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

Airoboros 65B Gpt4 1.2 GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Airoboros 65B Gpt4 1.2 GPTQ   URL Share it on

  5   
  4-bit   Autotrain compatible Dataset:jondurbin/airoboros-gp...   Gptq   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/airoboros-65B-gpt4-1.2-GPTQ 

Airoboros 65B Gpt4 1.2 GPTQ Benchmarks

ARC: 65.53 vs 96.7 (so35)-32.2%
HellaSwag: 85.77 vs 95.3 (gpt4)-10%
MMLU: 61.95 vs 88.3 (so35)-29.8%
TruthfulQA: 52.43 vs 59 (gpt4)-11.1%
WinoGrande: 79.79 vs 87.5 (gpt4)-8.8%
GSM8K: 18.04 vs 96.4 (so35)-81.3%
LLME Score: 0.1109
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 1.2 GPTQ (TheBloke/airoboros-65B-gpt4-1.2-GPTQ)
🌟 Advertise your project 🚀

Airoboros 65B Gpt4 1.2 GPTQ Parameters and Internals

Model Type 
text generation
Additional Notes 
This model uses a prompt template which involves a special preamble followed by user input and assistant response indicators. It contains updates such as ELI5 reasoning/math prompts and coding examples in multiple languages.
Training Details 
Data Sources:
jondurbin/airoboros-gpt4-1.2
Methodology:
Fine-tuned using qlora with synthetic training data created by GPT-4.
Input Output 
Input Format:
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. USER: prompt ASSISTANT:
LLM NameAiroboros 65B Gpt4 1.2 GPTQ
Repository 🤗https://huggingface.co/TheBloke/airoboros-65B-gpt4-1.2-GPTQ 
Base Model(s)  jondurbin/airoboros-65b-gpt4-1.2   jondurbin/airoboros-65b-gpt4-1.2
Model Size65b
Required VRAM33.5 GB
Updated2025-09-13
MaintainerTheBloke
Model Typellama
Model Files  33.5 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licenseother
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 1.2 GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...en Instruct Human Mix 65B GPTQ2K / 33.5 GB110
Guanaco 65B GPTQ2K / 33.5 GB1731263
Airoboros 65B Gpt4 1.4 GPTQ2K / 33.5 GB413
Airoboros 65B Gpt4 1.3 GPTQ2K / 33.5 GB43
Dromedary 65B Lora GPTQ2K / 33.5 GB46
Gpt4 Alpaca Lora Mlp 65B GPTQ2K / 33.5 GB414
Airoboros 65B GPT4 2.0 GPTQ2K / 33.5 GB63
Airoboros 65B GPT4 M2.0 GPTQ2K / 33.5 GB82
...stage Llama1 65B Instruct GPTQ2K / 34.7 GB53
...Research Oasst1 Llama 65B GPTQ2K / 33.5 GB75
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/airoboros-65B-gpt4-1.2-GPTQ.

Rank the Airoboros 65B Gpt4 1.2 GPTQ 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? 51352 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 v20241124
  Support LLM Explorer