Skills with output "Trained model checkpoints"

pyhealth - Develop healthcare AI with PyHealth

healthcare AI clinical machine learning electronic health records medical coding

★ 399 · Updated 2026-10-03

Develop, train, evaluate, and deploy healthcare machine learning models using clinical data, medical codes, physiological signals, and healthcare datasets.

⚙ Load healthcare datasets ⚙ Define prediction tasks ⚙ Select healthcare models

fine-tuning-serving-openpi - Fine-Tune and Serve OpenPI Robot Policies

OpenPI Physical Intelligence VLA Robotics

★ 85 · Updated 2026-09-28

Fine-tunes and serves Physical Intelligence OpenPI models with JAX or PyTorch for robot policy inference in ALOHA, DROID, and LIBERO environments.

⚙ Fine-tune OpenPI models ⚙ Serve policy inference ⚙ Convert JAX checkpoints

tao-train-image-classification - Train and deploy TAO PyTorch image classifiers

image classification PyTorch TAO

★ 3,463 · Updated 2026-09-28

Train, evaluate, distill, quantize, export, and run inference for PyTorch-based TAO image-classification models.

⚙ Train image classifiers ⚙ Evaluate model performance ⚙ Distill classification models

simpo - Simple Preference Optimization

Post-Training SimPO Preference Optimization Alignment

★ 9 · Updated 2026-09-16

Executes reference-free preference optimization for language model post-training without requiring a reference model.

⚙ Train base models with SimPO ⚙ Fine-tune instruct models ⚙ Optimize reasoning intensive tasks

verl-rl-training - verl: LLM RL Training Framework

Reinforcement Learning RLHF GRPO PPO

★ 1 · Updated 2026-06-30

Flexible RL training library for large language models

⚙ train models ⚙ run rollout ⚙ compute reward