Welcome to LLaVA Discussions!

[haotian-liu]

👋 Welcome!

We’re using Discussions as a place to connect with other members of our community. We hope that you:

• Ask questions you’re wondering about.
• Share ideas.
• Engage with other community members.
• Welcome others and are open-minded. Remember that this is a community we build together 💪.

To get started, comment below with an introduction of yourself and tell us about what you do with this community.

[mudomau]

wave Welcome!

We’re using Discussions as a place to connect with other members of our community. We hope that you:

* Ask questions you’re wondering about.

* Share ideas.

* Engage with other community members.

* Welcome others and are open-minded. Remember that this is a community we
  build together muscle.

To get started, comment below with an introduction of yourself and tell us about what you do with this community.

Hi! I'm mau, just a guy whos curious about AI. I started experimenting with LLaMa/Alpaca/Vicuna when they came out, and decided to try now LLaVA too 😃 Really impressed with it so far. Looking forward to seeing how your project develops.

doc_2023-04-25_16-22-14.mp4

[zolf1983]

执行以下语句：python -m llava.serve.model_worker --host 192.168.2.114 --controller http://192.168.2.114:10000/ --port 40000 --worker http://192.168.2.114:40000/ --model-path E:/llava/llava-v1.5-13b
报错: OS错误: E:/llava/llava-v1.5-13b 似乎没有名为 preprocessor_config.json的文件.查看可用的文件的"https://huggingface.co/E:/llava/llava-v1.5-13b/main".想启动本地的模型为什么会报这样的错误呢？启动本地模型需要改什么配置呢？
本地模型文件在https://huggingface.co/liuhaotian/llava-v1.5-13b/tree/main 下载的，放在本地E:/llava/llava-v1.5-13b文件夹下。

[HarshmJenya]

I have tried to load the model running the command:
python -m llava.serve.model_worker --host "0.0.0.0" --controller-address "http://localhost:10000" --port 40000 --worker-address "http://localhost:40000" --model-path "models/llava-v1.5-7b" --load-8bit
and
encountered the following error

[Marco-DAmato]

Hi,

Is LLaVA 1.5 or even better 1.6 preview available in Google Colab? I mean the entire pipeline where the model is trained and fine-tuned in Google Colab. Anyone that can help?

Thanks for your time.

[Eilyn]

Hello, I am trying to run the liuhaotian/llava-v1.5-13b sample, however I am getting the CUDA out of memory error. I saw in the read me that there are some parameters which could be used to run the code with less GPUs, however I cannot find where to configure those.

Any advice?

[kalle07]

i tryed llava 1.5 and 1.6 its not better in recognizing images than boro-tag-coco.
Who has other experiences?