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

Aya 23 8B 3.0bpw H6 EXL2 by LoneStriker

 »  All LLMs  »  LoneStriker  »  Aya 23 8B 3.0bpw H6 EXL2   URL Share it on

  5   
  3-bit   Ar   Autotrain compatible   Cohere   Conversational   Cs   De   El   En   Endpoints compatible   Es   Exl2   Fa   Fr   He   Hi   Id   It   Ja   Ko   Nl   Pl   Pt   Quantized   Region:us   Ro   Ru   Safetensors   Tr   Uk   Vi   Zh
Model Card on HF 🤗: https://huggingface.co/LoneStriker/aya-23-8B-3.0bpw-h6-exl2 

Aya 23 8B 3.0bpw H6 EXL2 Benchmarks

LLME Score: 0.19864
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Aya 23 8B 3.0bpw H6 EXL2 (LoneStriker/aya-23-8B-3.0bpw-h6-exl2)

Aya 23 8B 3.0bpw H6 EXL2 Parameters and Internals

Model Type 
text generation
Additional Notes 
Aya 23 is a multilingual model with high proficiency across 23 languages.
Supported Languages 
Arabic (high), Chinese (simplified & traditional) (high), Czech (high), Dutch (high), English (high), French (high), German (high), Greek (high), Hebrew (high), Hindi (high), Indonesian (high), Italian (high), Japanese (high), Korean (high), Persian (high), Polish (high), Portuguese (high), Romanian (high), Russian (high), Spanish (high), Turkish (high), Ukrainian (high), Vietnamese (high)
Training Details 
Methodology:
Optimized transformer architecture. Fine-tuned to follow human instructions.
Context Length:
8192
Model Architecture:
Auto-regressive language model with optimized transformer architecture.
Input Output 
Input Format:
Text
Accepted Modalities:
text
Output Format:
Text
LLM NameAya 23 8B 3.0bpw H6 EXL2
Repository 🤗https://huggingface.co/LoneStriker/aya-23-8B-3.0bpw-h6-exl2 
Model Size8b
Required VRAM5.9 GB
Updated2024-12-21
MaintainerLoneStriker
Model Typecohere
Model Files  5.9 GB
Supported Languagesen fr de es it pt ja ko zh ar el fa pl id cs he hi nl ro ru tr uk vi
Quantization Typeexl2
Model ArchitectureCohereForCausalLM
Licensecc-by-nc-4.0
Context Length8192
Model Max Length8192
Transformers Version4.40.0.dev0
Tokenizer ClassCohereTokenizer
Padding Token<PAD>
Vocabulary Size256000
Torch Data Typefloat16

Best Alternatives to Aya 23 8B 3.0bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
Aya 23 8B 4bit8K / 4.5 GB202
...ereForAI Aya 23 8B 6 0bpw EXL28K / 9.2 GB142
Aya 23 8B 8bit8K / 8.5 GB151
...ereForAI Aya 23 8B 8 0bpw EXL28K / 10.2 GB61
...reForAI Aya 23 8B 3 75bpw EXL28K / 6.7 GB100
Aya 23 8B 4.0bpw H6 EXL28K / 6.9 GB110
...ereForAI Aya 23 8B 2 2bpw EXL28K / 5.1 GB80
Aya 23 8B 6.0bpw H6 EXL28K / 8.9 GB61
Aya 23 8B 5.0bpw H6 EXL28K / 7.9 GB51
Aya Expanse 8B8K / 16 GB37388307
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/aya-23-8B-3.0bpw-h6-exl2.

Rank the Aya 23 8B 3.0bpw H6 EXL2 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? 40066 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