
Guides an agent through fine-tuning GR00T or openpi robot policies on LeRobot data
- Open source
- 4K GitHub stars
- AI models and LLM tooling


Guides an agent through fine-tuning GR00T or openpi robot policies on LeRobot data

Runs the full Isaac for Healthcare workflow pipeline from recording to checkpoint check

Grades or filters workflow HDF5 episodes by visual success using a vision model

Guides an agent through post-training LLMs with TRL: SFT, DPO, GRPO, KTO and reward models

Guides fine-tuning of NVIDIA Cosmos3 reasoning models with Cosmos Framework or Cosmos-RL

Fine-tune LLMs with TRL or Unsloth on Hugging Face Jobs GPUs and convert to GGUF

Guides an agent through building LLM eval pipelines with datasets, evaluators and pixie

Guides an agent through drafting, testing and tuning new agent skills with measured evals

Plans and configures chained Nemotron customization steps like SFT, RL, and evaluation

Runs iterative NeMo-RL experiments with git branches and TSV logs as a research ledger

Trains, evaluates and exports TAO Sparse4D multi-camera 3D detection and tracking models

Guides an agent through fine-tuning models on Microsoft Foundry with SFT, DPO or RFT
The closest alternatives to I4h workflow train rl are I4h workflow finetune, I4h workflow E2E, I4h workflow dataset annotate, Trl training and Tao finetune cosmos reason.
Yes. I4h workflow finetune, I4h workflow E2E, I4h workflow dataset annotate have a free or open-source option.