LLaVA-NeXT
LLaVA-NeXT copied to clipboard
LLaVA-VL
I run scripts/video/eval/activitynet_eval.sh, but there are no llavavid/eval in the project
I'm always missing the `transformer_engine` package after running `pip install -e ".[train]"` and attempt to run the demo ``` bash scripts/video/demo/video_demo.sh lmms-lab/LLaVA-NeXT-Video-32B-Qwen qwen_1_5 32 2 average after grid True ```...
不是引流，只是考虑到可能大家会有些不构成 issue 的小问题，有个群会比较好。 后续如果官方有需要，我愿意转让群管理 我的微信 dreamingforhope ，若二维码失效可添加我 
# Common Issue More Questions will be added...... ## Training Related Q : Can not finetune the existing LLaVA-Onevision checkpoints A : We edit our model's config so that it...
Hello, I noticed that `image_features = self.get_model().vision_resampler(image_features, images=images)` in the `encode_images` function has been commented out. Does this apply to all models in this repository?
Great job, may I ask how to implement the training format of alternating graphics and text? I have made changes according to the instructions in the repo, and this is...
I tried the demo code and got an error: ``` from llava.model.builder import load_pretrained_model from llava.mm_utils import get_model_name_from_path, process_images, tokenizer_image_token from llava.constants import IMAGE_TOKEN_INDEX, DEFAULT_IMAGE_TOKEN, DEFAULT_IM_START_TOKEN, DEFAULT_IM_END_TOKEN, IGNORE_INDEX from llava.conversation...
The link in `scripts/train/README.md` is broken: https://huggingface.co/collections/lmms-lab/llava-next-6623288e2d61edba3ddbf5ff
Great job! Thank you for your open-source code. I have a question about a part of the code: Why is the "times" parameter set to 1.1 instead of 1.0? :...
