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 2024-07-20 11:53:32 -07:00
commit 07228828a0
1 changed files with 2 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

2
unsloth/models/llama.py
View file

@ -1068,6 +1068,8 @@ def _wrap_fast_inference(generate, device_type, dtype, model):
# For newer HF
kwargs["cache_implementation"] = "dynamic"
print(kwargs)
# Set pad token
# old_pad_token_id = getattr(model.config, "pad_token_id", None)
# old_eos_token_id = getattr(model.config, "eos_token_id", None)