Hugging Face's logo

Xenova
/
LaMini-GPT-774M

Text Generation
Transformers.js
ONNX
gpt2
Model card Files Community
Xenova HF staff commited on
Commit
eaac27b
•
1 Parent(s): 02b9b5d

Upload folder using huggingface_hub

Browse files
Files changed (21) hide show
  1. .gitattributes +5 -0
  2. Constant_161_attr__value +3 -0
  3. Constant_171_attr__value +3 -0
  4. added_tokens.json +3 -0
  5. config.json +38 -0
  6. generation_config.json +6 -0
  7. merges.txt +0 -0
  8. onnx/decoder_model.onnx +3 -0
  9. onnx/decoder_model.onnx_data +3 -0
  10. onnx/decoder_model_merged.onnx +3 -0
  11. onnx/decoder_model_merged.onnx_data +3 -0
  12. onnx/decoder_model_merged_quantized.onnx +3 -0
  13. onnx/decoder_model_quantized.onnx +3 -0
  14. onnx/decoder_with_past_model.onnx +3 -0
  15. onnx/decoder_with_past_model.onnx_data +3 -0
  16. onnx/decoder_with_past_model_quantized.onnx +3 -0
  17. quantize_config.json +97 -0
  18. special_tokens_map.json +24 -0
  19. tokenizer.json +0 -0
  20. tokenizer_config.json +34 -0
  21. vocab.json +0 -0
.gitattributes CHANGED
@@ -33,3 +33,8 @@ 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
+ Constant_161_attr__value filter=lfs diff=lfs merge=lfs -text
37
+ Constant_171_attr__value filter=lfs diff=lfs merge=lfs -text
38
+ onnx/decoder_model.onnx_data filter=lfs diff=lfs merge=lfs -text
39
+ onnx/decoder_model_merged.onnx_data filter=lfs diff=lfs merge=lfs -text
40
+ onnx/decoder_with_past_model.onnx_data filter=lfs diff=lfs merge=lfs -text
Constant_161_attr__value ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae525b5c247f1f7b8310c42b37be7aed79adadb1806bb109d1e14c8c896fc319
3
+ size 1048576
Constant_171_attr__value ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae525b5c247f1f7b8310c42b37be7aed79adadb1806bb109d1e14c8c896fc319
3
+ size 1048576
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 50257
3
+ }
config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "MBZUAI/LaMini-GPT-774M",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 1280,
16
+ "n_head": 20,
17
+ "n_inner": null,
18
+ "n_layer": 36,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "transformers_version": "4.34.0.dev0",
36
+ "use_cache": false,
37
+ "vocab_size": 50258
38
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.34.0.dev0"
6
+ }
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 sha256:67676365f7446e55e2afbba07f67cd0f250cc6df294788eb542829a96f68c637
3
+ size 2649672
onnx/decoder_model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3947256c6bf1207f59892dd53031ffb84971b0e4f205142a3f457c853178ae7
3
+ size 3096125440
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46855eb558d85db95799cd4d6f3077f34fce47b0df758d075d9c449f032cc021
3
+ size 5288464
onnx/decoder_model_merged.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3947256c6bf1207f59892dd53031ffb84971b0e4f205142a3f457c853178ae7
3
+ size 3096125440
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:644310a0c217371925306bd677e663bb95c7087a54350514a94ee50e7c8a3c6f
3
+ size 782504456
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1875118d2aeec2b6f37ed840a1e256f28b658eded3c5bf1b12f8429ae4032a52
3
+ size 779162811
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa4f58bb8d0509b41a52d72f961b86da90f98aee713ce3efd18c6a18572186ac
3
+ size 2673105
onnx/decoder_with_past_model.onnx_data ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3947256c6bf1207f59892dd53031ffb84971b0e4f205142a3f457c853178ae7
3
+ size 3096125440
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1368f20badbb0e13427f20ab509f9a2e7278d9e7ec97085eb93c16805426ca9b
3
+ size 779187761
quantize_config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_model_merged": {
6
+ "op_types": [
7
+ "Mul",
8
+ "Cast",
9
+ "Tanh",
10
+ "Constant",
11
+ "ConstantOfShape",
12
+ "Unsqueeze",
13
+ "Div",
14
+ "If",
15
+ "Gemm",
16
+ "Reshape",
17
+ "Transpose",
18
+ "Squeeze",
19
+ "Softmax",
20
+ "Shape",
21
+ "Sqrt",
22
+ "Range",
23
+ "Add",
24
+ "MatMul",
25
+ "ReduceMean",
26
+ "Split",
27
+ "Where",
28
+ "Slice",
29
+ "Sub",
30
+ "Gather",
31
+ "Pow",
32
+ "Concat"
33
+ ],
34
+ "weight_type": "QInt8"
35
+ },
36
+ "decoder_with_past_model": {
37
+ "op_types": [
38
+ "Mul",
39
+ "Cast",
40
+ "Tanh",
41
+ "Constant",
42
+ "ConstantOfShape",
43
+ "Unsqueeze",
44
+ "Div",
45
+ "Gemm",
46
+ "Reshape",
47
+ "Transpose",
48
+ "Squeeze",
49
+ "Softmax",
50
+ "Shape",
51
+ "Sqrt",
52
+ "Range",
53
+ "Add",
54
+ "MatMul",
55
+ "ReduceMean",
56
+ "Split",
57
+ "Where",
58
+ "Slice",
59
+ "Sub",
60
+ "Gather",
61
+ "Pow",
62
+ "Concat"
63
+ ],
64
+ "weight_type": "QInt8"
65
+ },
66
+ "decoder_model": {
67
+ "op_types": [
68
+ "Mul",
69
+ "Cast",
70
+ "Tanh",
71
+ "Constant",
72
+ "ConstantOfShape",
73
+ "Unsqueeze",
74
+ "Div",
75
+ "Gemm",
76
+ "Reshape",
77
+ "Transpose",
78
+ "Squeeze",
79
+ "Softmax",
80
+ "Shape",
81
+ "Sqrt",
82
+ "Range",
83
+ "Add",
84
+ "MatMul",
85
+ "ReduceMean",
86
+ "Split",
87
+ "Where",
88
+ "Slice",
89
+ "Sub",
90
+ "Gather",
91
+ "Pow",
92
+ "Concat"
93
+ ],
94
+ "weight_type": "QInt8"
95
+ }
96
+ }
97
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "[PAD]",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
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": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 512,
23
+ "pad_token": null,
24
+ "padding_side": "right",
25
+ "tokenizer_class": "GPT2Tokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff