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

Airoboros L2 13B 2 1 YaRN 64K GGUF by TheBloke

 »  All LLMs  »  TheBloke  »  Airoboros L2 13B 2 1 YaRN 64K GGUF   URL Share it on

  129   
Base model:bhenrym14/airoboros... Base model:quantized:bhenrym14... Dataset:jondurbin/airoboros-2....   Gguf   Llama   Quantized   Region:us   Yarn
Model Card on HF 🤗: https://huggingface.co/TheBloke/Airoboros-L2-13B-2_1-YaRN-64K-GGUF 

Airoboros L2 13B 2 1 YaRN 64K GGUF Benchmarks

LLME Score: 0.13966
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Airoboros L2 13B 2 1 YaRN 64K GGUF (TheBloke/Airoboros-L2-13B-2_1-YaRN-64K-GGUF)

Airoboros L2 13B 2 1 YaRN 64K GGUF Parameters and Internals

Model Type 
llama
Use Cases 
Considerations:
Significant VRAM is required for full context capabilities.
Additional Notes 
This model employs Yet another RoPE extensioN method (YaRN) for extended context length capabilities. There's ongoing community evaluation on U shaped attention handling in long context windows.
Training Details 
Data Sources:
https://huggingface.co/datasets/jondurbin/airoboros-2.1
Methodology:
Finetune of Llama-2-13b with airoboros-2.1 (fp16), using YaRN scaling for RoPE to extend context length to 64k tokens
Context Length:
65586
Training Time:
~16 hours
Hardware Used:
1x RTX 6000 Ada
Model Architecture:
Llama-2-13b with additional pretraining using YaRN scaling for 64k tokens
Input Output 
Input Format:
A chat. USER: {prompt} ASSISTANT:
Performance Tips:
Alter model directory name if issues occur on Windows due to decimals in version number.
LLM NameAiroboros L2 13B 2 1 YaRN 64K GGUF
Repository 🤗https://huggingface.co/TheBloke/Airoboros-L2-13B-2_1-YaRN-64K-GGUF 
Model NameAiroboros L2 13B 2.1 YaRN 64K
Model Creatorbhenrym14
Base Model(s)  bhenrym14/airoboros-l2-13b-2.1-YaRN-64k   bhenrym14/airoboros-l2-13b-2.1-YaRN-64k
Model Size13b
Required VRAM5.4 GB
Updated2024-12-21
MaintainerTheBloke
Model Typellama
Model Files  5.4 GB   6.9 GB   6.3 GB   5.7 GB   7.4 GB   7.9 GB   7.4 GB   9.0 GB   9.2 GB   9.0 GB   10.7 GB   13.8 GB
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureAutoModel
Licensellama2

Best Alternatives to Airoboros L2 13B 2 1 YaRN 64K GGUF

Best Alternatives
Context / RAM
Downloads
Likes
Noromaid 13B V0.3 GGUF0K / 5.4 GB2075211
EstopianMaid 13B GGUF0K / 4.8 GB235345
Llama 2 13B Chat GGUF0K / 5.4 GB16403192
Llama 3 13B Instruct V0.1 GGUF0K / 5.1 GB5105
...aMa 3 Instruct Zeroed 13B GGUF0K / 5 GB271
LLaMa 3 Base Zeroed 13B GGUF0K / 5 GB181
Llama3 13B Ku GGUF0K / 8.7 GB210
Hermes 2 Pro Llama 3 13B GGUF0K / 4.6 GB110
WhiteRabbitNeo 13B GGUF0K / 5.4 GB344848
Model10K / 13.8 GB60
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Airoboros-L2-13B-2_1-YaRN-64K-GGUF.

Rank the Airoboros L2 13B 2 1 YaRN 64K GGUF 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? 40013 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