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 2024-02-07 18:18:43 +11:00
commit 60b47f6130
1 changed files with 1 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
unsloth/models/llama.py
View file

@ -174,6 +174,7 @@ def LlamaAttention_fast_forward_inference(
# Handle sliding windows
attention_size = getattr(self.config, "sliding_window", kv_seq_len)
if kv_seq_len <= attention_size:
attention_size = kv_seq_len
Knn, Vnn = Kn, Vn
else:
# From https://github.com/huggingface/transformers/blob/main/src/transformers/models/mistral/modeling_mistral.py#L193