CohereForAI Aya 23 8B 3 75bpw EXL2 by Zoyd

 ยป  All LLMs  ยป  Zoyd  ยป  CohereForAI Aya 23 8B 3 75bpw EXL2   URL Share it on

  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

CohereForAI Aya 23 8B 3 75bpw EXL2 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

CohereForAI Aya 23 8B 3 75bpw EXL2 Parameters and Internals

LLM NameCohereForAI Aya 23 8B 3 75bpw EXL2
Repository ๐Ÿค—https://huggingface.co/Zoyd/CohereForAI_aya-23-8B-3_75bpw_exl2 
Model Size8b
Required VRAM6.7 GB
Updated2024-11-21
MaintainerZoyd
Model Typecohere
Model Files  6.7 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
CohereForAI Aya 23 8B 3 75bpw EXL2 (Zoyd/CohereForAI_aya-23-8B-3_75bpw_exl2)

Best Alternatives to CohereForAI Aya 23 8B 3 75bpw EXL2

Best Alternatives
Context / RAM
Downloads
Likes
...4ai Command R 08 2024 Bnb 4bit128K / 19.9 GB817
Aya 23 8B 4bit8K / 4.5 GB132
...ereForAI Aya 23 8B 6 0bpw EXL28K / 9.2 GB52
Aya 23 8B 8bit8K / 8.5 GB141
...ereForAI Aya 23 8B 8 0bpw EXL28K / 10.2 GB51
Aya 23 8B 6.0bpw H6 EXL28K / 8.9 GB51
...ereForAI Aya 23 8B 2 2bpw EXL28K / 5.1 GB60
Aya 23 8B 5.0bpw H6 EXL28K / 7.9 GB41
Aya 23 8B 4.0bpw H6 EXL28K / 6.9 GB80
Aya 23 8B 3.0bpw H6 EXL28K / 5.9 GB60
Note: green Score (e.g. "73.2") means that the model is better than Zoyd/CohereForAI_aya-23-8B-3_75bpw_exl2.

Rank the CohereForAI Aya 23 8B 3 75bpw EXL2 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? 38255 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110