ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update llama.py

Browse source
This commit is contained in:
Daniel Han 2025-03-05 03:30:13 -08:00
commit 9cdc4dd16b
1 changed files with 5 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

5
unsloth/models/llama.py
View file

@ -2611,6 +2611,9 @@ class FastLlamaModel:
@staticmethod
def for_inference(model):
if not hasattr(model, "parameters"):
raise TypeError("Unsloth: I think you're passing a tokenizer, not the model to for_inference!")
def _for_inference(m):
if hasattr(m, "gradient_checkpointing"): m.gradient_checkpointing = False
if hasattr(m, "training"): m.training = False
@ -2640,6 +2643,8 @@ class FastLlamaModel:
@staticmethod
def for_training(model, use_gradient_checkpointing = True):
if not hasattr(model, "parameters"):
raise TypeError("Unsloth: I think you're passing a tokenizer, not the model to for_inference!")
# Delete all fast inference loras
for param in model.parameters():