Bunny V1.0 3B by BAAI

 ยป  All LLMs  ยป  BAAI  ยป  Bunny V1.0 3B   URL Share it on

  Arxiv:2402.11530   Autotrain compatible   Bunny-phi   Custom code   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF ๐Ÿค—: https://huggingface.co/BAAI/Bunny-v1_0-3B 

Bunny V1.0 3B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Bunny V1.0 3B (BAAI/Bunny-v1_0-3B)

Bunny V1.0 3B Parameters and Internals

Model Type 
multimodal
Additional Notes 
This is the merged weights of bunny-phi-2-siglip-lora. Bunny-v1.0-3B model built upon SigLIP and Phi-2 outperforms state-of-the-art MLLMs of similar size and even larger ones, including 13B models.
Training Details 
Data Sources:
LAION-2M, Bunny-695K
LLM NameBunny V1.0 3B
Repository ๐Ÿค—https://huggingface.co/BAAI/Bunny-v1_0-3B 
Model Size3b
Required VRAM6.4 GB
Updated2025-03-22
MaintainerBAAI
Model Typebunny-phi
Model Files  5.0 GB: 1-of-2   1.4 GB: 2-of-2
Model ArchitectureBunnyPhiForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.36.2
Tokenizer ClassCodeGenTokenizer
Vocabulary Size50295
Torch Data Typefloat16

Best Alternatives to Bunny V1.0 3B

Best Alternatives
Context / RAM
Downloads
Likes
Opencsg Bunny V0.1 3B2K / 6.4 GB173

Rank the Bunny V1.0 3B Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 45389 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227