-
this model has a vision adapter: mmproj-model-f16.gguf
i never used any vision model in lmstudio, so I don´t know if that is a bug or related to this particular model.
because this model has strong …
-
```
CUDA_VISIBLE_DEVICES=2 python run.py --data MMMU_TEST --model MiniCPM-Llama3-V-2_5 --verbose
Did not detect the .env file at /data/mm/VLMEvalKit/.env, failed to load.
Did not detect the .env fi…
-
### 🚀 The feature, motivation and pitch
Tested with the latest commit but got error:
`[rank0]: ValueError: Model architectures ['MiniCPMV'] are not supported for now. Supported architectures: ['Aq…
wizd updated
11 hours ago
-
### 是否已有关于该错误的issue或讨论? | Is there an existing issue / discussion for this?
- [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions
### 该问题是否在FAQ中有解答? | Is there an existing ans…
-
### 提交前必须检查以下项目 | The following items must be checked before submission
- [X] 请确保使用的是仓库最新代码(git pull),一些问题已被解决和修复。 | Make sure you are using the latest code from the repository (git pull), some issue…
-
> 在导出MiniCPM-V的过程中, Resampler总报错“aten::_upsample_bilinear2d_aa”算子不支持,因此暂时无法使用多模态交互。
在 MiniCPM-V 的 2.0 版本中 [openbmb/MiniCPM-V-2](https://huggingface.co/openbmb/MiniCPM-V-2/tree/main),修改后的 Resampler …
-
Fellow MiniCPM-Llama3-V 2.5 project authors, a few days ago I discovered a shocking fact.There is a large amount of work in the llama3-V (https://github.com/mustafaaljadery/llama3v) project that is su…
-
用vllm如下命令,显示不支持MiniCPM-2.5
CUDA_VISIBLE_DEVICES=0 swift app-ui --model_type minicpm-v-v2_5-chat--infer_backend vllm
然后在swift的gradio端口中也没有找到如何进行粘贴或者上传图片,进行推理,求解答谢谢!
-
### Checklist
- [x] 1. I have searched related issues but cannot get the expected help.
- [x] 2. The bug has not been fixed in the latest version.
### Describe the bug
minicpm-v采用W4A16量化后,显存占用确实小了,…
-
Dear author, hello. I am a staff member of Openbmb and I would like to increase LMs support for our open source community model. However, I am unsure how to proceed. Can you please let me know