Skip to content

Commit 4928ba3

Browse files
committed
Reduce memory requirement on export_llama tests with no params
Pull Request resolved: #11175 @imported-using-ghimport Differential Revision: [D75498713](https://our.internmc.facebook.com/intern/diff/D75498713/) ghstack-source-id: 287631950
1 parent 0b624e8 commit 4928ba3

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

examples/models/llama/model_args.py

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -5,7 +5,7 @@
55
@dataclass
66
class ModelArgs:
77
dim: int = 4096
8-
n_layers: int = 8
8+
n_layers: int = 1
99
n_heads: int = 32
1010
n_kv_heads: Optional[int] = None
1111
vocab_size: int = 512 # Arbitrary value, should be defined later by tokenizer.

0 commit comments

Comments
 (0)