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 AWQ GEMM by alijawad07

 »  All LLMs  »  alijawad07  »  Aya 23 8B AWQ GEMM   URL Share it on

  107   
  4-bit   Autotrain compatible   Awq   Cohere   Conversational   Endpoints compatible   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/alijawad07/aya-23-8B-AWQ-GEMM 

Aya 23 8B AWQ GEMM Benchmarks

LLME Score: 0.19297
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 AWQ GEMM (alijawad07/aya-23-8B-AWQ-GEMM)

Aya 23 8B AWQ GEMM Parameters and Internals

Model Type 
auto-regressive language model
Additional Notes 
This is an AWQ quantized version of the Aya-23-8B model using AutoAWQ. AWQ offers efficient, accurate, and fast low-bit weight quantization.
Supported Languages 
Arabic (optimized), Chinese (simplified & traditional) (optimized), Czech (optimized), Dutch (optimized), English (optimized), French (optimized), German (optimized), Greek (optimized), Hebrew (optimized), Hindi (optimized), Indonesian (optimized), Italian (optimized), Japanese (optimized), Korean (optimized), Persian (optimized), Polish (optimized), Portuguese (optimized), Romanian (optimized), Russian (optimized), Spanish (optimized), Turkish (optimized), Ukrainian (optimized), Vietnamese (optimized)
Training Details 
Data Sources:
Aya Collection
Methodology:
Instruction fine-tuned
Context Length:
8192
Model Architecture:
Optimized transformer architecture
Input Output 
Input Format:
text only
Accepted Modalities:
text
Output Format:
text only
Performance Tips:
Install transformers from the source repository including necessary changes for AWQ quantized models
LLM NameAya 23 8B AWQ GEMM
Repository 🤗https://huggingface.co/alijawad07/aya-23-8B-AWQ-GEMM 
Model Size8b
Required VRAM7.8 GB
Updated2025-02-22
Maintaineralijawad07
Model Typecohere
Model Files  7.1 GB: 1-of-2   0.7 GB: 2-of-2
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureCohereForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.41.0
Tokenizer ClassCohereTokenizer
Padding Token<PAD>
Vocabulary Size256000
Torch Data Typefloat16

Best Alternatives to Aya 23 8B AWQ GEMM

Best Alternatives
Context / RAM
Downloads
Likes
Aya 23 8B 4bit8K / 4.5 GB322
Aya 23 8B 8bit8K / 8.5 GB231
...ereForAI Aya 23 8B 6 0bpw EXL28K / 9.2 GB92
...ereForAI Aya 23 8B 8 0bpw EXL28K / 10.2 GB51
...ereForAI Aya 23 8B 2 2bpw EXL28K / 5.1 GB50
...reForAI Aya 23 8B 3 75bpw EXL28K / 6.7 GB50
Aya 23 8B 5.0bpw H6 EXL28K / 7.9 GB61
Aya 23 8B 6.0bpw H6 EXL28K / 8.9 GB61
Aya 23 8B 3.0bpw H6 EXL28K / 5.9 GB80
Aya 23 8B 4.0bpw H6 EXL28K / 6.9 GB70

Rank the Aya 23 8B AWQ GEMM 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? 43470 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