Visual Question Answering
Transformers
English
videollama2_mixtral
text-generation
multimodal large language model
large video-language model
Instructions to use DAMO-NLP-SG/VideoLLaMA2-8x7B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DAMO-NLP-SG/VideoLLaMA2-8x7B-Base with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "visual-question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("visual-question-answering", model="DAMO-NLP-SG/VideoLLaMA2-8x7B-Base")# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("DAMO-NLP-SG/VideoLLaMA2-8x7B-Base", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Update config.json
Zesen ChengVerified signaturebab71d8 -
Update README.md
Verified signaturea2c9800 -
update 72b model
Verified signatured99f1ce
-
Update README.md
Verified signatureb41dd4a -
Update README.md
Verified signaturef1f1ca1 -
Update README.md
Verified signaturec992340 -
copy 7b base
Verified signature787f367 -
Upload model weights.
a8fb83c
-
initial commit
Zesen ChengVerified signature9f0b48f