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-Chen 2024-06-05 20:57:08 +10:00
commit d2fa16aafa
1 changed files with 5 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

8
unsloth/models/llama.py
View file

@ -1853,9 +1853,11 @@ class FastLlamaModel:
pass
# Wrap model.generate
model._unwrapped_old_generate = model.generate
model.generate = _wrap_fast_inference(model.generate, device_type, dtype, model)
if model.generate.__name__ != "_fast_generate":
model._unwrapped_old_generate = model.generate
model.generate = _wrap_fast_inference(model.generate, device_type, dtype, model)
pass
# Patch tokenizer to pad to the left
internal_model = model
while hasattr(internal_model, "model"):