breez7 commited on
Commit
89828ec
1 Parent(s): f8e139c

Upload GPTNeoForCausalLM

Browse files
Files changed (3) hide show
  1. config.json +47 -0
  2. generation_config.json +6 -0
  3. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roneneldan/TinyStories-33M",
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
+ ],
14
+ "attention_types": [
15
+ [
16
+ [
17
+ "global",
18
+ "local"
19
+ ],
20
+ 2
21
+ ]
22
+ ],
23
+ "bos_token_id": 50256,
24
+ "classifier_dropout": 0.1,
25
+ "embed_dropout": 0,
26
+ "eos_token_id": 50256,
27
+ "gradient_checkpointing": false,
28
+ "hidden_size": 768,
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": null,
31
+ "layer_norm_epsilon": 1e-05,
32
+ "max_position_embeddings": 2048,
33
+ "model_type": "gpt_neo",
34
+ "num_heads": 16,
35
+ "num_layers": 4,
36
+ "resid_dropout": 0,
37
+ "summary_activation": null,
38
+ "summary_first_dropout": 0.1,
39
+ "summary_proj_to_labels": true,
40
+ "summary_type": "cls_index",
41
+ "summary_use_proj": true,
42
+ "torch_dtype": "float32",
43
+ "transformers_version": "4.34.1",
44
+ "use_cache": true,
45
+ "vocab_size": 50257,
46
+ "window_size": 256
47
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.34.1"
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1aba2850719b32846dcfe665fa0b9401921305b1879f0795ee0837385603f35b
3
+ size 274074966