Skill search for "huggingface".

Create and manage datasets with configs and SQL querying

Run compute jobs and Python scripts on HF infrastructure

Build reusable scripts for HF API operations

Run ML models in the browser with Transformers.js

Browse and query HF datasets with the Dataset Viewer API

Model evaluation with vLLM/lighteval and eval tables

Train models with TRL: SFT, DPO, GRPO, GGUF conversion

Publish papers on HF Hub with model/dataset links

Track ML experiments with real-time dashboards

Train vision models on HF infrastructure

Build Gradio apps and deploy to HF Spaces

Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tas...

Look up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page. Use when the user shares a Hugging Face paper page URL, an arXiv URL or ID, or asks to summarize, explain, or analyze an AI research paper.

Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation,...