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 2025-03-04 19:02:12 -08:00
commit b2a5aff5f9
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
unsloth/models/llama.py
View file

@ -1975,7 +1975,7 @@ class FastLlamaModel:
# Patch generate
if model.generate.__name__ != "_fast_generate":
model._old_generate = model.generate
model.generate = types.MethodType(_wrap_fast_inference(model._old_generate), model.generate)
model.generate = types.MethodType(_wrap_fast_inference(model._old_generate), model)
return model, tokenizer
pass
@ -2412,7 +2412,7 @@ class FastLlamaModel:
# Patch generate
if model.generate.__name__ != "_fast_generate":
model._old_generate = model.generate
model.generate = types.MethodType(_wrap_fast_inference(model._old_generate), model.generate)
model.generate = types.MethodType(_wrap_fast_inference(model._old_generate), model)
return model
pass