Mlxa commited on
Commit
bbc6c44
1 Parent(s): c944feb

Upload GPTNeoForCausalLM

Browse files
Files changed (2) hide show
  1. config.json +50 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roneneldan/TinyStories-1M",
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
+ "embed_dropout": 0,
29
+ "eos_token_id": 50256,
30
+ "gradient_checkpointing": false,
31
+ "hidden_size": 64,
32
+ "initializer_range": 0.02,
33
+ "intermediate_size": null,
34
+ "layer_norm_epsilon": 1e-05,
35
+ "max_position_embeddings": 2048,
36
+ "model_type": "gpt_neo",
37
+ "num_heads": 16,
38
+ "num_layers": 8,
39
+ "resid_dropout": 0,
40
+ "summary_activation": null,
41
+ "summary_first_dropout": 0.1,
42
+ "summary_proj_to_labels": true,
43
+ "summary_type": "cls_index",
44
+ "summary_use_proj": true,
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.25.1",
47
+ "use_cache": true,
48
+ "vocab_size": 50257,
49
+ "window_size": 256
50
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab669932cdd9a4a59ca747f0dbc74b09702e28c4a6fdb606a52b193bc605756e
3
+ size 48719101