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

Light 3B by Sakalti

 »  All LLMs  »  Sakalti  »  Light 3B   URL Share it on

  314   
  Merged Model   Arxiv:2306.01708   Autotrain compatible   Conversational   En   Endpoints compatible   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Sakalti/light-3B 

Light 3B Benchmarks

MMLU Pro: 30.83
GPQA: 6.04
MUSR: 8.09
BBH: 27.47
IFEval: 53.37 vs 88 (so35)-39.4%
MATH Lvl 5: 10.8
LLME Score: 0.3649
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Light 3B (Sakalti/light-3B)

Light 3B Parameters and Internals

LLM NameLight 3B
Repository 🤗https://huggingface.co/Sakalti/light-3B 
Merged ModelYes
Model Size3b
Required VRAM6.9 GB
Updated2025-01-20
MaintainerSakalti
Model Typeqwen2
Model Files  0.6 GB: 1-of-8   1.0 GB: 2-of-8   1.0 GB: 3-of-8   1.0 GB: 4-of-8   1.0 GB: 5-of-8   1.0 GB: 6-of-8   1.0 GB: 7-of-8   0.3 GB: 8-of-8
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.45.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Light 3B

Best Alternatives
Context / RAM
Downloads
Likes
Saba2 3B128K / 6.2 GB2940
Light 1.1 3B128K / 6.2 GB591
Saba1.5 Pro 3B128K / 5.8 GB261
SmallThinker 3B Preview32K / 6.8 GB62177361
Qwen2.5 3B Instruct32K / 6.2 GB588599147
Dria Agent A 3B32K / 6.2 GB97643
Qwen2.5 3B32K / 6.2 GB19674048
Neptuno Alpha32K / 6.8 GB2061
Calme 3.2 Instruct 3B32K / 11 GB31991
Calme 3.1 Baguette 3B32K / 6.2 GB27471
Note: green Score (e.g. "73.2") means that the model is better than Sakalti/light-3B.

Rank the Light 3B 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? 41636 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