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

SauerkrautLM Gemma 7B by VAGOsolutions

 »  All LLMs  »  VAGOsolutions  »  SauerkrautLM Gemma 7B   URL Share it on

  7778   
  Alpha   Autotrain compatible   De   Dpo   En   Endpoints compatible   Finetuned   Gemma   Laser-qlora   Laserrmt   Region:us   Safetensors   Sft   Sharded   Tensorflow   Work in progress
Model Card on HF 🤗: https://huggingface.co/VAGOsolutions/SauerkrautLM-Gemma-7b 

SauerkrautLM Gemma 7B Benchmarks

MMLU Pro: 21.79
GPQA: 4.81
MUSR: 2.93
BBH: 18.49
IFEval: 34.07 vs 88 (so35)-61.3%
ARC: 59.98 vs 96.7 (so35)-38%
HellaSwag: 81.91 vs 95.3 (gpt4)-14.1%
MMLU: 63.76 vs 88.3 (so35)-27.8%
TruthfulQA: 61 vs 59 (gpt4)3.4%
WinoGrande: 76.64 vs 87.5 (gpt4)-12.4%
GSM8K: 63.68 vs 96.4 (so35)-33.9%
MATH Lvl 5: 5.51
LLME Score: 0.2823
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
SauerkrautLM Gemma 7B (VAGOsolutions/SauerkrautLM-Gemma-7b)

SauerkrautLM Gemma 7B Parameters and Internals

Model Type 
finetuned
Additional Notes 
Early stage finetuned model with potential strange behavior.
Supported Languages 
de (trained), en (trained)
Training Details 
Data Sources:
SFT, DPO, Laser data(x), Laser again on data(y)
Methodology:
Spherical Linear Interpolation and a lasered version of the model, partially freezing with laser-like analysis
Model Architecture:
novel training technique: laser-QLoRA
Input Output 
Input Format:
vicuna prompt template
Performance Tips:
Use stopping strings "~~", " "
Release Notes 
Version:
01.03.2024
Date:
2024-03-01
Notes:
Reuploaded the model in bfloat16 dtype.
Version:
02.03.2024
Date:
2024-03-02
Notes:
Strongest Gemma finetune model so far with additional scoring.
LLM NameSauerkrautLM Gemma 7B
Repository 🤗https://huggingface.co/VAGOsolutions/SauerkrautLM-Gemma-7b 
Model Size7b
Required VRAM17.1 GB
Updated2024-12-21
MaintainerVAGOsolutions
Model Typegemma
Model Files  5.0 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   2.1 GB: 4-of-4
Supported Languagesde en
Model ArchitectureGemmaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.39.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16

Best Alternatives to SauerkrautLM Gemma 7B

Best Alternatives
Context / RAM
Downloads
Likes
Kaggle Math Model Gemma V112K / 17.1 GB240
Gemma 1.1 7B It8K / 17.1 GB15665267
SeaLLM 7B V2.58K / 17.1 GB1495849
Zephyr 7B Gemma V0.18K / 17.1 GB763121
... Codegemma 2 7B It Alpaca V1.38K / 17.1 GB190
Codegemma 7B8K / 17.1 GB3463170
Codegemma 7B It8K / 17.1 GB1964205
DiscoPOP Zephyr 7B Gemma8K / 17.1 GB708536
Gemma 7B Openhermes V0.808K / 17 GB74681
Gemma 1.1 7B It8K / 17.1 GB74343
Note: green Score (e.g. "73.2") means that the model is better than VAGOsolutions/SauerkrautLM-Gemma-7b.

Rank the SauerkrautLM Gemma 7B 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? 40013 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 v20241217
  Support LLM Explorer