roneneldan commited on
Commit
6fb5cbb
1 Parent(s): 32b90a3

Upload 2 files

Browse files
Files changed (2) hide show
  1. config.json +42 -0
  2. pytorch_model.bin +3 -0
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "//amlta41566503acb2986203fbd2fc58f9ff6/projects/CODE_YUANZHI/amlt-results/7318108978.60506-7a5ae11e-b56c-43eb-b4b6-b2b1f9c0e061/trainer_textbook/checkpoint-28000/",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPTNeoForCausalLM"
6
+ ],
7
+ "attention_dropout": 0,
8
+ "attention_layers": [
9
+ "global"
10
+ ],
11
+ "attention_types": [
12
+ [
13
+ [
14
+ "global"
15
+ ],
16
+ 1
17
+ ]
18
+ ],
19
+ "bos_token_id": 50256,
20
+ "embed_dropout": 0,
21
+ "eos_token_id": 50256,
22
+ "gradient_checkpointing": false,
23
+ "hidden_size": 1024,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": null,
26
+ "layer_norm_epsilon": 1e-05,
27
+ "max_position_embeddings": 2048,
28
+ "model_type": "gpt_neo",
29
+ "num_heads": 16,
30
+ "num_layers": 1,
31
+ "resid_dropout": 0,
32
+ "summary_activation": null,
33
+ "summary_first_dropout": 0.1,
34
+ "summary_proj_to_labels": true,
35
+ "summary_type": "cls_index",
36
+ "summary_use_proj": true,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.28.1",
39
+ "use_cache": true,
40
+ "vocab_size": 50257,
41
+ "window_size": 256
42
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4afe8f12f705ae981e4381865ccfee9a3950854f8850fae2977fe9f84ae3a57
3
+ size 268822634