Skip to content

GitLab

Unverified Commit c152e2a8 authored by Yuxuan Zhang's avatar Yuxuan Zhang Committed by GitHub
Browse files

not tie_word_embeddings for glm-4.5 and glm-4.5v (#22460) 


Signed-off-by: default avatarzRzRzRzRzRzRzR <2448370773@qq.com>
parent 17eaaef5
Hide whitespace changes
Inline Side-by-side
Showing with 0 additions and 2 deletions
vllm/model_executor/models/glm4_moe.py
View file @ c152e2a8
......@@ -601,8 +601,6 @@ class Glm4MoeForCausalLM(nn.Module, SupportsPP, SupportsLoRA):
quant_config=quant_config)
else:
self.lm_head = PPMissingLayer()
if self.config.tie_word_embeddings:
self.lm_head.weight = self.model.embed_tokens.weight
self.logits_processor = LogitsProcessor(config.vocab_size)
self.make_empty_intermediate_tensors = (
self.model.make_empty_intermediate_tensors)
......
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