mirror of
https://github.com/ml-explore/mlx-examples.git
synced 2025-12-15 17:58:54 +08:00
feat(mlx-lm): add de-quant for fuse.py (#365)
* feat(mlx-lm): add de-quant for fuse * chore: disable quant in to linear when de-quant enabled * chore: add better error handling for adapter file not found
This commit is contained in:
@@ -24,7 +24,7 @@ MODEL_MAPPING = {
|
||||
"qwen": qwen,
|
||||
"plamo": plamo,
|
||||
}
|
||||
MAX_FILE_SIZE_GB = 15
|
||||
MAX_FILE_SIZE_GB = 5
|
||||
|
||||
linear_class_predicate = (
|
||||
lambda m: isinstance(m, nn.Linear)
|
||||
|
||||
Reference in New Issue
Block a user