NKU-2urSt8g
NKU-2urSt8g
> Hello, sorry to disturb you. I met the same problem. Have you solved the problem now? nope
Could you list the details of the runtime error you have counted? > Hello. In the README you say that with scipy>1.9 FVD calculations will be wrong. Could you, please,...
**OOM when finetuning Cambrian in the 80GB A100 cluster even with a batch size of 1** **Description:** I am encountering an Out-of-Memory (OOM) error while attempting to fine-tune the Cambrian...
> > **OOM when finetuning Cambrian in the 80GB A100 cluster even with a batch size of 1** > > **Description:** I am encountering an Out-of-Memory (OOM) error while attempting...
> @nku-zhichengzhang it seems that 15.58G memories are reserved by pytorch but unallocated. You may follow the instruction given by the error, or try to clear cuda memories. Loading the...
> > > @nku-zhichengzhang it seems that 15.58G memories are reserved by pytorch but unallocated. You may follow the instruction given by the error, or try to clear cuda memories....
> Hi, thanks for this brilliant project. Is there any ETA for releasing the GPU training script and evaluation code? > > Thanks in advance. Hi, have you found the...
> Can you follow https://docs.vllm.ai/en/latest/getting_started/troubleshooting.html to get more detailed logs? cc [@youkaichao](https://github.com/youkaichao) Thx for the reply, and here is the logging. run sh: `/home/zhangzhicheng03/anaconda3/envs/videva/bin/python /home/zhangzhicheng03/code/face-llm/ms-swift/swift/cli/infer.py --ckpt_dir /home/zhangzhicheng03/HuggingFace/VideoLLM/models--Qwen--Qwen2.5-VL-72B-Instruct --infer_backend vllm --val_dataset...
You can try this: https://github.com/QwenLM/Qwen2.5-VL/pull/1078