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

Llava Next 110B by lmms-lab

 »  All LLMs  »  lmms-lab  »  Llava Next 110B   URL Share it on

  9   
  Autotrain compatible   Conversational   Endpoints compatible   Llava   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/lmms-lab/llava-next-110b 

Llava Next 110B Benchmarks

LLME Score: 0.15224
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llava Next 110B (lmms-lab/llava-next-110b)
🌟 Advertise your project 🚀

Llava Next 110B Parameters and Internals

Model Type 
auto-regressive language model, chatbot, transformer architecture
Use Cases 
Areas:
research on large multimodal models and chatbots
Training Details 
Data Sources:
558K filtered image-text pairs from LAION/CC/SBU, captioned by BLIP., 158K GPT-generated multimodal instruction-following data., 500K academic-task-oriented VQA data mixture., 50K GPT-4V data mixture., 40K ShareGPT data., 20K COCO Caption data.
Methodology:
We conducted the training on LLaVA-1.6's codebase with adding support of Llama-3 and Qwen model.
Context Length:
32768
Training Time:
18-20 hours on 16 x 8 NVIDIA H800-SXM4-80GB (may vary due to hardware differences)
Hardware Used:
16 x 8 NVIDIA H800-SXM4-80GB
Model Architecture:
transformer architecture
LLM NameLlava Next 110B
Repository 🤗https://huggingface.co/lmms-lab/llava-next-110b 
Model Size110b
Required VRAM198 GB
Updated2025-09-23
Maintainerlmms-lab
Model Typellava
Model Files  4.4 GB: 1-of-50   4.6 GB: 2-of-50   4.6 GB: 3-of-50   4.3 GB: 4-of-50   4.6 GB: 5-of-50   4.6 GB: 6-of-50   4.3 GB: 7-of-50   4.6 GB: 8-of-50   4.6 GB: 9-of-50   4.3 GB: 10-of-50   4.6 GB: 11-of-50   4.6 GB: 12-of-50   4.3 GB: 13-of-50   4.6 GB: 14-of-50   4.6 GB: 15-of-50   4.3 GB: 16-of-50   4.6 GB: 17-of-50   4.6 GB: 18-of-50   4.3 GB: 19-of-50   4.6 GB: 20-of-50   4.6 GB: 21-of-50   4.3 GB: 22-of-50   4.6 GB: 23-of-50   4.6 GB: 24-of-50   4.3 GB: 25-of-50   4.6 GB: 26-of-50   4.6 GB: 27-of-50   4.3 GB: 28-of-50   4.6 GB: 29-of-50   4.6 GB: 30-of-50   4.3 GB: 31-of-50   4.6 GB: 32-of-50   4.6 GB: 33-of-50   4.3 GB: 34-of-50   4.6 GB: 35-of-50   4.6 GB: 36-of-50   4.3 GB: 37-of-50   4.6 GB: 38-of-50   4.6 GB: 39-of-50   4.3 GB: 40-of-50   4.6 GB: 41-of-50   4.6 GB: 42-of-50   4.3 GB: 43-of-50   4.6 GB: 44-of-50
Model ArchitectureLlavaQwenForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.40.0.dev0
Vocabulary Size152064
Torch Data Typebfloat16

Best Alternatives to Llava Next 110B

Best Alternatives
Context / RAM
Downloads
Likes
Llavanext Qwen Tokenizer32K /  GB112

Rank the Llava Next 110B 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? 51566 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