A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 10:45 UTC
[Bugfix] Weight loading fix for OPT model (#9042)
Co-authored-by: dvres <dvres@fri.uni-lj.si>
Domen Vreš committed
Oct 4, 2024 at 01:53 UTC
2838d6b38e1e37b303b01f2af0a9ddee2dd66f39
1 file changed
+1
-1
vllm/model_executor/models/opt.py
+1
-1
@@ -353,7 +353,7 @@ class OPTForCausalLM(nn.Module):
353
]
354
params_dict = dict(self.named_parameters(remove_duplicate=False))
355
for name, loaded_weight in weights:
356
- if "lm_head.weight" in name:
356
+ if "lm_head.weight" in name and self.config.tie_word_embeddings:
357
continue
358
if name.startswith("decoder."):
359
name = "model." + name