Visual Question Answering
Transformers
Safetensors
English
videollama2_qwen2
text-generation
Audio-visual Question Answering
Audio Question Answering
multimodal large language model
Instructions to use DAMO-NLP-SG/VideoLLaMA2.1-7B-AV with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DAMO-NLP-SG/VideoLLaMA2.1-7B-AV with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="DAMO-NLP-SG/VideoLLaMA2.1-7B-AV")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("DAMO-NLP-SG/VideoLLaMA2.1-7B-AV", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download special_tokens_map.json from DAMO-NLP-SG/VideoLLaMA2.1-7B-AV: direct link, hf CLI and curl.
- Browser
- Download file 367 Bytes
-
https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2.1-7B-AV/resolve/main/special_tokens_map.json
- Command line
-
hf download hf://DAMO-NLP-SG/VideoLLaMA2.1-7B-AV/special_tokens_map.json
-
curl -L -o special_tokens_map.json https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2.1-7B-AV/resolve/main/special_tokens_map.json
367 Bytes
| { | |
| "additional_special_tokens": [ | |
| "<|im_start|>", | |
| "<|im_end|>" | |
| ], | |
| "eos_token": { | |
| "content": "<|im_end|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "pad_token": { | |
| "content": "<|endoftext|>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| } | |
| } | |