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

GPT NeoX 20B Erebus by KoboldAI

 »  All LLMs  »  KoboldAI  »  GPT NeoX 20B Erebus   URL Share it on

  4160   
  Arxiv:2204.06745   Autotrain compatible   En   Gpt neox   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/KoboldAI/GPT-NeoX-20B-Erebus 

GPT NeoX 20B Erebus Benchmarks

ARC: 45.48 vs 96.7 (so35)-53%
HellaSwag: 72.79 vs 95.3 (gpt4)-23.6%
MMLU: 26.77 vs 88.3 (so35)-69.7%
TruthfulQA: 32.15 vs 59 (gpt4)-45.5%
WinoGrande: 68.11 vs 87.5 (gpt4)-22.2%
GSM8K: 2.27 vs 96.4 (so35)-97.6%
LLME Score: 0.10658
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
GPT NeoX 20B Erebus (KoboldAI/GPT-NeoX-20B-Erebus)

GPT NeoX 20B Erebus Parameters and Internals

Model Type 
autoregressive, language model
Use Cases 
Limitations:
Strong NSFW bias
Additional Notes 
Warning: THIS model is NOT suitable for use by minors. The model will output X-rated content.
Training Details 
Data Sources:
Literotica, Sexstories, Dataset-G, Doc's Lab, Pike Dataset, SoFurry
Methodology:
Heavily modified version of Ben Wang's Mesh Transformer JAX library
Hardware Used:
TPUv3-256 TPU pod
Responsible Ai Considerations 
Mitigation Strategies:
Warning: This model has a very strong NSFW bias!
LLM NameGPT NeoX 20B Erebus
Repository 🤗https://huggingface.co/KoboldAI/GPT-NeoX-20B-Erebus 
Model Size20b
Required VRAM41.4 GB
Updated2025-03-13
MaintainerKoboldAI
Model Typegpt_neox
Model Files  2.0 GB: 1-of-23   2.0 GB: 2-of-23   1.9 GB: 3-of-23   1.8 GB: 4-of-23   1.9 GB: 5-of-23   1.8 GB: 6-of-23   1.8 GB: 7-of-23   1.9 GB: 8-of-23   2.0 GB: 9-of-23   1.8 GB: 10-of-23   1.9 GB: 11-of-23   2.0 GB: 12-of-23   1.8 GB: 13-of-23   1.8 GB: 14-of-23   2.0 GB: 15-of-23   1.9 GB: 16-of-23   2.0 GB: 17-of-23   1.4 GB: 18-of-23   1.8 GB: 19-of-23   1.8 GB: 20-of-23   2.0 GB: 21-of-23   1.8 GB: 22-of-23   0.3 GB: 23-of-23
Supported Languagesen
Model ArchitectureGPTNeoXForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.19.0.dev0
Tokenizer ClassGPTNeoXTokenizer
Vocabulary Size50432
Torch Data Typefloat16

Best Alternatives to GPT NeoX 20B Erebus

Best Alternatives
Context / RAM
Downloads
Likes
GPT NeoXT Chat Base 20B2K / 41.2 GB5401696
EleutherAI GPT Neox 20B 4bits2K / 12.5 GB80
...t Gm Oasst1 Multilang 1024 20B2K / 41.2 GB199110
H2ogpt Gm Oasst1 En 1024 20B2K / 41.2 GB19974
H2ogpt Oasst1 512 20B2K / 41.2 GB204340
GPT Neox 20B Full Precision2K / 82.5 GB19580
Oasst GPT Neox 20B 1000 Steps2K / 41.2 GB19490
Oasst GPT Neox 20B 3000 Steps2K / 41.2 GB19540
GPTNeoX 20B TestGen Dart V1.02K / 41.2 GB112
GPT Neox 20B2K / 40.8 GB21896555
Note: green Score (e.g. "73.2") means that the model is better than KoboldAI/GPT-NeoX-20B-Erebus.

Rank the GPT NeoX 20B Erebus 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? 44950 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 v20241227
  Support LLM Explorer