OpenBMB / MiniCPM-V

MiniCPM-Llama3-V 2.5: A GPT-4V Level Multimodal LLM on Your Phone
Apache License 2.0
7.86k stars 547 forks source link

[BUG] <title>windows系统使用ollama运行MiniCPM-Llama3-V-2_5的gguf各种量化版本,均不能加载识别图片 #247

Closed zrainbowk closed 3 weeks ago

zrainbowk commented 3 weeks ago

是否已有关于该错误的issue或讨论? | Is there an existing issue / discussion for this?

该问题是否在FAQ中有解答? | Is there an existing answer for this in FAQ?

当前行为 | Current Behavior

windows系统使用ollama运行MiniCPM-Llama3-V-2_5的gguf各种量化版本,均不能加载识别图片。

e5c0ea3fe8644b854878abecf52d93c

同样使用ollama,更换llava模型可以正常加载识别图片。

2943ceea79a94d5a8659bd9bc63a9fe

期望行为 | Expected Behavior

有什么办法可以使得ollama运行MiniCPM-Llama3-V-2_5的gguf各种量化版本,能成功加载和识别图片

复现方法 | Steps To Reproduce

No response

运行环境 | Environment

- OS:Windows 11 专业版 26100.1
- Python:3.11.7
- Transformers:4.41.2
- PyTorch:2.3.1+cu121
- CUDA (`python -c 'import torch; print(torch.version.cuda)'`):12.4

备注 | Anything else?

No response

TonyHuang6666 commented 3 weeks ago

老哥你好,请问解决了吗?我也是在Windows, WSL和Ubuntu都没法分析图片

nigo81 commented 3 weeks ago

不能用官方的ollama,需要用build的:https://github.com/OpenBMB/MiniCPM-V/issues/171