bolin22 commited on
Commit
13d70de
1 Parent(s): cb957d0

Upload config.json

Browse files
Files changed (1) hide show
  1. config.json +70 -0
config.json ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "EleutherAI/gpt-neo-125M",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "Re_gptForCausalLM"
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
+ ],
22
+ "attention_types": [
23
+ [
24
+ [
25
+ "global",
26
+ "local"
27
+ ],
28
+ 6
29
+ ]
30
+ ],
31
+ "bos_token_id": 50256,
32
+ "chunk_size": 64,
33
+ "dec_attn_dropout": 0.25,
34
+ "dec_cross_attn_layers": [
35
+ 5,
36
+ 128
37
+ ],
38
+ "dec_ff_dropout": 0.25,
39
+ "dec_heads": 16,
40
+ "dim_head": 64,
41
+ "embed_dropout": 0,
42
+ "enc_att_dropout": 0.0,
43
+ "enc_cross_attn_layers": null,
44
+ "enc_depth": 2,
45
+ "enc_dim": 768,
46
+ "enc_ff_dropout": 0.0,
47
+ "enc_heads": 16,
48
+ "eos_token_id": 50256,
49
+ "ff_mult": 4,
50
+ "gradient_checkpointing": false,
51
+ "hidden_size": 768,
52
+ "initializer_range": 0.02,
53
+ "intermediate_size": null,
54
+ "layer_norm_epsilon": 1e-05,
55
+ "max_position_embeddings": 2048,
56
+ "model_type": "re_gpt",
57
+ "num_heads": 12,
58
+ "num_layers": 12,
59
+ "resid_dropout": 0,
60
+ "summary_activation": null,
61
+ "summary_first_dropout": 0.1,
62
+ "summary_proj_to_labels": true,
63
+ "summary_type": "cls_index",
64
+ "summary_use_proj": true,
65
+ "torch_dtype": "float32",
66
+ "transformers_version": "4.20.1",
67
+ "use_cache": true,
68
+ "vocab_size": 50257,
69
+ "window_size": 256
70
+ }