Instructions to use llava-hf/LLaVA-NeXT-Video-7B-hf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use llava-hf/LLaVA-NeXT-Video-7B-hf with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("llava-hf/LLaVA-NeXT-Video-7B-hf") model = AutoModelForMultimodalLM.from_pretrained("llava-hf/LLaVA-NeXT-Video-7B-hf", device_map="auto") - Notebooks
- Google Colab
- Kaggle
rope_scaling factor value is wrong. shoud be 2.0 instead of 2.5
#12
by lalalandw - opened
in the config.json. the scaling factor is 2.5. But no matter in the source code or in the convert weight python file(https://github.com/huggingface/transformers/blob/main/src/transformers/models/llava_next_video/convert_llava_next_video_weights_to_hf.py), all of them showed that the factor shoud be 2.0 when predict. And also the inference result is way much better in 2.0