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

LLaVA Lightning MPT 7B Preview by liuhaotian

 »  All LLMs  »  liuhaotian  »  LLaVA Lightning MPT 7B Preview   URL Share it on

  101   
  Autotrain compatible   Instruct   Llava mpt   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/liuhaotian/LLaVA-Lightning-MPT-7B-preview 

LLaVA Lightning MPT 7B Preview Benchmarks

LLME Score: 0.09878
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
LLaVA Lightning MPT 7B Preview (liuhaotian/LLaVA-Lightning-MPT-7B-preview)

LLaVA Lightning MPT 7B Preview Parameters and Internals

Model Type 
multimodal, chatbot, transformer
Use Cases 
Areas:
research
Applications:
large multimodal models and chatbots
Primary Use Cases:
Research on large multimodal models
Additional Notes 
The model is an open-source chatbot trained by fine-tuning LLaMA/Vicuna/MPT on GPT-generated multimodal instruction-following data. It should comply with MPT-7B-chat license and agreements.
Training Details 
Data Sources:
LAION, CC, SBU
Data Volume:
558K filtered image-text pairs, 80K GPT-generated multimodal instruction-following data
Methodology:
Fine-tuning LLaMA/Vicuna/MPT on GPT-generated multimodal instruction-following data
Training Time:
Trained in May 2023
Model Architecture:
Transformer
LLM NameLLaVA Lightning MPT 7B Preview
Repository 🤗https://huggingface.co/liuhaotian/LLaVA-Lightning-MPT-7B-preview 
Model Size7b
Required VRAM13.3 GB
Updated2025-04-25
Maintainerliuhaotian
Model Typellava_mpt
Instruction-BasedYes
Model Files  9.9 GB: 1-of-2   3.4 GB: 2-of-2
Model ArchitectureLlavaMPTForCausalLM
Licensecc-by-nc-sa-4.0
Model Max Length2048
Transformers Version4.28.0.dev0
Tokenizer ClassGPTNeoXTokenizer
Vocabulary Size50282
Torch Data Typefloat16

Rank the LLaVA Lightning MPT 7B Preview 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? 46715 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