Hugging Face's logo

dmmagdal
/
opt-1.3b-onnx-js-quantized

Text Generation
Transformers
ONNX
opt
Inference Endpoints
Model card Files Community
dmmagdal commited on
Commit
2cb184c
·
1 Parent(s): fa57cf4

Uploaded model files (quantized)

Browse files
Files changed (18) hide show
  1. .gitattributes +3 -0
  2. config.json +30 -0
  3. generation_config.json +7 -0
  4. merges.txt +0 -0
  5. onnx/decoder_model.onnx +3 -0
  6. onnx/decoder_model.onnx_data +3 -0
  7. onnx/decoder_model_merged.onnx +3 -0
  8. onnx/decoder_model_merged.onnx_data +3 -0
  9. onnx/decoder_model_merged_quantized.onnx +3 -0
  10. onnx/decoder_model_quantized.onnx +3 -0
  11. onnx/decoder_with_past_model.onnx +3 -0
  12. onnx/decoder_with_past_model.onnx_data +3 -0
  13. onnx/decoder_with_past_model_quantized.onnx +3 -0
  14. quantize_config.json +110 -0
  15. special_tokens_map.json +30 -0
  16. tokenizer.json +0 -0
  17. tokenizer_config.json +40 -0
  18. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ onnx/decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
37
+ onnx/decoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text
38
+ onnx/decoder_with_past_model.onnx_data filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/opt-1.3b",
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": 8192,
16
+ "hidden_size": 2048,
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": 32,
23
+ "num_hidden_layers": 24,
24
+ "pad_token_id": 1,
25
+ "prefix": "</s>",
26
+ "transformers_version": "4.33.2",
27
+ "use_cache": true,
28
+ "vocab_size": 50272,
29
+ "word_embed_proj_dim": 2048
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": "4.33.2"
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:c84b8fda9dbbbc658d65034f38132587bc9e7738d503d82113ceae3f4dc31594
3
+ size 739110
onnx/decoder_model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58a13ea650bd8e29381173934232573bf1a25b2791b8c07e650f5ece1edcc032
3
+ size 5262639104
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ea2f5582147c30364617f02bae1aac4f05327c9c9529c96c66cd9a1be9c8330
3
+ size 1460469
onnx/decoder_model_merged.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58a13ea650bd8e29381173934232573bf1a25b2791b8c07e650f5ece1edcc032
3
+ size 5262639104
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab1b07602dba4b2796753639e87e9ff206c233221ba629a69933dc263df0fec2
3
+ size 1319515094
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9051c4ed39bab572b71cde43db6db0826fcd028db91aa7c2df6dab9cbfe45aa
3
+ size 1318404834
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc17b4f2f2bbc1dccbc239f4d30d678860a189804157b5260e2d0d52e5b00ff2
3
+ size 749533
onnx/decoder_with_past_model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58a13ea650bd8e29381173934232573bf1a25b2791b8c07e650f5ece1edcc032
3
+ size 5262639104
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d48048920ebd4a3056b49befd2a84e9cf34ebddfb2f239483b6e170a232a5f8
3
+ size 1318412480
quantize_config.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Unsqueeze",
8
+ "Constant",
9
+ "Mul",
10
+ "Equal",
11
+ "Slice",
12
+ "Shape",
13
+ "Gather",
14
+ "Concat",
15
+ "Reshape",
16
+ "ReduceMean",
17
+ "Less",
18
+ "Max",
19
+ "Softmax",
20
+ "MatMul",
21
+ "Cast",
22
+ "Div",
23
+ "Range",
24
+ "CumSum",
25
+ "Pow",
26
+ "Transpose",
27
+ "Sub",
28
+ "Add",
29
+ "ConstantOfShape",
30
+ "Expand",
31
+ "Gemm",
32
+ "Squeeze",
33
+ "Relu",
34
+ "Sqrt",
35
+ "Where",
36
+ "Identity"
37
+ ],
38
+ "weight_type": "QInt8"
39
+ },
40
+ "decoder_with_past_model": {
41
+ "op_types": [
42
+ "Unsqueeze",
43
+ "Constant",
44
+ "Mul",
45
+ "Equal",
46
+ "Slice",
47
+ "Shape",
48
+ "Gather",
49
+ "Concat",
50
+ "Reshape",
51
+ "ReduceMean",
52
+ "Max",
53
+ "Softmax",
54
+ "MatMul",
55
+ "Where",
56
+ "Div",
57
+ "CumSum",
58
+ "Pow",
59
+ "Transpose",
60
+ "Sub",
61
+ "Add",
62
+ "ConstantOfShape",
63
+ "Expand",
64
+ "Gemm",
65
+ "Squeeze",
66
+ "Relu",
67
+ "Sqrt",
68
+ "Cast",
69
+ "Identity"
70
+ ],
71
+ "weight_type": "QInt8"
72
+ },
73
+ "decoder_model_merged": {
74
+ "op_types": [
75
+ "Unsqueeze",
76
+ "Constant",
77
+ "Mul",
78
+ "Equal",
79
+ "Slice",
80
+ "Shape",
81
+ "Gather",
82
+ "Concat",
83
+ "Reshape",
84
+ "ReduceMean",
85
+ "Less",
86
+ "If",
87
+ "Max",
88
+ "Softmax",
89
+ "MatMul",
90
+ "Cast",
91
+ "Div",
92
+ "Range",
93
+ "CumSum",
94
+ "Pow",
95
+ "Transpose",
96
+ "Sub",
97
+ "Add",
98
+ "ConstantOfShape",
99
+ "Expand",
100
+ "Gemm",
101
+ "Squeeze",
102
+ "Relu",
103
+ "Sqrt",
104
+ "Where",
105
+ "Identity"
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