roneneldan commited on
Commit
01e0132
1 Parent(s): 6652604

Upload 2 files

Browse files
Files changed (2) hide show
  1. config.json +44 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "//amlta41566503acb2986203fbd2fc58f9ff6/projects/CODE_YUANZHI/amlt-results/7318108978.59905-0b55e936-4c89-4ab6-94c2-3ad145de1a5f/trainer_textbook/checkpoint-2500/",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global",
10
+ "local"
11
+ ],
12
+ "attention_types": [
13
+ [
14
+ [
15
+ "global",
16
+ "local"
17
+ ],
18
+ 1
19
+ ]
20
+ ],
21
+ "bos_token_id": 50256,
22
+ "embed_dropout": 0,
23
+ "eos_token_id": 50256,
24
+ "gradient_checkpointing": false,
25
+ "hidden_size": 1024,
26
+ "initializer_range": 0.02,
27
+ "intermediate_size": null,
28
+ "layer_norm_epsilon": 1e-05,
29
+ "max_position_embeddings": 2048,
30
+ "model_type": "gpt_neo",
31
+ "num_heads": 16,
32
+ "num_layers": 2,
33
+ "resid_dropout": 0,
34
+ "summary_activation": null,
35
+ "summary_first_dropout": 0.1,
36
+ "summary_proj_to_labels": true,
37
+ "summary_type": "cls_index",
38
+ "summary_use_proj": true,
39
+ "torch_dtype": "float32",
40
+ "transformers_version": "4.28.1",
41
+ "use_cache": true,
42
+ "vocab_size": 50257,
43
+ "window_size": 256
44
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b75ab0c9fbac45c194f14751616514c86dea23dd380891f5135a3adb664bbb43
3
+ size 323394263