kaanino commited on
Commit
3ac790c
·
verified ·
1 Parent(s): d28e96d

Training in progress, step 106

Browse files
Files changed (3) hide show
  1. config.json +19 -0
  2. model.safetensors +3 -0
  3. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_type": "gelu",
3
+ "architectures": [
4
+ "GPT"
5
+ ],
6
+ "dropout": 0.1,
7
+ "dtype": "float32",
8
+ "max_seq_length": 128,
9
+ "model_type": "gpt",
10
+ "n_embd": 64,
11
+ "n_head": 4,
12
+ "n_kv_head": 1,
13
+ "n_layer": 6,
14
+ "norm_type": "rmsnorm",
15
+ "pos_enc_type": "relative",
16
+ "transformers_version": "5.5.4",
17
+ "use_cache": false,
18
+ "vocab_size": 50257
19
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c56e0bf65189fb6e9d6bf24b6a11f07d733fed56f9a5675e642515018a8281cf
3
+ size 27266224
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd22bd540c79e1f052d5bc3713b67a0802bf68c5df5574b5b650800a993c54d9
3
+ size 5201