llama.cpp
Qwen2: assume tied weights if lm_head/output weights is missing
#6738
Merged

Qwen2: assume tied weights if lm_head/output weights is missing #6738

jklj077
jklj077 Qwen2: assume tied weights if lm_head/output weights is missing
c7ab76ea
slaren
slaren approved these changes on 2024-04-18
ggerganov ggerganov merged e11b2e6e into master 1 year ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone