ChunB1 commited on
Commit
64dea1f
1 Parent(s): 5c3a930

Upload GPTNeoForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +52 -0
  2. generation_config.json +7 -0
  3. model.safetensors +3 -0
config.json ADDED
@@ -0,0 +1,52 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/content/drive/MyDrive/results_adv/checkpoint-120000",
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
+ ],
18
+ "attention_types": [
19
+ [
20
+ [
21
+ "global",
22
+ "local"
23
+ ],
24
+ 4
25
+ ]
26
+ ],
27
+ "bos_token_id": 50256,
28
+ "classifier_dropout": 0.1,
29
+ "embed_dropout": 0,
30
+ "eos_token_id": 50256,
31
+ "gradient_checkpointing": false,
32
+ "hidden_size": 64,
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": null,
35
+ "layer_norm_epsilon": 1e-05,
36
+ "max_position_embeddings": 2048,
37
+ "model_type": "gpt_neo",
38
+ "num_heads": 16,
39
+ "num_layers": 8,
40
+ "pad_token_id": 50256,
41
+ "resid_dropout": 0,
42
+ "summary_activation": null,
43
+ "summary_first_dropout": 0.1,
44
+ "summary_proj_to_labels": true,
45
+ "summary_type": "cls_index",
46
+ "summary_use_proj": true,
47
+ "torch_dtype": "float32",
48
+ "transformers_version": "4.36.1",
49
+ "use_cache": true,
50
+ "vocab_size": 50257,
51
+ "window_size": 256
52
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "pad_token_id": 50256,
6
+ "transformers_version": "4.36.1"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1286e7638088e05dbcc2c02889c49bd45c385cf52634f09a51c462e4cf8f435b
3
+ size 14994712