Hugging Face's logo

Xenova
/
opt-350m

Text Generation
Transformers.js
ONNX
opt
Model card Files Community
Xenova HF staff commited on
Commit
7539080
•
1 Parent(s): c1ffc1d

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 +110 -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-350m",
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": false,
12
+ "dropout": 0.1,
13
+ "enable_bias": true,
14
+ "eos_token_id": 2,
15
+ "ffn_dim": 4096,
16
+ "hidden_size": 1024,
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": 16,
23
+ "num_hidden_layers": 24,
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": 512
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 sha256:71de5ac436b0e66f6994459b8a1c5cae87c8dc23ab043229025c6d2e02fb98d5
3
+ size 1325248428
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8df62c42a8c43182ba63f943e490cb10fe9d0fa1dfa332bdf900f684879c0f76
3
+ size 1325909033
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4c41dcd1a4836ea1d1494c07cf50f183c03254cd620f9d45cfb52aff3843d9b
3
+ size 334060030
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:821537d8e1e6a6de36b723c01c644db8ad7ecc4460867ac6aa3f88bceea7d696
3
+ size 333010835
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5795a2d7e42996086acfb9f18cb8da8843a12231f3b0b522278a97281f6efd1d
3
+ size 1325256050
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:816be951d0fccb08dd03d2a04ca4f010da3a1045127be1dfcac43163f54b03be
3
+ size 333019128
quantize_config.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_with_past_model": {
6
+ "op_types": [
7
+ "ConstantOfShape",
8
+ "Unsqueeze",
9
+ "Mul",
10
+ "Div",
11
+ "Where",
12
+ "Expand",
13
+ "Cast",
14
+ "Constant",
15
+ "Max",
16
+ "Sqrt",
17
+ "CumSum",
18
+ "Relu",
19
+ "MatMul",
20
+ "Add",
21
+ "Squeeze",
22
+ "Pow",
23
+ "Identity",
24
+ "Sub",
25
+ "ReduceMean",
26
+ "Softmax",
27
+ "Gemm",
28
+ "Gather",
29
+ "Slice",
30
+ "Reshape",
31
+ "Concat",
32
+ "Equal",
33
+ "Transpose",
34
+ "Shape"
35
+ ],
36
+ "weight_type": "QInt8"
37
+ },
38
+ "decoder_model_merged": {
39
+ "op_types": [
40
+ "ConstantOfShape",
41
+ "Unsqueeze",
42
+ "Mul",
43
+ "Div",
44
+ "Cast",
45
+ "Where",
46
+ "Expand",
47
+ "Constant",
48
+ "Max",
49
+ "Sqrt",
50
+ "CumSum",
51
+ "Relu",
52
+ "MatMul",
53
+ "Squeeze",
54
+ "Add",
55
+ "Pow",
56
+ "Identity",
57
+ "Sub",
58
+ "ReduceMean",
59
+ "Softmax",
60
+ "Gemm",
61
+ "Gather",
62
+ "Slice",
63
+ "Reshape",
64
+ "If",
65
+ "Concat",
66
+ "Less",
67
+ "Equal",
68
+ "Transpose",
69
+ "Shape",
70
+ "Range"
71
+ ],
72
+ "weight_type": "QInt8"
73
+ },
74
+ "decoder_model": {
75
+ "op_types": [
76
+ "ConstantOfShape",
77
+ "Unsqueeze",
78
+ "Mul",
79
+ "Div",
80
+ "Cast",
81
+ "Where",
82
+ "Expand",
83
+ "Constant",
84
+ "Max",
85
+ "Sqrt",
86
+ "CumSum",
87
+ "Relu",
88
+ "MatMul",
89
+ "Squeeze",
90
+ "Add",
91
+ "Pow",
92
+ "Identity",
93
+ "Sub",
94
+ "ReduceMean",
95
+ "Softmax",
96
+ "Gemm",
97
+ "Gather",
98
+ "Slice",
99
+ "Reshape",
100
+ "Concat",
101
+ "Less",
102
+ "Equal",
103
+ "Transpose",
104
+ "Shape",
105
+ "Range"
106
+ ],
107
+ "weight_type": "QInt8"
108
+ }
109
+ }
110
+ }
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