diff options
Diffstat (limited to 'config/train_shakespeare_char.py')
| -rw-r--r-- | config/train_shakespeare_char.py | 4 |
1 files changed, 4 insertions, 0 deletions
diff --git a/config/train_shakespeare_char.py b/config/train_shakespeare_char.py index 41c81df..ec4e5b5 100644 --- a/config/train_shakespeare_char.py +++ b/config/train_shakespeare_char.py @@ -35,3 +35,7 @@ warmup_iters = 100 # not super necessary potentially # on macbook also add # device = 'cpu' # run on cpu only # compile = False # do not torch compile the model + +# Maxwell GPU fix (K2200 — no bf16 support) +dtype = 'float32' # bfloat16 requires compute 8.0+; Maxwell is 5.0 +flash = False # disable SDPA — uses bf16 internally on CUDA 11.8 |
