Hugging Face's logo
Dokyoon's picture
105 306

Dokyoon

leeloolee
kaki-paper's profile picture GigaBoy's profile picture victor's profile picture
Ā·

AI & ML interests

ai

Recent Activity

upvoted an article 2 days ago
Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective
reacted to Parveshiiii's post with šŸ”„ 5 days ago
šŸš€ Wanna train your own AI Model or Tokenizer from scratch? Building models isnā€™t just for big labs anymore ā€” with the right data, compute, and workflow, you can create **custom AI models** and **tokenizers** tailored to any domain. Whether itā€™s NLP, domainā€‘specific datasets, or experimental architectures, training from scratch gives you full control over vocabulary, embeddings, and performance. āœØ Why train your own? - Full control over vocabulary & tokenization - Domainā€‘specific optimization (medical, legal, technical, etc.) - Better performance on niche datasets - Freedom to experiment with architectures āš” The best part? - Tokenizer training (TikToken / BPE) can be done in **just 3 lines of code**. - Model training runs smoothly on **Google Colab notebooks** ā€” no expensive hardware required. šŸ“‚ Try out my work: - šŸ”— https://github.com/OE-Void/Tokenizer-from_scratch - šŸ”— https://github.com/OE-Void/GPT
upvoted a paper 5 days ago
VISTA-PATH: An interactive foundation model for pathology image segmentation and quantitative analysis in computational pathology
View all activity

Organizations

MultišŸ¤–Transformers's profile picture ģøģŠ¤ķŠøėŸ­ķŠø.ķ•œźµ­'s profile picture Pi3AI's profile picture nanochat students's profile picture