Hugging Face's logo

Xenova
/
opt-125m

Text Generation
Transformers.js
ONNX
opt
Model card Files Community
Xenova HF staff commited on
Commit
cd365b8
•
1 Parent(s): 76a5ffe

Upload folder using huggingface_hub

Browse files
Files changed (14) hide show
  1. config.json +30 -0
  2. generation_config.json +7 -0
  3. merges.txt +0 -0
  4. onnx/decoder_model.onnx +3 -0
  5. onnx/decoder_model_merged.onnx +3 -0
  6. onnx/decoder_model_merged_quantized.onnx +3 -0
  7. onnx/decoder_model_quantized.onnx +3 -0
  8. onnx/decoder_with_past_model.onnx +3 -0
  9. onnx/decoder_with_past_model_quantized.onnx +3 -0
  10. quantize_config.json +107 -0
  11. special_tokens_map.json +30 -0
  12. tokenizer.json +0 -0
  13. tokenizer_config.json +40 -0
  14. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/opt-125m",
3
+ "_remove_final_layer_norm": false,
4
+ "activation_dropout": 0.0,
5
+ "activation_function": "relu",
6
+ "architectures": [
7
+ "OPTForCausalLM"
8
+ ],
9
+ "attention_dropout": 0.0,
10
+ "bos_token_id": 2,
11
+ "do_layer_norm_before": true,
12
+ "dropout": 0.1,
13
+ "enable_bias": true,
14
+ "eos_token_id": 2,
15
+ "ffn_dim": 3072,
16
+ "hidden_size": 768,
17
+ "init_std": 0.02,
18
+ "layer_norm_elementwise_affine": true,
19
+ "layerdrop": 0.0,
20
+ "max_position_embeddings": 2048,
21
+ "model_type": "opt",
22
+ "num_attention_heads": 12,
23
+ "num_hidden_layers": 12,
24
+ "pad_token_id": 1,
25
+ "prefix": "</s>",
26
+ "transformers_version": "4.34.0.dev0",
27
+ "use_cache": true,
28
+ "vocab_size": 50272,
29
+ "word_embed_proj_dim": 768
30
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 2,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 1,
6
+ "transformers_version": "4.34.0.dev0"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:defc8a7e4b956cec8e2f56a0105286df47d784de8561a09460cf98a13ae222ef
3
+ size 501287893
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6d6190ff3a9ff04c89ce893d1ddc572f572106b44b386ca136d3ad03bf05f0a
3
+ size 501617316
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1de5493939c6236c7f7162a4738600fb3b82a20d1d75250eb0399cf8d05a3023
3
+ size 126657726
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7327894360d3d15abe774168cc33de9e69154d0d7cf05575838ff8755b766f4
3
+ size 126132773
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d17967b27032cc2bba4924f64308882b83ede15483cb2a93d00ee01cfd4dc75
3
+ size 501288974
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b5b3e8bde352937077c78c17089b9fcec3344f92b6e16472e30fd0107ff9e54
3
+ size 126133129
quantize_config.json ADDED
@@ -0,0 +1,107 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_with_past_model": {
6
+ "op_types": [
7
+ "Gather",
8
+ "Slice",
9
+ "MatMul",
10
+ "Mul",
11
+ "Softmax",
12
+ "Max",
13
+ "CumSum",
14
+ "Expand",
15
+ "Add",
16
+ "Sub",
17
+ "Equal",
18
+ "Reshape",
19
+ "Unsqueeze",
20
+ "ReduceMean",
21
+ "Shape",
22
+ "Where",
23
+ "Constant",
24
+ "Div",
25
+ "Transpose",
26
+ "Squeeze",
27
+ "Relu",
28
+ "Concat",
29
+ "Sqrt",
30
+ "Gemm",
31
+ "ConstantOfShape",
32
+ "Pow",
33
+ "Cast"
34
+ ],
35
+ "weight_type": "QInt8"
36
+ },
37
+ "decoder_model_merged": {
38
+ "op_types": [
39
+ "Gather",
40
+ "Less",
41
+ "Slice",
42
+ "MatMul",
43
+ "Mul",
44
+ "Softmax",
45
+ "Max",
46
+ "CumSum",
47
+ "Expand",
48
+ "Add",
49
+ "Sub",
50
+ "Equal",
51
+ "Reshape",
52
+ "Unsqueeze",
53
+ "ReduceMean",
54
+ "Shape",
55
+ "Where",
56
+ "Constant",
57
+ "Div",
58
+ "Range",
59
+ "Squeeze",
60
+ "Transpose",
61
+ "Relu",
62
+ "If",
63
+ "Concat",
64
+ "Sqrt",
65
+ "Gemm",
66
+ "ConstantOfShape",
67
+ "Pow",
68
+ "Cast"
69
+ ],
70
+ "weight_type": "QInt8"
71
+ },
72
+ "decoder_model": {
73
+ "op_types": [
74
+ "Gather",
75
+ "Less",
76
+ "Slice",
77
+ "MatMul",
78
+ "Mul",
79
+ "Softmax",
80
+ "Max",
81
+ "CumSum",
82
+ "Expand",
83
+ "Add",
84
+ "Sub",
85
+ "Equal",
86
+ "Reshape",
87
+ "Unsqueeze",
88
+ "ReduceMean",
89
+ "Shape",
90
+ "Where",
91
+ "Constant",
92
+ "Div",
93
+ "Range",
94
+ "Squeeze",
95
+ "Transpose",
96
+ "Relu",
97
+ "Concat",
98
+ "Sqrt",
99
+ "Gemm",
100
+ "ConstantOfShape",
101
+ "Pow",
102
+ "Cast"
103
+ ],
104
+ "weight_type": "QInt8"
105
+ }
106
+ }
107
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "</s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "</s>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "</s>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "clean_up_tokenization_spaces": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "</s>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 1000000000000000019884624838656,
23
+ "pad_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<pad>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "tokenizer_class": "GPT2Tokenizer",
32
+ "unk_token": {
33
+ "__type": "AddedToken",
34
+ "content": "</s>",
35
+ "lstrip": false,
36
+ "normalized": true,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ }
40
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff