yashshinde0080 commited on
Commit
a8d7309
·
verified ·
1 Parent(s): 0062f13

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +23 -0
  2. model.py +0 -0
  3. pytorch_model.pt +3 -0
config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_type": "gpt",
3
+ "architecture": "GPT (nanoGPT-style)",
4
+ "block_size": 128,
5
+ "vocab_size": 50257,
6
+ "n_layer": 6,
7
+ "n_head": 6,
8
+ "n_embd": 384,
9
+ "dropout": 0.1,
10
+ "bias": true,
11
+ "num_parameters": 29946240,
12
+ "tokenizer": "tiktoken gpt2",
13
+ "training": {
14
+ "max_iters": 20000,
15
+ "batch_size": 32,
16
+ "learning_rate": 0.001,
17
+ "gradient_accumulation_steps": 4,
18
+ "warmup_steps": 1000,
19
+ "optimizer": "AdamW",
20
+ "weight_decay": 0.1
21
+ },
22
+ "best_val_loss": 4.458158016204834
23
+ }
model.py ADDED
File without changes
pytorch_model.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b5d38ea7b8a2b25e9e78f6fb1afb4590e7e215f35bb2fc99578dd35668dd98d
3
+ size 120010898