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

LLaVA Phi 3 Mini 4K Instruct FT by MBZUAI

 »  All LLMs  »  MBZUAI  »  LLaVA Phi 3 Mini 4K Instruct FT   URL Share it on

  26   
  Autotrain compatible   Conversational   Custom code   Endpoints compatible   Instruct   Llava phi   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/MBZUAI/LLaVA-Phi-3-mini-4k-instruct-FT 

LLaVA Phi 3 Mini 4K Instruct FT Benchmarks

LLME Score: 0.18282
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
LLaVA Phi 3 Mini 4K Instruct FT (MBZUAI/LLaVA-Phi-3-mini-4k-instruct-FT)

LLaVA Phi 3 Mini 4K Instruct FT Parameters and Internals

Model Type 
vision-language understanding, multimodal
Training Details 
Data Sources:
LCS-558K, LLaVA-Instruct-665K
Methodology:
Pretraining and fine-tuning strategies are used. During pretraining, only the Vision-to-Language projector is trained, while all other model parameters are frozen. During fine-tuning, all model parameters are updated, with the exception of the vision-backbone (CLIP) which remains frozen.
LLM NameLLaVA Phi 3 Mini 4K Instruct FT
Repository 🤗https://huggingface.co/MBZUAI/LLaVA-Phi-3-mini-4k-instruct-FT 
Model Size4.1b
Required VRAM8.3 GB
Updated2025-02-22
MaintainerMBZUAI
Model Typellava_phi
Instruction-BasedYes
Model Files  5.0 GB: 1-of-2   3.3 GB: 2-of-2   0.0 GB
Model ArchitectureLlavaPhiForCausalLM
Licensemit
Context Length4096
Model Max Length4096
Transformers Version4.41.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to LLaVA Phi 3 Mini 4K Instruct FT

Best Alternatives
Context / RAM
Downloads
Likes
LLaVA Phi 3 Mini 4K Instruct4K / 8.3 GB230722
Llava V1.5 Phi3 Derma4K / 8.3 GB110
Note: green Score (e.g. "73.2") means that the model is better than MBZUAI/LLaVA-Phi-3-mini-4k-instruct-FT.

Rank the LLaVA Phi 3 Mini 4K Instruct FT 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