
Fine-tune LLMs with TRL or Unsloth on Hugging Face Jobs GPUs and convert to GGUF
- Open source
- 11.4K GitHub stars
- AI models and LLM tooling


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

Guides an agent through training sentence-transformers embedding, reranker and sparse

Trains, distills, quantizes and runs RT-DETR real-time object detection models

Guides an agent through fine-tuning models on Microsoft Foundry with SFT, DPO or RFT

Fine-tunes and runs NVIDIA CLIP models for image-text retrieval and zero-shot

Trains, evaluates, exports and runs NVIDIA TAO Deformable DETR object detectors

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

Runs an iterative retrain-and-evaluate loop to improve NVIDIA TAO CLIP image-text

Guides training, evaluating and exporting reinforcement-learning robot policies for Isaac

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

Continues self-supervised DINOv3 pre-training on unlabeled images to adapt vision

Lets an agent log, alert on and query ML training experiment metrics with Trackio
The closest alternatives to Trl training are Huggingface LLM trainer, Train sentence transformers, Tao train rtdetr, Finetuning and Tao finetune clip.
Yes. Huggingface LLM trainer, Train sentence transformers, Tao train rtdetr have a free or open-source option.