lcw99 commited on
Commit
933bed7
1 Parent(s): f01b53a

Upload GPTNeoForCausalLM

Browse files
Files changed (2) hide show
  1. config.json +74 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./StockModels/gpt-neo-1.3B-ko-2860",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local",
11
+ "global",
12
+ "local",
13
+ "global",
14
+ "local",
15
+ "global",
16
+ "local",
17
+ "global",
18
+ "local",
19
+ "global",
20
+ "local",
21
+ "global",
22
+ "local",
23
+ "global",
24
+ "local",
25
+ "global",
26
+ "local",
27
+ "global",
28
+ "local",
29
+ "global",
30
+ "local",
31
+ "global",
32
+ "local"
33
+ ],
34
+ "attention_types": [
35
+ [
36
+ [
37
+ "global",
38
+ "local"
39
+ ],
40
+ 12
41
+ ]
42
+ ],
43
+ "bos_token_id": 50256,
44
+ "embed_dropout": 0,
45
+ "eos_token_id": 50256,
46
+ "gradient_checkpointing": false,
47
+ "hidden_size": 2048,
48
+ "initializer_range": 0.02,
49
+ "intermediate_size": null,
50
+ "layer_norm_epsilon": 1e-05,
51
+ "max_position_embeddings": 2048,
52
+ "model_type": "gpt_neo",
53
+ "num_heads": 16,
54
+ "num_layers": 24,
55
+ "resid_dropout": 0,
56
+ "summary_activation": null,
57
+ "summary_first_dropout": 0.1,
58
+ "summary_proj_to_labels": true,
59
+ "summary_type": "cls_index",
60
+ "summary_use_proj": true,
61
+ "task_specific_params": {
62
+ "text-generation": {
63
+ "do_sample": true,
64
+ "max_length": 50,
65
+ "temperature": 0.9
66
+ }
67
+ },
68
+ "tokenizer_class": "GPT2Tokenizer",
69
+ "torch_dtype": "float16",
70
+ "transformers_version": "4.23.1",
71
+ "use_cache": false,
72
+ "vocab_size": 50257,
73
+ "window_size": 256
74
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c89ef199fe36500318d403761d89adf0abd1f31197bb714cbe02a2f4c2113b2
3
+ size 2731927913