Airoboros 180B 2.2.1 By jondurbin: Benchmarks, Features and Detailed Analysis. Insights on Airoboros 180B 2.2.1.

Autotrain compatible Dataset:jondurbin/airoboros-2.... Endpoints compatible Falcon Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/jondurbin/airoboros-180b-2.2.1

Airoboros 180B 2.2.1 Benchmarks

LLME Score: 0.13593

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Airoboros 180B 2.2.1 (jondurbin/airoboros-180b-2.2.1)

🌟 Advertise your project 🚀

Airoboros 180B 2.2.1 Parameters and Internals

Additional Notes

Designed for instruction following rather than casual chat/roleplay. Heavy use of synthetic data generated by airoboros.

Training Details

Data Sources:

jondurbin/airoboros-2.2.1

Methodology:

Fine-tuned with rope scaling to 4k context

Context Length:

4000

Input Output

Input Format:

A chat. USER: {prompt} ASSISTANT: {response}

Accepted Modalities:

text

Output Format:

text

Performance Tips:

Add stopping criteria/early inference stopping on 'USER:'. For closed-context question answering, use explicit delimiters like BEGININPUT and BEGININSTRUCTION.

LLM Name	Airoboros 180B 2.2.1
Repository 🤗	https://huggingface.co/jondurbin/airoboros-180b-2.2.1
Model Size	180b
Required VRAM	154.2 GB
Updated	2025-08-20
Maintainer	jondurbin
Model Type	falcon
Model Files	2.8 GB: 1-of-107 4.0 GB: 2-of-107 4.0 GB: 3-of-107 2.7 GB: 4-of-107 2.7 GB: 5-of-107 4.0 GB: 6-of-107 4.0 GB: 7-of-107 2.7 GB: 8-of-107 2.7 GB: 9-of-107 4.0 GB: 10-of-107 4.0 GB: 11-of-107 2.7 GB: 12-of-107 2.7 GB: 13-of-107 4.0 GB: 14-of-107 4.0 GB: 15-of-107 2.7 GB: 16-of-107 2.7 GB: 17-of-107 4.0 GB: 18-of-107 4.0 GB: 19-of-107 2.7 GB: 20-of-107 2.7 GB: 21-of-107 4.0 GB: 22-of-107 4.0 GB: 23-of-107 2.7 GB: 24-of-107 2.7 GB: 25-of-107 4.0 GB: 26-of-107 4.0 GB: 27-of-107 2.7 GB: 28-of-107 2.7 GB: 29-of-107 4.0 GB: 30-of-107 4.0 GB: 31-of-107 2.7 GB: 32-of-107 2.7 GB: 33-of-107 4.0 GB: 34-of-107 4.0 GB: 35-of-107 2.7 GB: 36-of-107 2.7 GB: 37-of-107 4.0 GB: 38-of-107 4.0 GB: 39-of-107 2.7 GB: 40-of-107 2.7 GB: 41-of-107 4.0 GB: 42-of-107 4.0 GB: 43-of-107 2.7 GB: 44-of-107 2.7 GB: 45-of-107 4.0 GB: 46-of-107
Model Architecture	FalconForCausalLM
License	other
Context Length	2048
Model Max Length	2048
Transformers Version	4.35.0.dev0
Is Biased	0
Vocabulary Size	65024
Torch Data Type	bfloat16

Quantized Models of the Airoboros 180B 2.2.1

Model	Likes	Downloads	VRAM
Airoboros 180B 2.2.1 AWQ	6	9	96 GB

Best Alternatives to Airoboros 180B 2.2.1

Best Alternatives	Context / RAM	Downloads	Likes
Largefalcon	2K / 411.4 GB	5	0
...buddy Falcon 180B V13 Preview0	2K / 358.1 GB	1761	2
...buddy Falcon 180B V12 Preview0	2K / 358.1 GB	1765	0
...buddy Falcon 180B V13 Preview2	2K / 358.1 GB	7	1
...buddy Falcon 180B V13 Preview1	2K / 358.1 GB	10	4
...alcon 180B Omniquant W3a16g512	2K / 69.4 GB	5	3
Falcon 180B	0K / 193.8 GB	2535	1147
Falcon 180B WizardLM Orca	0K / 358 GB	1736	1
... 180B Wizard Alpaca Dolly Orca	0K / 358 GB	1739	4
Falcon 180B Chat Instruct	0K / 358 GB	1736	2

Note: green Score (e.g. "73.2") means that the model is better than jondurbin/airoboros-180b-2.2.1.

Rank the Airoboros 180B 2.2.1 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? 50767 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