Skip to content

GitLab

Unverified Commit a2f602b5 authored by Rin Intachuen's avatar Rin Intachuen Committed by GitHub
Browse files

fixed lm_head.weight error for quantized qwen (#2910)

parent 8f2c522a
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 0 deletions
python/sglang/srt/models/qwen2.py
View file @ a2f602b5
...@@ -356,6 +356,8 @@ class Qwen2ForCausalLM(nn.Module): ...@@ -356,6 +356,8 @@ class Qwen2ForCausalLM(nn.Module):
break break
else: else:
# Skip loading extra bias for GPTQ models. # Skip loading extra bias for GPTQ models.
if "lm_head.weight" in name:
continue
if name.endswith(".bias") and name not in params_dict: if name.endswith(".bias") and name not in params_dict:
continue continue
param = params_dict[name] param = params_dict[name]
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment