ayo/ipex-llm
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

support transformers 4.34+ for llama (#9229)

Browse source
This commit is contained in:
Yang Wang 2023-10-20 13:36:30 +08:00 committed by GitHub
parent 7e96d3e79a
commit 118249b011
1 changed files with 2 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
python/llm/src/bigdl/llm/transformers/models/llama.py
View file

@ -79,6 +79,8 @@ def llama_attention_forward_4_31(
past_key_value: Optional[Tuple[torch.Tensor]] = None, past_key_value: Optional[Tuple[torch.Tensor]] = None,
output_attentions: bool = False, output_attentions: bool = False,
use_cache: bool = False, use_cache: bool = False,
padding_mask: Optional[torch.LongTensor] = None,
**kwargs,
) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]: ) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
bsz, q_len, _ = hidden_states.size() bsz, q_len, _ = hidden_states.size()
device = hidden_states.device device = hidden_states.device