LLM EXPLORER 66,613 MODELS INDEXED

Airoboros 65B GPT4 M2.0 GPTQ by TheBloke

By TheBloke · 3 downloads
HF Repo ↗ Copy URL

Airoboros 65B GPT4 M2.0 GPTQ is an open-source language model by TheBloke. Features: 65b LLM, VRAM: 33.5GB, Context: 2K, License: other, Quantized, LLM Explorer Score: 0.08.

  4-bit Base model:jondurbin/airoboros... Base model:quantized:jondurbin... Dataset:jondurbin/airoboros-gp...   Gptq   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/Airoboros-65B-GPT4-m2.0-GPTQ 

Airoboros 65B GPT4 M2.0 GPTQ Parameters and Internals

Model Type 
llama, text generation
Use Cases 
Areas:
research, academic use
Limitations:
No commercial use allowed, Uncertain legal stance regarding OpenAI API data use
Additional Notes 
Quanitization conducted with AutoGPTQ for optimized VRAM and performance balance. Exploration of GPTQ parameters offered to adapt to various hardware setups.
Training Details 
Data Sources:
airoboros-gpt4-2.0, airoboros-gpt4-m2.0
Methodology:
Instruction fine-tuning using synthetic instructions generated by airoboros with GPT-4, integrating data from March and June GPT-4 versions. Fine-tuned using QLoRA approach.
Context Length:
2048
Model Architecture:
LLaMA-based
Input Output 
Input Format:
Prompt follows: A chat between a user and an assistant. USER: [prompt] ASSISTANT:
Accepted Modalities:
text
Output Format:
Detailed, comprehensive responses
Performance Tips:
Use proper formatting for closed-context queries to enhance response quality.
LLM NameAiroboros 65B GPT4 M2.0 GPTQ
Repository 🤗https://huggingface.co/TheBloke/Airoboros-65B-GPT4-m2.0-GPTQ 
Model NameAiroboros 65B GPT4 m2.0
Model CreatorJon Durbin
Base Model(s)  jondurbin/airoboros-65b-gpt4-m2.0   jondurbin/airoboros-65b-gpt4-m2.0
Model Size65b
Required VRAM33.5 GB
Updated2026-07-10
MaintainerTheBloke
Model Typellama
Model Files  33.5 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length2048
Model Max Length2048
Transformers Version4.31.0
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 M2.0 GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...en Instruct Human Mix 65B GPTQ2K / 33.5 GB110
Airoboros 65B Gpt4 1.4 GPTQ2K / 33.5 GB1213
Airoboros 65B Gpt4 1.3 GPTQ2K / 33.5 GB53
Airoboros 65B Gpt4 1.2 GPTQ2K / 33.5 GB4111
Dromedary 65B Lora GPTQ2K / 33.5 GB66
Gpt4 Alpaca Lora Mlp 65B GPTQ2K / 33.5 GB4914
Guanaco 65B GPTQ2K / 33.5 GB481262
Airoboros 65B GPT4 2.0 GPTQ2K / 33.5 GB83
...stage Llama1 65B Instruct GPTQ2K / 34.7 GB93
...Research Oasst1 Llama 65B GPTQ2K / 33.5 GB115
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Airoboros-65B-GPT4-m2.0-GPTQ.