frozenleaves/vllm
1
0
Fork 0
mirror of https://github.com/vllm-project/vllm.git synced 2025-10-20 14:53:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Bugfix] Fix loading of fine-tuned models based on Phi-3-Small (#12689)

Browse Source 
Signed-off-by: Michael Greenbaum <mgreenbaum@microsoft.com>
Co-authored-by: Michael Greenbaum <mgreenbaum@microsoft.com>
This commit is contained in:
Michael Greenbaum
2025-02-04 14:58:48 +02:00
committed by GitHub
parent 815079de8e
commit 6469038b14
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/models/phi3_small.py
View File

@ -476,6 +476,8 @@ class Phi3SmallForCausalLM(nn.Module, SupportsPP):
continue
if is_pp_missing_parameter(name, self):
continue
if "lm_head.weight" in name and self.config.tie_word_embeddings:
continue
param = params_dict[name]
weight_loader = getattr(param, "weight_loader",
default_weight_loader)