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

Airoboros 70B 3.3 by jondurbin

 »  All LLMs  »  jondurbin  »  Airoboros 70B 3.3   URL Share it on

  2551   
  Autotrain compatible Base model:finetune:meta-llama... Base model:meta-llama/meta-lla...   Conversational Dataset:bluemoon-fandom-1-1-rp...   Dataset:boolq Dataset:glaiveai/glaive-functi... Dataset:grimulkan/limarp-augme... Dataset:jondurbin/airoboros-3.... Dataset:jondurbin/cinematika-v... Dataset:jondurbin/gutenberg-dp...   Dataset:ldjnr/capybara Dataset:mattpscott/airoboros-s...   Dataset:piqa Dataset:unalignment/toxic-dpo-... Dataset:vezora/tested-22k-pyth...   Endpoints compatible   Llama   Llama-3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/jondurbin/airoboros-70b-3.3 

Airoboros 70B 3.3 Benchmarks

ARC: 71.67 vs 96.7 (so35)-25.9%
HellaSwag: 85.27 vs 95.3 (gpt4)-10.5%
MMLU: 79.31 vs 88.3 (so35)-10.2%
TruthfulQA: 59.68 vs 59 (gpt4)1.2%
WinoGrande: 84.37 vs 87.5 (gpt4)-3.6%
GSM8K: 73.84 vs 96.4 (so35)-23.4%
LLME Score: 0.24039
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Airoboros 70B 3.3 (jondurbin/airoboros-70b-3.3)

Airoboros 70B 3.3 Parameters and Internals

LLM NameAiroboros 70B 3.3
Repository 🤗https://huggingface.co/jondurbin/airoboros-70b-3.3 
Base Model(s)  Meta Llama 3 8B   meta-llama/Meta-Llama-3-8B
Model Size8b
Required VRAM141.2 GB
Updated2024-12-26
Maintainerjondurbin
Model Typellama
Model Files  4.0 GB: 1-of-37   3.6 GB: 2-of-37   3.9 GB: 3-of-37   3.9 GB: 4-of-37   3.9 GB: 5-of-37   3.7 GB: 6-of-37   3.9 GB: 7-of-37   3.9 GB: 8-of-37   3.9 GB: 9-of-37   3.7 GB: 10-of-37   3.9 GB: 11-of-37   3.9 GB: 12-of-37   3.9 GB: 13-of-37   3.7 GB: 14-of-37   3.9 GB: 15-of-37   3.9 GB: 16-of-37   3.9 GB: 17-of-37   3.7 GB: 18-of-37   3.9 GB: 19-of-37   3.9 GB: 20-of-37   3.9 GB: 21-of-37   3.7 GB: 22-of-37   3.9 GB: 23-of-37   3.9 GB: 24-of-37   3.9 GB: 25-of-37   3.7 GB: 26-of-37   3.9 GB: 27-of-37   3.9 GB: 28-of-37   3.9 GB: 29-of-37   3.7 GB: 30-of-37   3.9 GB: 31-of-37   3.9 GB: 32-of-37   3.9 GB: 33-of-37   3.7 GB: 34-of-37   3.9 GB: 35-of-37   3.9 GB: 36-of-37   2.6 GB: 37-of-37
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length8192
Model Max Length8192
Transformers Version4.40.1
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size128256
Torch Data Typebfloat16

Best Alternatives to Airoboros 70B 3.3

Best Alternatives
Context / RAM
Downloads
Likes
...a 3 8B Instruct Gradient 1048K1024K / 16.1 GB4387678
Thor V1.4 8B DARK FICTION1024K / 16.1 GB9412
MrRoboto ProLong 8B V2b1024K / 16.1 GB1780
MrRoboto ProLong 8B V1n1024K / 16.1 GB1770
MrRoboto ProLong 8B V4i1024K / 16.1 GB571
4834155661024K / 16.1 GB680
MrRoboto ProLong 8B V4h1024K / 16.1 GB960
HEL V0.8 8B LONG DARK1024K / 16.1 GB2300
MrRoboto ProLong 8B V4b1024K / 16.1 GB1070
MrRoboto ProLong 8B V4c1024K / 16.1 GB860
Note: green Score (e.g. "73.2") means that the model is better than jondurbin/airoboros-70b-3.3.

Rank the Airoboros 70B 3.3 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? 40248 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