Dennis Huang
Dennis Huang
Thank you for sharing the detailed fix😊!
@tc-mb Let me confirm it.
@kada0720 @jessie-chen99 No problem, you can just follow [this LLaMA-Factory file](https://github.com/hiyouga/LLaMA-Factory/blob/main/data/mllm_video_audio_demo.json) to build the relevant data. But keep in mind — if you’re using MiniCPM-V 4.5, you won’t be able...
Could you please provide a bit more information so we can better pinpoint the issue? For example, the vLLM startup command, the full logs, and your GPU model?
Thank you for the detailed response! We’ll try to reproduce the issue on our end and investigate further. We’ll get back to you as soon as we have any updates....
@mythzZzZ After some investigation, it looks like there might be an issue with your inference code. You can try using the code below for offline inference with vLLM — it...
That's a strange issue 🤔, and it does seem possible that it could be related to the CUDA version. You might want to try upgrading your CUDA version and see...
MiniCPM-V 4.5 is now available on Ollama. You can access the model via [this link](https://ollama.com/openbmb/minicpm-v4.5). You can also run MiniCPM-V 4.5 directly on Ollama using this command: `ollama run openbmb/minicpm-v4.5`
您好，感谢您的反馈。 由于您当前的数据量较大，在预处理阶段出现了显著的 I/O 与内存瓶颈，导致 tokenizer 进程逐渐变慢，最终因通信超时而中断。您可以尝试缩小数据集或联系LLaMA-Factory官方修改数据加载逻辑。 此外，关于您提到的 streaming 模式报错问题，根据现有信息分析，可能与数据集格式或组织方式有关，建议检查数据格式是否符合流式读取的要求。如能提供更详细的错误日志和数据集结构，我们将能进一步定位问题。