Visual Question Answering
Transformers
Safetensors
English
videollama3_qwen2
text-generation
multi-modal
large-language-model
video-language-model
custom_code
Instructions to use DAMO-NLP-SG/VideoLLaMA3-7B-Image with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DAMO-NLP-SG/VideoLLaMA3-7B-Image with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="DAMO-NLP-SG/VideoLLaMA3-7B-Image", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("DAMO-NLP-SG/VideoLLaMA3-7B-Image", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "chat_template": "\n{%- set identifier = 'im' %}\n{% for message in messages %}\n {% if add_system_prompt and loop.first and message['role'] != 'system' %}\n {{- '<|im_start|>system\nYou are VideoLLaMA3 created by Alibaba DAMO Academy, a helpful assistant to help people understand images and videos.<|im_end|>\n' -}}\n {% endif %}\n {% if message['role'] == 'stream' %}\n {% set identifier = 'stream' %}\n {% else %}\n {% set identifier = 'im' %}\n {% endif %}\n {{- '<|' + identifier + '_start|>' + message['role'] + '\n' -}}\n {% if message['content'] is string %}\n {{- message['content'] + '<|' + identifier + '_end|>\n' -}}\n {% else %}\n {% for content in message['content'] %}\n {% if content is string %}\n {{- content -}}\n {% elif content['type'] == 'text' or 'text' in content %}\n {{- content['text'] -}}\n {% elif content['type'] == 'image' or 'image' in content %}\n {% if 'timestamp' in content %}\n {{- 'Time ' + content['timestamp'] | round(1) | string + 's: ' -}}\n {% endif %}\n {{- image_token + '\n' -}}\n {% elif content['type'] == 'video' or 'video' in content %}\n {% for i in range(content['num_frames']) %}\n {% if 'timestamps' in content %}\n {{- 'Time ' + content['timestamps'][i] | round(1) | string + 's:' -}}\n {% endif %}\n {% if i < content['num_frames'] - 1 %}\n {{- image_token + ',' -}}\n {% else %}\n {{- image_token + '\n' -}}\n {% endif %}\n {% endfor %}\n {% endif %}\n {% endfor %}\n {% if identifier == 'stream' %}\n {{- '<|' + identifier + '_end|>' -}}\n {% else %}\n {{- '<|' + identifier + '_end|>\n' -}}\n {% endif %}\n {% endif %}\n{% endfor %}\n{% if add_generation_prompt %}\n {{- '<|im_start|>assistant\n' -}}\n{% endif %}\n" | |
| } | |