Nebulae000 commited on
Commit
a8a1258
1 Parent(s): a23e077

Upload 3 files

Browse files

additional files

Files changed (3) hide show
  1. config.json +27 -0
  2. generation_config.json +6 -0
  3. tokenizer_config.json +6 -0
config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./polyglot-ko-12.8b_1000sample/",
3
+ "architectures": [
4
+ "GPTNeoXForCausalLM"
5
+ ],
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": 0.1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 20480,
13
+ "layer_norm_eps": 1e-05,
14
+ "max_position_embeddings": 2048,
15
+ "model_type": "gpt_neox",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 40,
18
+ "num_steps": "global_step301000",
19
+ "rotary_emb_base": 10000,
20
+ "rotary_pct": 0.5,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.29.2",
24
+ "use_cache": true,
25
+ "use_parallel_residual": true,
26
+ "vocab_size": 30080
27
+ }
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": "4.29.2"
6
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "name_or_path": "Nebulae000/polyglot-ko-12.8b_1000sample",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "tokenizer_class": "PreTrainedTokenizerFast"
6
+ }