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

Airoboros 65B Gpt4 1.3 by jondurbin

 »  All LLMs  »  jondurbin  »  Airoboros 65B Gpt4 1.3   URL Share it on

  885   

Airoboros 65B Gpt4 1.3 is an open-source language model by jondurbin. Features: 65b LLM, VRAM: 130.4GB, Context: 2K, License: cc-by-nc-4.0, HF Score: 60.2, LLM Explorer Score: 0.11, Arc: 66.1, HellaSwag: 86, MMLU: 63.9, TruthfulQA: 51.3, WinoGrande: 80, GSM8K: 13.7.

Dataset:jondurbin/airoboros-gp...   Endpoints compatible   Llama   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/jondurbin/airoboros-65b-gpt4-1.3 

Airoboros 65B Gpt4 1.3 Benchmarks

ARC: 66.13 vs 96.7 (so35)-31.6%
HellaSwag: 85.99 vs 95.3 (gpt4)-9.8%
MMLU: 63.89 vs 88.3 (so35)-27.6%
TruthfulQA: 51.32 vs 59 (gpt4)-13%
WinoGrande: 79.95 vs 87.5 (gpt4)-8.6%
GSM8K: 13.65 vs 96.4 (so35)-85.8%
LLME Score: 0.10821
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Airoboros 65B Gpt4 1.3 (jondurbin/airoboros-65b-gpt4-1.3)
🌟 Advertise your project 🚀

Airoboros 65B Gpt4 1.3 Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
Research
Limitations:
Cannot be used commercially
Additional Notes 
This version 1.3 of the model has issues and a new release, version 1.4, is anticipated.
Training Details 
Data Sources:
Synthetic data created with OpenAI GPT-4 via Airoboros.
Methodology:
Fine-tuned with a fork of qlora, using a slightly modified vicuna template. Utilized a special training method involving synthetic generation and QLoRA fine-tuning.
Context Length:
2800
Model Architecture:
A 65 billion parameter version of LlaMa using QLoRA for efficient fine-tuning.
Input Output 
Input Format:
A chat format with 'USER: ' followed by input and 'ASSISTANT: ' for responses.
Accepted Modalities:
text
Output Format:
Responses in text format.
LLM NameAiroboros 65B Gpt4 1.3
Repository 🤗https://huggingface.co/jondurbin/airoboros-65b-gpt4-1.3 
Model Size65b
Required VRAM130.4 GB
Updated2026-03-29
Maintainerjondurbin
Model Typellama
Model Files  9.9 GB: 1-of-14   9.7 GB: 2-of-14   9.7 GB: 3-of-14   9.7 GB: 4-of-14   9.7 GB: 5-of-14   9.7 GB: 6-of-14   9.7 GB: 7-of-14   9.7 GB: 8-of-14   9.7 GB: 9-of-14   9.7 GB: 10-of-14   9.7 GB: 11-of-14   9.7 GB: 12-of-14   9.7 GB: 13-of-14   4.1 GB: 14-of-14
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-4.0
Context Length2048
Model Max Length2048
Transformers Version4.31.0.dev0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Airoboros 65B Gpt4 1.3

Best Alternatives
Context / RAM
Downloads
Likes
Lite Oute 1 65M Instruct2K / 0.3 GB1712
Lite Oute 1 65M2K / 0.3 GB1311
StableBeluga1 Delta2K / 130.4 GB84756
Airoboros 65B Gpt4 2.02K / 130.4 GB18060
Airoboros 65B Gpt4 M2.02K / 130.4 GB10960
Openbuddy Llama 65B V8 Bf162K / 130.6 GB8409
UltraLM 65B2K / 130.4 GB10269
Llama 65B Instruct2K / 130.4 GB102214
Airoboros 65B Gpt4 1.22K / 130.4 GB138422
Airoboros 65B Gpt4 1.42K / 130.4 GB79317
Note: green Score (e.g. "73.2") means that the model is better than jondurbin/airoboros-65b-gpt4-1.3.

Rank the Airoboros 65B Gpt4 1.3 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? 52721 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer