Hugging Face's logo

Qwen
/
Qwen2-VL-2B-Instruct

Image-Text-to-Text
Transformers
Safetensors
English
qwen2_vl
multimodal
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
25

RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cuda:0)

#24
by zkkz17 - opened
Discussion
zkkz17

RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cuda:0). The 7B model did not show any anomalies, but the 2B model did. Changing "device_map" from "auto" or "balanced" to a specified GPU can resolve the issue.

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment