
7ee5ab0
•
1 Parent(s): 5e6b07a

Upload folder using huggingface_hub

Browse files
Files changed (9) 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 +88 -0
config.json CHANGED
@@ -47,7 +47,7 @@
47
  "summary_proj_to_labels": true,
48
  "summary_type": "cls_index",
49
  "summary_use_proj": true,
50
- "transformers_version": "4.29.2",
51
  "use_cache": false,
52
  "vocab_size": 50258,
53
  "window_size": 256
 
47
  "summary_proj_to_labels": true,
48
  "summary_type": "cls_index",
49
  "summary_use_proj": true,
50
+ "transformers_version": "4.33.0.dev0",
51
  "use_cache": false,
52
  "vocab_size": 50258,
53
  "window_size": 256
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:b0f586629a5c1dc00495a85d2f5c0a0bdfeca920efed9d81beff576e4cfe90db
3
- size 663875781
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:495a71c1e0b3bab2635b246850881ef27a3101b01b5ae000ca0b3918098efbbe
3
+ size 509481664
onnx/decoder_model_merged.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a22d3658b34dce337faf404ae6676be07ea8b4067b6d62a3c822f11b01ae04bb
3
- size 664181010
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9be8abd3ce0240b3b0dd9cdaa378f4f00ea1427abf12a10b1478ba68bc19684
3
+ size 518173878
onnx/decoder_model_merged_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:73f9cda9618743ee5334a2fc840fac348e4fde2ef207f9df9ca82059ea3d3637
3
- size 174104756
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c738a0bebd9cae8408ed1941192bd7cce35140997c8f42fca632dda543d1465
3
+ size 143638305
onnx/decoder_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1de292dc884bcee7c288153692142da949633eef0dc0433a311af2cf8acaf6dd
3
- size 173615198
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e53834a268d833c5efdc3b890c074806055f093e0d69cc0fa3f469c36dec1cf7
3
+ size 134762955
onnx/decoder_with_past_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a31ee7af77875693df54e37562d40795077f93bd4f60b597bfd2a22f8418f4c
3
- size 663883544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:423da608d177bea869d8a6683b55097b8de1616ee8a1cb0d1774f1267ebc94cb
3
+ size 509489427
onnx/decoder_with_past_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cea7873f398d5a4f7af7d7315d65689781725b2fce5cea9118c184589fcb0cb6
3
- size 173624782
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3771be8da093ba69bf84a3847f7bec486acd2f5bdb2ebb37b8f03499b3084ed
3
+ size 134772539
quantize_config.json ADDED
@@ -0,0 +1,88 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": true,
3
+ "reduce_range": true,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Tanh",
8
+ "Slice",
9
+ "MatMul",
10
+ "Div",
11
+ "Shape",
12
+ "ReduceMean",
13
+ "Concat",
14
+ "Squeeze",
15
+ "Constant",
16
+ "Reshape",
17
+ "Mul",
18
+ "Where",
19
+ "Range",
20
+ "Gather",
21
+ "Sqrt",
22
+ "Pow",
23
+ "Transpose",
24
+ "Cast",
25
+ "Sub",
26
+ "Unsqueeze",
27
+ "Add",
28
+ "Softmax"
29
+ ],
30
+ "weight_type": "QInt8"
31
+ },
32
+ "decoder_model_merged": {
33
+ "op_types": [
34
+ "Tanh",
35
+ "Slice",
36
+ "MatMul",
37
+ "Div",
38
+ "Shape",
39
+ "ReduceMean",
40
+ "Concat",
41
+ "Squeeze",
42
+ "Constant",
43
+ "Reshape",
44
+ "Mul",
45
+ "Where",
46
+ "Range",
47
+ "Gather",
48
+ "Sqrt",
49
+ "Pow",
50
+ "Transpose",
51
+ "Cast",
52
+ "Sub",
53
+ "Unsqueeze",
54
+ "Add",
55
+ "If",
56
+ "Softmax"
57
+ ],
58
+ "weight_type": "QInt8"
59
+ },
60
+ "decoder_with_past_model": {
61
+ "op_types": [
62
+ "Tanh",
63
+ "Slice",
64
+ "MatMul",
65
+ "Div",
66
+ "Shape",
67
+ "ReduceMean",
68
+ "Concat",
69
+ "Squeeze",
70
+ "Constant",
71
+ "Reshape",
72
+ "Mul",
73
+ "Where",
74
+ "Range",
75
+ "Gather",
76
+ "Sqrt",
77
+ "Pow",
78
+ "Transpose",
79
+ "Cast",
80
+ "Sub",
81
+ "Unsqueeze",
82
+ "Add",
83
+ "Softmax"
84
+ ],
85
+ "weight_type": "QInt8"
86
+ }
87
+ }
88
+ }