Zhe Chen
The 4-bit version of the model has been released. Check it out at [OpenGVLab/InternVL-Chat-V1-5-AWQ](https://huggingface.co/OpenGVLab/InternVL-Chat-V1-5-AWQ). Thanks to the lmdeploy team for their support with model quantization. I'm closing this issue now,...
Thank you for your interest! I have this plan, estimated in the next few days.
Hello, thank you for your interest, can you provide more information, such as what command is used to load the model?
Oh, I figured it out. You should go to the `internvl_chat` folder and execute the following command: ```shell python3.10 -m internvl.serve.model_worker --host 0.0.0.0 --controller http://localhost:10000/ --port 40000 --device auto --worker...
Yes, I have considered Mac, but I've been quite busy with work lately and haven't had the time to try it out. On the other hand, my Mac only has...
这边需要对不同语言模型用不同的key去匹配，我加个TODO。
Sorry for giving the wrong link, now readme has corrected it, please download the following two files: wget https://huggingface.co/OpenGVLab/InternVL/raw/main/textvqa_val.jsonl wget https://huggingface.co/OpenGVLab/InternVL/raw/main/textvqa_val_llava.jsonl
May I ask are you trying to use this model weight: https://huggingface.co/OpenGVLab/InternVL-14B-224px
[InternVL-14B-224px](https://huggingface.co/OpenGVLab/InternVL-14B-224px) is the only CLIP-like model we have released so far, and there are currently no plans to develop a smaller CLIP model. Since there hasn't been much activity for...
Due to using only single-image samples during training, the model's responses are not very stable when dealing with multiple images. We plan to collect some multi-image QA data to enhance...