Closed pseudotensor closed 3 months ago
2.0.4 docker image
https://github.com/huggingface/text-generation-inference/pull/1709#issuecomment-2134264274
llava next 1.6 was supposedly added, but 34b fails.
72b can't use sharding: https://github.com/huggingface/text-generation-inference/pull/1709#issuecom
Even lmms-lab/llama3-llava-next-8b fails same way
This issue is stale because it has been open 30 days with no activity. Remove stale label or comment or this will be closed in 5 days.
System Info
2.0.4 docker image
Information
Tasks
Reproduction
https://github.com/huggingface/text-generation-inference/pull/1709#issuecomment-2134264274
Expected behavior
llava next 1.6 was supposedly added, but 34b fails.
72b can't use sharding: https://github.com/huggingface/text-generation-inference/pull/1709#issuecom