1,000 Stars 🎉
-
Eindhoven / Trondheim
- Freelance
-
23:20
(UTC +02:00) - https://hf.co/ssmits
- @StijnSmits
- in/sjssmits
Pinned Loading
-
docs-to-eval
docs-to-eval Publicdocs-to-eval builds tailor-made evaluation sets from raw documentation and scores model outputs with the right verification strategy. It combines lightweight FastAPI services, reusable Python compo…
-
grpo-optuna
grpo-optuna PublicOptimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna
-
modernbert-finetune
modernbert-finetune PublicFine-tune ModernBERT on a large Dataset with Custom Tokenizer Training
-
agentic-cursorrules
agentic-cursorrules PublicA practical approach to managing multiple AI agents in Cursor through strict file-tree partitioning and domain boundaries.
-
EasyDeL-GSPO
EasyDeL-GSPO PublicForked from erfanzar/EasyDeL
Accelerate your training with this open-source library. Optimize performance with streamlined training and serving options with JAX. 🚀
Python 4
-
automatic-learning-amplifier
automatic-learning-amplifier PublicMLX-based QA pair generator and LLM finetuning tool in Streamlit
If the problem persists, check the GitHub status page or contact support.