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 2024-02-02 22:26:47 +11:00
commit dc2740416b
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
unsloth/models/llama.py
View file

@ -683,7 +683,7 @@ torch._inductor.config.coordinate_descent_tuning = True
torch._inductor.config.triton.unique_kernel_names = True
# https://github.com/huggingface/transformers/blob/main/src/transformers/models/llama/modeling_llama.py#L825
@torch.compile(mode = "reduce-overhead", fullgraph = True)
@torch.compile(mode = "reduce-overhead")
def LlamaModel_fast_forward_inference(
self,
input_ids,