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

LongVA 7B by lmms-lab

 »  All LLMs  »  lmms-lab  »  LongVA 7B   URL Share it on

  5798   
  Arxiv:2406.16852   Autotrain compatible   Conversational   Endpoints compatible   Instruct   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/lmms-lab/LongVA-7B 

LongVA 7B Benchmarks

LLME Score: 0.23733
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
LongVA 7B (lmms-lab/LongVA-7B)

LongVA 7B Parameters and Internals

Model Type 
Multimodal, Vision, Language
Use Cases 
Areas:
Research, Commercial Applications
Applications:
Image Description, Video Captioning, Assistive Technology
Primary Use Cases:
Describing images and videos, Providing detailed visual information, Assistive technologies for visually impaired
Limitations:
Dependent on GPU memory capacity
Additional Notes 
LongVA supports zero-shot learning capabilities transferring from language to vision and can process large-scale visual data.
Input Output 
Input Format:
Prompts formatted for system and user interaction
Accepted Modalities:
text, image, video
Output Format:
Generative text outputs
Performance Tips:
Possibility to elevate max frames number dependent on GPU memory.
LLM NameLongVA 7B
Repository 🤗https://huggingface.co/lmms-lab/LongVA-7B 
Model Size7b
Required VRAM15.9 GB
Updated2025-02-22
Maintainerlmms-lab
Model Typeqwen2
Instruction-BasedYes
Model Files  4.9 GB: 1-of-4   4.9 GB: 2-of-4   5.0 GB: 3-of-4   1.1 GB: 4-of-4   0.0 GB
Model ArchitectureLlavaQwenForCausalLM
Context Length224000
Model Max Length224000
Transformers Version4.40.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to LongVA 7B

Best Alternatives
Context / RAM
Downloads
Likes
Llava Onevision Qwen2 7B Si32K / 16.1 GB1170012
Note: green Score (e.g. "73.2") means that the model is better than lmms-lab/LongVA-7B.

Rank the LongVA 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? 43470 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 v20241227
  Support LLM Explorer