“Hugging Face”

获取 Hugging Face 上的模型、数据集和 Space 的统计信息

Create and manage datasets on Hugging Face Hub.

Add and manage evaluation results in Hugging Face model cards.

This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs…

Convert existing Hugging Face Transformers Trainer or TRL SFTTrainer training code into an NVFLARE federated job using flare.patch(trainer), local validation…

Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure.

Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT…

Publish and manage research papers on Hugging Face Hub.

Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help.

Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware.

Use when building Hugging Face smolagents, code-executing agents, Python-action agents, Hub-shared tools, or lightweight agent prototypes that need sandboxing…

Use this skill for Hugging Face Diffusers tasks: pipeline inference, schedulers, adapters/loaders, training recipes, modular pipelines, conversion helpers…

Use this skill when working with Hugging Face Datasets: loading local or Hub datasets, defining Features schemas, processing/streaming datasets, converting…

Use Hugging Face Accelerate for PyTorch training-loop migration, distributed launch/configuration, DeepSpeed/FSDP/TPU backend setup, big-model…

Use Hugging Face Evaluate to load metrics, comparisons, and measurements; compute and combine results; run evaluator pipelines; create custom modules…

Use bitsandbytes for k-bit PyTorch quantization, Hugging Face quantized model loading, 8-bit and paged optimizers, direct quantized layers/functions, and…

Fetches and summarizes recent arXiv and Hugging Face papers with Agentic Paper Digest.

Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder, dense or static embedding model for retrieval, similarity…

Discovers and evaluates scientific datasets, models, methodology posts, and Spaces through the Hugging Science catalog.

Use when a medical AI paper should be found and cited by AI search engines and RAG tools.

Finetune a pretrained KERMT encoder on a labeled CSV.

Comprehensive news aggregator that fetches, filters, and deeply analyzes real-time content from 44+ sources including Hacker News, Lobsters, Dev.to, GitHub…

Continue KERMT pretraining on a custom SMILES corpus with a grover_base, cmim, or hybrid checkpoint.

Extract per-molecule embeddings from any encoder-bearing KERMT checkpoint.