LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

VideoLLaMA2 7B by DAMO-NLP-SG

 »  All LLMs  »  DAMO-NLP-SG  »  VideoLLaMA2 7B   URL Share it on

  11894   
  Arxiv:2306.02858   Arxiv:2406.07476   Autotrain compatible   Dataset:lin-chen/sharegpt4v Dataset:liuhaotian/llava-instr... Dataset:opengvlab/videochat2-i...   En   Endpoints compatible   Instruct   Large video-language model Multimodal large language mode...   Region:us   Safetensors   Sharded   Tensorflow   Videollama2 mistral   Visual-question-answering
Model Card on HF 🤗: https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-7B 

VideoLLaMA2 7B Benchmarks

LLME Score: 0.26885
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
VideoLLaMA2 7B (DAMO-NLP-SG/VideoLLaMA2-7B)

VideoLLaMA2 7B Parameters and Internals

Model Type 
multimodal large language model, large video-language model
Release Notes 
Version:
VideoLLaMA2-7B-Base
Notes:
Base variant with a visual encoder and language decoder. Trained on 8 frames.
Version:
VideoLLaMA2-7B
Notes:
Chat variant with a visual encoder and language decoder. Trained on 8 frames.
Version:
VideoLLaMA2-7B-16F-Base
Notes:
Base variant with 16 training frames.
Version:
VideoLLaMA2-7B-16F
Notes:
Chat variant with 16 training frames.
Version:
VideoLLaMA2-8x7B-Base
Notes:
Base variant with Mixtral-8x7B-Instruct-v0.1 and 8 frames.
Version:
VideoLLaMA2-8x7B
Notes:
Chat variant with Mixtral-8x7B-Instruct-v0.1 and 8 frames.
Version:
VideoLLaMA2-72B-Base
Notes:
Base variant with Qwen2-72B-Instruct and 8 frames.
Version:
VideoLLaMA2-72B
Notes:
Chat variant with Qwen2-72B-Instruct and 8 frames.
LLM NameVideoLLaMA2 7B
Repository 🤗https://huggingface.co/DAMO-NLP-SG/VideoLLaMA2-7B 
Model Size7b
Required VRAM16 GB
Updated2024-12-14
MaintainerDAMO-NLP-SG
Model Typevideollama2_mistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   1.1 GB: 4-of-4
Supported Languagesen
Model ArchitectureVideollama2MistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to VideoLLaMA2 7B

Best Alternatives
Context / RAM
Downloads
Likes
VideoLLaMA2 7B 16F32K / 16 GB69814

Rank the VideoLLaMA2 7B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 39237 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124
  Support LLM Explorer