Hugging Face's logo

clfegg
/
gpt-tinystories-vi-subset-js

Text Generation
Transformers.js
ONNX
Vietnamese
gpt2
Model card Files
xet
Community
clfegg commited on
Commit
e978fd6
·
verified ·
1 Parent(s): b9d1029

Upload 14 files

Browse files
Files changed (14) hide show
  1. added_tokens.json +4 -0
  2. bpe.codes +0 -0
  3. config.json +33 -0
  4. generation_config.json +6 -0
  5. onnx/decoder_model.onnx +3 -0
  6. onnx/decoder_model_merged.onnx +3 -0
  7. onnx/decoder_model_merged_quantized.onnx +3 -0
  8. onnx/decoder_model_quantized.onnx +3 -0
  9. onnx/decoder_with_past_model.onnx +3 -0
  10. onnx/decoder_with_past_model_quantized.onnx +3 -0
  11. quantize_config.json +97 -0
  12. special_tokens_map.json +9 -0
  13. tokenizer_config.json +12 -0
  14. vocab.txt +0 -0
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<mask>": 64001,
3
+ "<|endoftext|": 64000
4
+ }
bpe.codes ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "clfegg/gpt-tinystories-vi-subset",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 0,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 2,
11
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 256,
17
+ "n_head": 8,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "transformers_version": "4.33.2",
31
+ "use_cache": true,
32
+ "vocab_size": 64001
33
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.33.2"
6
+ }
onnx/decoder_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2366deb94af0b6c73badcaca67137994a55dc12383d6e527213a749abd9d2192
3
+ size 106012863
onnx/decoder_model_merged.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e799ab3ac9c757bd2150a23d3546ffd4e33b474b6349b1bbe6eae390c62205e6
3
+ size 107536113
onnx/decoder_model_merged_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7e0aca2e6dad71a22b4eeb7bc10323c89033e9cf0be11ce549847a9b5875c4b
3
+ size 29757432
onnx/decoder_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31d9d15d5d9bca6420c0f42793e9df1ffeb0659da302b4e8bf6bf1bbeb6ee73a
3
+ size 27998459
onnx/decoder_with_past_model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a880a37483cc25e0a0c79dc18e2d6cdacd9aaa912c424881c527dbd2889909e0
3
+ size 106019668
onnx/decoder_with_past_model_quantized.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e1ad6700fee6c33de58ad9a8beb40495d0824b41ccb1a69829d8a278c1bbf8c
3
+ size 28007506
quantize_config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_with_past_model": {
6
+ "op_types": [
7
+ "Pow",
8
+ "Concat",
9
+ "Gather",
10
+ "Squeeze",
11
+ "Sub",
12
+ "Mul",
13
+ "Transpose",
14
+ "Where",
15
+ "Div",
16
+ "Unsqueeze",
17
+ "Constant",
18
+ "Range",
19
+ "Add",
20
+ "Gemm",
21
+ "Softmax",
22
+ "Reshape",
23
+ "Tanh",
24
+ "ConstantOfShape",
25
+ "MatMul",
26
+ "ReduceMean",
27
+ "Slice",
28
+ "Sqrt",
29
+ "Split",
30
+ "Cast",
31
+ "Shape"
32
+ ],
33
+ "weight_type": "QInt8"
34
+ },
35
+ "decoder_model": {
36
+ "op_types": [
37
+ "Pow",
38
+ "Concat",
39
+ "Gather",
40
+ "Squeeze",
41
+ "Sub",
42
+ "Mul",
43
+ "Transpose",
44
+ "Where",
45
+ "Div",
46
+ "Unsqueeze",
47
+ "Constant",
48
+ "Range",
49
+ "Add",
50
+ "Gemm",
51
+ "Softmax",
52
+ "Reshape",
53
+ "Tanh",
54
+ "ConstantOfShape",
55
+ "MatMul",
56
+ "ReduceMean",
57
+ "Slice",
58
+ "Sqrt",
59
+ "Split",
60
+ "Cast",
61
+ "Shape"
62
+ ],
63
+ "weight_type": "QInt8"
64
+ },
65
+ "decoder_model_merged": {
66
+ "op_types": [
67
+ "Pow",
68
+ "Concat",
69
+ "Gather",
70
+ "Squeeze",
71
+ "Sub",
72
+ "Mul",
73
+ "Transpose",
74
+ "Where",
75
+ "Div",
76
+ "Unsqueeze",
77
+ "Constant",
78
+ "Range",
79
+ "Add",
80
+ "Gemm",
81
+ "Softmax",
82
+ "Reshape",
83
+ "Tanh",
84
+ "ConstantOfShape",
85
+ "If",
86
+ "MatMul",
87
+ "ReduceMean",
88
+ "Slice",
89
+ "Sqrt",
90
+ "Split",
91
+ "Cast",
92
+ "Shape"
93
+ ],
94
+ "weight_type": "QInt8"
95
+ }
96
+ }
97
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": "<mask>",
6
+ "pad_token": "<pad>",
7
+ "sep_token": "<|endoftext|",
8
+ "unk_token": "<unk>"
9
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "clean_up_tokenization_spaces": true,
4
+ "cls_token": "<s>",
5
+ "eos_token": "</s>",
6
+ "mask_token": "<mask>",
7
+ "model_max_length": 1000000000000000019884624838656,
8
+ "pad_token": "<pad>",
9
+ "sep_token": "<|endoftext|",
10
+ "tokenizer_class": "PhobertTokenizer",
11
+ "unk_token": "<unk>"
12
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff