Gemma 2 9B ArliAI RPMax V1.1 by ArliAI

 ยป  All LLMs  ยป  ArliAI  ยป  Gemma 2 9B ArliAI RPMax V1.1   URL Share it on

  Gemma2   Region:us   Safetensors   Sharded   Tensorflow

Gemma 2 9B ArliAI RPMax V1.1 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gemma 2 9B ArliAI RPMax V1.1 (ArliAI/Gemma-2-9B-ArliAI-RPMax-v1.1)

Gemma 2 9B ArliAI RPMax V1.1 Parameters and Internals

Model Type 
creative writing, role-playing
Use Cases 
Areas:
creative writing, role-playing applications
Limitations:
The model might not adhere to a specific personality consistently., One epoch training for minimized repetition sickness.
Additional Notes 
Trained with focus on deduplication to improve creativity and non-repetitiveness. Quantized formats available: FP16, GPTQ_Q4, GPTQ_Q8, GGUF.
Training Details 
Data Sources:
curated creative writing dataset, RP datasets
Methodology:
Diverse set with focus on variety and deduplication
Context Length:
4096
Training Time:
Approximately 2 days
Hardware Used:
2x3090Ti
Input Output 
Input Format:
Gemma Instruct Prompt Format
LLM NameGemma 2 9B ArliAI RPMax V1.1
Repository ๐Ÿค—https://huggingface.co/ArliAI/Gemma-2-9B-ArliAI-RPMax-v1.1 
Model Size9b
Required VRAM18.6 GB
Updated2024-12-22
MaintainerArliAI
Model Typegemma2
Model Files  4.9 GB: 1-of-4   5.0 GB: 2-of-4   5.0 GB: 3-of-4   3.7 GB: 4-of-4
Model ArchitectureGemma2ForCausalLM
Licensegemma
Context Length8192
Model Max Length8192
Transformers Version4.45.0.dev0
Tokenizer ClassGemmaTokenizer
Padding Token<pad>
Vocabulary Size256000
Torch Data Typebfloat16

Best Alternatives to Gemma 2 9B ArliAI RPMax V1.1

Best Alternatives
Context / RAM
Downloads
Likes
Gemma 2 9B It SimPO8K / 18.6 GB16451136
Gemma 2 9B It8K / 18.6 GB340182594
Gemma 2 9B8K / 37.1 GB114489613
...2 9B Cpt Sahabatai V1 Instruct8K / 18.6 GB347627
SILMA 9B Instruct V1.08K / 18.6 GB1104755
MT3 Gen4 Gemma 2 9B8K / 20.4 GB191
MT4 Gen2 Gemma 2 9B8K / 20.4 GB1803
Darkest Muse V18K / 20.4 GB28625
Magnum V4 9B8K / 18.6 GB266314
MT4 Gen4 Gemma 2 9B8K / 20.4 GB240
Note: green Score (e.g. "73.2") means that the model is better than ArliAI/Gemma-2-9B-ArliAI-RPMax-v1.1.

Rank the Gemma 2 9B ArliAI RPMax V1.1 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 40066 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217