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

Luxia 21.4B Alignment V1.0 by saltlux

 »  All LLMs  »  saltlux  »  Luxia 21.4B Alignment V1.0   URL Share it on

  11449   
  Autotrain compatible   En   Endpoints compatible   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/saltlux/luxia-21.4b-alignment-v1.0 

Luxia 21.4B Alignment V1.0 Benchmarks

MMLU Pro: 26.7
GPQA: 6.82
MUSR: 12.51
BBH: 48.02
IFEval: 36.93 vs 88 (so35)-58%
ARC: 77.73 vs 96.7 (so35)-19.6%
HellaSwag: 91.82 vs 95.3 (gpt4)-3.7%
MMLU: 68.05 vs 88.3 (so35)-22.9%
TruthfulQA: 79.2 vs 59 (gpt4)34.2%
WinoGrande: 87.37 vs 87.5 (gpt4)-0.1%
GSM8K: 62.24 vs 96.4 (so35)-35.4%
MATH Lvl 5: 9.74
LLME Score: 0.27602
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

Luxia 21.4B Alignment V1.0 Parameters and Internals

Model Type 
instruction-tuned, alignment model
Additional Notes 
Data Contamination Test Results and Evaluation Results will be updated soon.
Supported Languages 
en (proficient)
Training Details 
Methodology:
state-of-the-art instruction fine-tuning methods including supervised fine-tuning (SFT) and direct preference optimization (DPO)
LLM NameLuxia 21.4B Alignment V1.0
Repository 🤗https://huggingface.co/saltlux/luxia-21.4b-alignment-v1.0 
Model Size21.4b
Required VRAM42.8 GB
Updated2025-06-09
Maintainersaltlux
Model Typellama
Model Files  9.8 GB: 1-of-5   9.8 GB: 2-of-5   9.9 GB: 3-of-5   9.9 GB: 4-of-5   3.4 GB: 5-of-5
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Is Biased0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size92544
Torch Data Typebfloat16
Luxia 21.4B Alignment V1.0 (saltlux/luxia-21.4b-alignment-v1.0)

Quantized Models of the Luxia 21.4B Alignment V1.0

Model
Likes
Downloads
VRAM
...uxia 21.4B Alignment V1.0 GGUF91938 GB

Best Alternatives to Luxia 21.4B Alignment V1.0

Best Alternatives
Context / RAM
Downloads
Likes
Luxia 21.4B Alignment V1.232K / 43 GB73299
UNA ThePitbull 21.4B V232K / 43 GB2116
Final Model Test V232K / 43 GB150
DPO Model Test132K / 43 GB50
Sft Model Test132K / 43 GB100
UNA ThePitbull 21.4 V132K / 43 GB85
Merge Model Test232K / 42.8 GB80
Merge Model Test132K / 42.8 GB60
Sft Model Test032K / 43 GB70
All DPO Model Test132K / 43 GB70
Note: green Score (e.g. "73.2") means that the model is better than saltlux/luxia-21.4b-alignment-v1.0.

Rank the Luxia 21.4B Alignment V1.0 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? 48046 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 v20241124
  Support LLM Explorer