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

TinyLLaVA 2.0B by bczhou

 »  All LLMs  »  bczhou  »  TinyLLaVA 2.0B   URL Share it on

  68   

TinyLLaVA 2.0B is an open-source language model by bczhou. Features: 2.0b LLM, VRAM: 4.1GB, Context: 4K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.12.

  Arxiv:2402.14289   Conversational   Custom code   Dataset:lin-chen/sharegpt4v Dataset:liuhaotian/llava-instr... Dataset:liuhaotian/llava-pretr...   En   Endpoints compatible   Image-text-to-text   Instruct   Llava   Lmm   Region:us   Safetensors   Tiny llava stablelm   Vision   Vision-language   Zh
Model Card on HF 🤗: https://huggingface.co/bczhou/TinyLLaVA-2.0B 

TinyLLaVA 2.0B Benchmarks

LLME Score: 0.11864
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
TinyLLaVA 2.0B (bczhou/TinyLLaVA-2.0B)
🌟 Advertise your project 🚀

TinyLLaVA 2.0B Parameters and Internals

Model Type 
text generation, multimodal, vision-language
Additional Notes 
TinyLLaVA models are designed to provide high performance with fewer parameters.
Supported Languages 
en (English), zh (Chinese)
Training Details 
Data Sources:
LLaVA, ShareGPT4V
Data Volume:
558K LAION-CC-SBU subset
Methodology:
Pretrained and finetuned
Context Length:
3072
Model Architecture:
Small-scale Large Multimodal Model
Input Output 
Input Format:
image-text prompt
Accepted Modalities:
image, text
Output Format:
text
Release Notes 
Version:
TinyLLaVA-1.4B
Date:
2024-01-11
Notes:
First model release.
Version:
TinyLLaVA-1.5B
Date:
2024-02-25
Notes:
Model release.
Version:
TinyLLaVA-2.0B
Date:
2024-02-25
Notes:
Model release.
Version:
TinyLLaVA-3.1B
Date:
2024-02-25
Notes:
Model release.
LLM NameTinyLLaVA 2.0B
Repository 🤗https://huggingface.co/bczhou/TinyLLaVA-2.0B 
Model Size2.0b
Required VRAM4.1 GB
Updated2026-05-21
Maintainerbczhou
Model Typetiny_llava_stablelm
Instruction-BasedYes
Model Files  4.1 GB
Supported Languagesen zh
Model ArchitectureTinyLlavaStablelmForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.37.2
Tokenizer ClassArcade100kTokenizer
Padding Token<|endoftext|>
Vocabulary Size100352
Torch Data Typebfloat16
Errorsreplace

Rank the TinyLLaVA 2.0B 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? 53999 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer