SO0529 commited on
Commit
88fe7f0
1 Parent(s): a545e98

first commit

Browse files
Files changed (5) hide show
  1. config.json +22 -0
  2. emoji.json +0 -0
  3. pytorch_model.bin +3 -0
  4. tokenizer_config.json +7 -0
  5. vocab.txt +0 -0
config.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GPTNeoXJapaneseForCausalLM"
4
+ ],
5
+ "model_type": "gpt_neox_japanese",
6
+ "vocab_size": 32000,
7
+ "hidden_size": 2560,
8
+ "num_hidden_layers": 32,
9
+ "num_attention_heads": 32,
10
+ "intermediate_multiple_size": 4,
11
+ "hidden_act": "gelu",
12
+ "rotary_pct": 1.00,
13
+ "rotary_emb_base": 10000,
14
+ "max_position_embeddings": 2048,
15
+ "initializer_range": 0.02,
16
+ "layer_norm_eps": 1e-5,
17
+ "use_cache": true,
18
+ "bos_token_id": 31999,
19
+ "eos_token_id": 31999,
20
+ "tokenizer_class": "GPTNeoXJapaneseTokenizer",
21
+ "transformers_version": "4.19.0.dev0"
22
+ }
emoji.json ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc76ae55db775bdd701bfda8189725a7881c6459877dc92ed763bf06d4312607
3
+ size 5690003881
tokenizer_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "pad_token": "<|endoftext|>",
3
+ "unk_token": "<|endoftext|>",
4
+ "bos_token": "<|startoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "do_clean_text": false
7
+ }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff