saldra commited on
Commit
dab770b
1 Parent(s): 304352a

Upload 7 files

Browse files
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "rinna/japanese-gpt2-xsmall",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 1,
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": 512,
17
+ "n_head": 8,
18
+ "n_inner": 2304,
19
+ "n_layer": 6,
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
+ "task_specific_params": {
31
+ "text-generation": {
32
+ "do_sample": true,
33
+ "max_length": 50
34
+ }
35
+ },
36
+ "transformers_version": "4.33.2",
37
+ "use_cache": true,
38
+ "vocab_size": 32000
39
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.33.2"
6
+ }
quantize_config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Cast",
8
+ "Unsqueeze",
9
+ "Gemm",
10
+ "Softmax",
11
+ "Tanh",
12
+ "Add",
13
+ "Sub",
14
+ "Slice",
15
+ "Div",
16
+ "Range",
17
+ "Split",
18
+ "Squeeze",
19
+ "ReduceMean",
20
+ "Pow",
21
+ "Sqrt",
22
+ "Shape",
23
+ "Where",
24
+ "Mul",
25
+ "Concat",
26
+ "Constant",
27
+ "Reshape",
28
+ "MatMul",
29
+ "ConstantOfShape",
30
+ "Transpose",
31
+ "Gather"
32
+ ],
33
+ "weight_type": "QInt8"
34
+ },
35
+ "decoder_model_merged": {
36
+ "op_types": [
37
+ "Cast",
38
+ "Unsqueeze",
39
+ "Gemm",
40
+ "Softmax",
41
+ "Tanh",
42
+ "Add",
43
+ "Sub",
44
+ "Slice",
45
+ "Div",
46
+ "Range",
47
+ "Split",
48
+ "Squeeze",
49
+ "ReduceMean",
50
+ "Pow",
51
+ "Sqrt",
52
+ "Shape",
53
+ "If",
54
+ "Where",
55
+ "Mul",
56
+ "Concat",
57
+ "Constant",
58
+ "Reshape",
59
+ "MatMul",
60
+ "ConstantOfShape",
61
+ "Transpose",
62
+ "Gather"
63
+ ],
64
+ "weight_type": "QInt8"
65
+ },
66
+ "decoder_with_past_model": {
67
+ "op_types": [
68
+ "Cast",
69
+ "Unsqueeze",
70
+ "Gemm",
71
+ "Softmax",
72
+ "Tanh",
73
+ "Add",
74
+ "Sub",
75
+ "Slice",
76
+ "Div",
77
+ "Range",
78
+ "Split",
79
+ "Squeeze",
80
+ "ReduceMean",
81
+ "Pow",
82
+ "Sqrt",
83
+ "Shape",
84
+ "Where",
85
+ "Mul",
86
+ "Concat",
87
+ "Constant",
88
+ "Reshape",
89
+ "MatMul",
90
+ "ConstantOfShape",
91
+ "Transpose",
92
+ "Gather"
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": "[CLS]",
4
+ "eos_token": "</s>",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": "<unk>"
9
+ }
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5cbdfa8aa7c54c8c5af85b78c309c54a5f2749a20468bf6f60eee007fe6fec1
3
+ size 805634
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [],
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "cls_token": "[CLS]",
6
+ "do_lower_case": true,
7
+ "eos_token": "</s>",
8
+ "extra_ids": 0,
9
+ "legacy": true,
10
+ "mask_token": "[MASK]",
11
+ "model_max_length": 1000000000000000019884624838656,
12
+ "pad_token": "[PAD]",
13
+ "sep_token": "[SEP]",
14
+ "sp_model_kwargs": {},
15
+ "tokenizer_class": "T5Tokenizer",
16
+ "unk_token": "<unk>"
17
+ }