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

LUNA SOLARkrautLM Instruct by fblgit

 »  All LLMs  »  fblgit  »  LUNA SOLARkrautLM Instruct   URL Share it on

  734   

LUNA SOLARkrautLM Instruct is an open-source language model by fblgit. Features: 10.7b LLM, VRAM: 21.4GB, Context: 4K, License: cc-by-nc-4.0, Instruction-Based, HF Score: 73.8, LLM Explorer Score: 0.13, Arc: 71.2, HellaSwag: 88.3, MMLU: 66.1, TruthfulQA: 73.4, WinoGrande: 83, GSM8K: 60.9.

  Augmentation   Conversational Dataset:argilla/distilabel-mat...   De   Doi:10.57967/hf/1517   Dpo   En   Endpoints compatible   Finetuned   German   Instruct   Llama   Model-index   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/fblgit/LUNA-SOLARkrautLM-Instruct 

LUNA SOLARkrautLM Instruct Benchmarks

ARC: 71.16 vs 96.7 (so35)-26.4%
HellaSwag: 88.28 vs 95.3 (gpt4)-7.4%
MMLU: 66.11 vs 88.3 (so35)-25.1%
TruthfulQA: 73.37 vs 59 (gpt4)24.4%
WinoGrande: 82.95 vs 87.5 (gpt4)-5.2%
GSM8K: 60.88 vs 96.4 (so35)-36.8%
LLME Score: 0.12706
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
LUNA SOLARkrautLM Instruct (fblgit/LUNA-SOLARkrautLM-Instruct)
🌟 Advertise your project 🚀

LUNA SOLARkrautLM Instruct Parameters and Internals

Model Type 
LUNA-SOLARkrautLM-Instruct, text-generation
Use Cases 
Areas:
research, commercial applications
Additional Notes 
Despite data cleansing, uncensored content may still occur.
Supported Languages 
English (Yes), German (Yes)
Training Details 
Data Sources:
SauerkrautLM-DPO, argilla/distilabel-math-preference-dpo, HuggingFaceH4/ultrafeedback_binarized
Methodology:
Aligned through DPO with German data augmentation. Translated data was used and unnatural phrasings were corrected using data augmentation techniques.
LLM NameLUNA SOLARkrautLM Instruct
Repository 🤗https://huggingface.co/fblgit/LUNA-SOLARkrautLM-Instruct 
Model Size10.7b
Required VRAM21.4 GB
Updated2026-04-08
Maintainerfblgit
Model Typellama
Instruction-BasedYes
Model Files  4.9 GB: 1-of-5   5.0 GB: 2-of-5   4.9 GB: 3-of-5   4.9 GB: 4-of-5   1.7 GB: 5-of-5
Supported Languagesen de
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-4.0
Context Length4096
Model Max Length4096
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat16

Quantized Models of the LUNA SOLARkrautLM Instruct

Model
Likes
Downloads
VRAM
...UNA SOLARkrautLM Instruct GGUF41994 GB
...UNA SOLARkrautLM Instruct GPTQ256 GB
LUNA SOLARkrautLM Instruct AWQ066 GB

Best Alternatives to LUNA SOLARkrautLM Instruct

Best Alternatives
Context / RAM
Downloads
Likes
SOLAR 10.7B Instruct V1.0 128K128K / 21.4 GB1243
SOLAR 10.7B V1.0 Instruct 16K16K / 21.4 GB632
SauerkrautLM SOLAR Instruct8K / 21.4 GB96846
MetaModelv28K / 21.4 GB7860
Kazemi 1.2 Solar8K / 21.4 GB00
SOLAR 10.7B Instruct V1.04K / 21.4 GB37162649
Somer24K / 21.4 GB100
SOLAR 10.7B Instruct V1.04K / 21.4 GB120
Solarmer34K / 21.4 GB50
Somer4K / 21.4 GB50
Note: green Score (e.g. "73.2") means that the model is better than fblgit/LUNA-SOLARkrautLM-Instruct.

Rank the LUNA SOLARkrautLM Instruct 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? 52721 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