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

Light 1.1 3B by Sakalti

 »  All LLMs  »  Sakalti  »  Light 1.1 3B   URL Share it on

  3   
  Autotrain compatible Base model:finetune:sakalti/li...   Base model:sakalti/light-3b   Conversational   En   Endpoints compatible   Ja   Qwen2   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl   Unsloth
Model Card on HF 🤗: https://huggingface.co/Sakalti/light-1.1-3B 

Light 1.1 3B Benchmarks

MMLU Pro: 2.33
GPQA: 1.57
MUSR: 7.29
BBH: 1.88
IFEval: 27.35 vs 88 (so35)-68.9%
MATH Lvl 5: 1.13
LLME Score: 0.24164
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Light 1.1 3B (Sakalti/light-1.1-3B)

Light 1.1 3B Parameters and Internals

LLM NameLight 1.1 3B
Repository 🤗https://huggingface.co/Sakalti/light-1.1-3B 
Base Model(s)  Light 3B   Sakalti/light-3B
Model Size3b
Required VRAM6.2 GB
Updated2025-05-15
MaintainerSakalti
Model Typeqwen2
Model Files  5.0 GB: 1-of-2   1.2 GB: 2-of-2
Supported Languagesen ja
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length131072
Model Max Length131072
Transformers Version4.47.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Light 1.1 3B

Best Alternatives
Context / RAM
Downloads
Likes
...b Sft Stage1.2 Ss1 Expert Math128K / 15.1 GB110
...2 Ss1 Expert Fictional Lyrical128K / 15.1 GB70
...Sft Stage1.2 Ss1 Expert How To128K / 15.1 GB180
... Formattedtext Math Wiki Merge128K / 15.1 GB60
Saba1.5 Pro 3B128K / 5.8 GB41
...tage1.1 Ss1 With Math.no Issue128K / 15.1 GB50
...ware Howto Formattedtext Merge128K / 15.1 GB50
...1 No Redteam Skg Poem.no Issue128K / 15.1 GB50
...ide 3b Orpo Stage1.1 Ss1 Orpo3128K / 15.1 GB140
...b Sft Stage1.2 Ss1 Expert News128K / 15.1 GB60
Note: green Score (e.g. "73.2") means that the model is better than Sakalti/light-1.1-3B.

Rank the Light 1.1 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? 47368 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