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

SauerkrautLM SOLAR Instruct by VAGOsolutions

 »  All LLMs  »  VAGOsolutions  »  SauerkrautLM SOLAR Instruct   URL Share it on

  799   
  Augmentation   Autotrain compatible   Conversational Dataset:argilla/distilabel-mat...   De   Dpo   En   Endpoints compatible   Finetuned   German   Instruct   Llama   Region:us   Safetensors   Sharded   Tensorflow

SauerkrautLM SOLAR Instruct Benchmarks

MMLU Pro: 24.26
GPQA: 7.38
MUSR: 8.33
BBH: 31.84
IFEval: 49.17 vs 88 (so35)-44.1%
ARC: 70.82 vs 96.7 (so35)-26.8%
HellaSwag: 88.63 vs 95.3 (gpt4)-7%
MMLU: 66.2 vs 88.3 (so35)-25%
TruthfulQA: 71.95 vs 59 (gpt4)21.9%
WinoGrande: 83.5 vs 87.5 (gpt4)-4.6%
GSM8K: 64.14 vs 96.4 (so35)-33.5%
LLME Score: 0.26004
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

SauerkrautLM SOLAR Instruct Parameters and Internals

Model Type 
text generation, multimodal
Use Cases 
Areas:
research, education, non-commercial applications
Applications:
language translation, text generation
Primary Use Cases:
text augmentation, language proficiency improvement
Limitations:
Possible uncensored content
Considerations:
Ensure appropriate use for target audience.
Additional Notes 
Translation improvements aimed to enhance German language fluency.
Supported Languages 
en (English), de (German)
Training Details 
Data Sources:
VAGOsolutions/SauerkrautLM-DPO, argilla/distilabel-math-preference-dpo, HuggingFaceH4/ultrafeedback_binarized, SFT SauerkrautLM, Sauerkraut-7b-HerO
Methodology:
German language augmentation and translation alignment to improve German proficiency.
Input Output 
Accepted Modalities:
text
Output Format:
formatted text responses
LLM NameSauerkrautLM SOLAR Instruct
Repository 🤗https://huggingface.co/VAGOsolutions/SauerkrautLM-SOLAR-Instruct 
Model Size10.7b
Required VRAM21.4 GB
Updated2024-11-21
MaintainerVAGOsolutions
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 Length8192
Model Max Length8192
Transformers Version4.36.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16
SauerkrautLM SOLAR Instruct (VAGOsolutions/SauerkrautLM-SOLAR-Instruct)

Quantized Models of the SauerkrautLM SOLAR Instruct

Model
Likes
Downloads
VRAM
...uerkrautLM SOLAR Instruct GGUF21974 GB
...uerkrautLM SOLAR Instruct GPTQ296 GB
...auerkrautLM SOLAR Instruct AWQ066 GB

Best Alternatives to SauerkrautLM SOLAR Instruct

Best Alternatives
Context / RAM
Downloads
Likes
SOLAR 10.7B Instruct V1.0 128K128K / 21.4 GB784
SOLAR 10.7B V1.0 Instruct 16K16K / 21.4 GB632
MetaModelv28K / 21.4 GB12460
Kazemi 1.2 Solar8K / 21.4 GB00
SOLAR 10.7B Instruct V1.04K / 21.4 GB151224614
ConfigurableSOLAR 10.7B4K / 21.4 GB47572
...arbonVillain En 10.7B V2 Slerp4K / 21.4 GB127030
...auerkrautLM UNA SOLAR Instruct4K / 21.4 GB126726
...0.7B Instruct STOCK SOLAR Ties4K / 42.9 GB24460
...struct STOCK SOLAR Passthrough4K / 53.4 GB16850
Note: green Score (e.g. "73.2") means that the model is better than VAGOsolutions/SauerkrautLM-SOLAR-Instruct.

Rank the SauerkrautLM SOLAR 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? 38149 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 v20241110
  Support LLM Explorer