MultiModalityCausalLM is not supported #11444
Unanswered
zhkmxx9302013
asked this question in
Q&A
Replies: 2 comments 1 reply
-
|
have you solve this? |
Beta Was this translation helpful? Give feedback.
1 reply
-
|
no，its not support yet |
Beta Was this translation helpful? Give feedback.
-
|
Hey @zhkmxx9302013! 🚀 MultiModalityCausalLM isn’t supported in convert_hf_to_gguf.py since it’s built for standard causal models. Since DeepSeek-VL is multi-modal, check for script updates 🔍, tweak it to map multi-modal layers 🛠️, or try a different format. If stuck, ask the repo maintainers for guidance. 🤝🔥 |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I use the deepseek-vl-7b from safetensor to gguf.
python convert_hf_to_gguf.py F:/Code/deepseek/vlthe result log is below.
INFO:hf-to-gguf:Loading model: vl ERROR:hf-to-gguf:Model MultiModalityCausalLM is not supportedhow to support MultiModalityCausalLM .thx
Beta Was this translation helpful? Give feedback.
All reactions