mahotaka commited on
Commit
56454b6
1 Parent(s): c48f9bc

Upload 3 files

Browse files
Files changed (3) hide show
  1. config.json +39 -0
  2. pytorch_model.bin +3 -0
  3. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "colorfulscoop/gpt2-small-ja",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 2,
9
+ "cls_token_id": 4,
10
+ "do_sample": true,
11
+ "embd_pdrop": 0.1,
12
+ "eos_token_id": 3,
13
+ "gradient_checkpointing": false,
14
+ "initializer_range": 0.02,
15
+ "layer_norm_epsilon": 1e-05,
16
+ "model_type": "gpt2",
17
+ "n_ctx": 1024,
18
+ "n_embd": 768,
19
+ "n_head": 12,
20
+ "n_inner": null,
21
+ "n_layer": 12,
22
+ "n_positions": 1024,
23
+ "pad_token_id": 0,
24
+ "resid_pdrop": 0.1,
25
+ "scale_attn_weights": true,
26
+ "sep_token_id": 5,
27
+ "summary_activation": null,
28
+ "summary_first_dropout": 0.1,
29
+ "summary_proj_to_labels": true,
30
+ "summary_type": "cls_index",
31
+ "summary_use_proj": true,
32
+ "tokenizer_class": "BertGenerationTokenizer",
33
+ "top_p": 0.95,
34
+ "torch_dtype": "float32",
35
+ "transformers_version": "4.10.0",
36
+ "unk_token_id": 1,
37
+ "use_cache": true,
38
+ "vocab_size": 32000
39
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6426a61cc1c011a6fd6e5b71af903588af8d3fb4117cea0f2e7a85ef3295c9a
3
+ size 454321055
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da97c14d00955fedc31aab5efc1909ea66a860b149ffbff085d7c1dbe52d5707
3
+ size 2735