GPT Neo 125M Dutch by yhavinga

 ยป  All LLMs  ยป  yhavinga  ยป  GPT Neo 125M Dutch   URL Share it on

  Autotrain compatible Dataset:yhavinga/mc4 nl cleane...   Endpoints compatible   Gpt2   Gpt2-medium   Gpt neo   Jax   Nl   Pytorch   Region:us   Safetensors   Tensorboard

GPT Neo 125M Dutch Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
GPT Neo 125M Dutch (yhavinga/gpt-neo-125M-dutch)
๐ŸŒŸ Advertise your project ๐Ÿš€

GPT Neo 125M Dutch Parameters and Internals

Model Type 
text generation
Additional Notes 
This project was facilitated by compute from Google's TPU Research Cloud and utilized the HuggingFace Transformers ecosystem.
Supported Languages 
Dutch (proficient)
Training Details 
Data Sources:
cleaned Dutch mC4
Data Volume:
33 billion tokens
Methodology:
Trained from scratch on Dutch, using a BPE tokenizer
Context Length:
512
Training Time:
1 day 12 hours
Hardware Used:
TPU Research Cloud provided by Google
Model Architecture:
GPT-Neo
LLM NameGPT Neo 125M Dutch
Repository ๐Ÿค—https://huggingface.co/yhavinga/gpt-neo-125M-dutch 
Model Size125m
Required VRAM0.6 GB
Updated2025-09-21
Maintaineryhavinga
Model Typegpt_neo
Model Files  0.6 GB   0.6 GB
Supported Languagesnl
Model ArchitectureGPTNeoForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.13.0
Tokenizer ClassGPT2Tokenizer
Vocabulary Size50257
Torch Data Typefloat32
Activation Functiongelu_new

Best Alternatives to GPT Neo 125M Dutch

Best Alternatives
Context / RAM
Downloads
Likes
GPT Neo 125M Stf Imdb2K / 0.5 GB50
Abhinav Chatbot2K / 0.5 GB50
GPT Neo 125M Xsum Roya2K / 0.5 GB300
GPT Neo 125M Sft2K / 0 GB50
Aitextgen2K / 0.5 GB50
Neox 125m Storytelling2K / 0.5 GB60
Epfl Cs 522 Istari Mcqa2K / 0.5 GB50
NewsGen2K / 0.5 GB60
GPT Neo 125M Lama2K / 0.5 GB50
GPT Neo Plantuml2K / 0.5 GB51
Note: green Score (e.g. "73.2") means that the model is better than yhavinga/gpt-neo-125M-dutch.

Rank the GPT Neo 125M Dutch Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 51507 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124