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

Gemmasutra 9B V1 by TheDrummer

 »  All LLMs  »  TheDrummer  »  Gemmasutra 9B V1   URL Share it on

  4079   
  Merged Model   Autotrain compatible Base model:beaverai/gemmasutra... Base model:beaverai/gemmasutra...   Conversational   Endpoints compatible   Gemma2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/TheDrummer/Gemmasutra-9B-v1 

Gemmasutra 9B V1 Benchmarks

MMLU Pro: 33.83
GPQA: 8.05
MUSR: 20.94
BBH: 41.2
IFEval: 24.16 vs 88 (so35)-72.5%
MATH Lvl 5: 8.23
LLME Score: 0.32396
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gemmasutra 9B V1 (TheDrummer/Gemmasutra-9B-v1)

Gemmasutra 9B V1 Parameters and Internals

Model Type 
RP model
Use Cases 
Primary Use Cases:
Engaging Roleplay, Creative responses
Limitations:
Some censorship
Considerations:
Use Tiger Gemma if you want zero refusals as an Assistant / during Instruct mode.
Additional Notes 
- Engaging Roleplay with asterisks-capability - Long creative responses - Enhanced moist details - Less mention of the user and more focus on storytelling
Responsible Ai Considerations 
Mitigation Strategies:
Refusals allow the AI to roleplay certain behaviors like avoidance, rejection, etc.
Release Notes 
Version:
v1c
Notes:
This is an RP-enhanced model with some degree of censorship.
LLM NameGemmasutra 9B V1
Repository 🤗https://huggingface.co/TheDrummer/Gemmasutra-9B-v1 
Base Model(s)  BeaverAI/Gemmasutra-9B-v1b   BeaverAI/Gemmasutra-9B-v1a   BeaverAI/Gemmasutra-9B-v1b   BeaverAI/Gemmasutra-9B-v1a
Merged ModelYes
Model Size9b
Required VRAM20.4 GB
Updated2025-01-20
MaintainerTheDrummer
Model Typegemma2
Model Files  5.0 GB: 1-of-5   5.0 GB: 2-of-5   4.9 GB: 3-of-5   5.0 GB: 4-of-5   0.5 GB: 5-of-5
Model ArchitectureGemma2ForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.42.4
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16

Best Alternatives to Gemmasutra 9B V1

Best Alternatives
Context / RAM
Downloads
Likes
G2 GSHT 32K32K / 20.4 GB130
Gemma 2 9B It SimPO8K / 18.6 GB18888141
Gemma 2 9B It8K / 18.6 GB322464622
Gemma 2 9B8K / 37.1 GB90433628
...2 9B Cpt Sahabatai V1 Instruct8K / 18.6 GB229330
Wiroai Turkish Llm 9B8K / 37.1 GB3826814
MT Merge4 Gemma 2 9B8K / 20.4 GB1861
MT Merge5 Gemma 2 9B8K / 20.4 GB962
...erge 02012025163610 Gemma 2 9B8K / 20.4 GB561
Darkest Muse V18K / 20.4 GB39041
Note: green Score (e.g. "73.2") means that the model is better than TheDrummer/Gemmasutra-9B-v1.

Rank the Gemmasutra 9B V1 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? 41636 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