Reduce memory requirement on export_llama tests with no params #11175

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed

jackzhxng wants to merge 5 commits into gh/jackzhxng/22/base from gh/jackzhxng/22/head

examples/models/llama/model_args.py

-Original file line number
+Diff line change
@@ Expand Up / @@ -5,7 +5,7 @@ @@
     @dataclass
     class ModelArgs:
         dim: int = 4096
-        n_layers: int = 8
+        n_layers: int = 1
         n_heads: int = 32
         n_kv_heads: Optional[int] = None
         vocab_size: int = 512  # Arbitrary value, should be defined later by tokenizer.
@@ Expand Down @@