huggingface.co/models. Filter by: - Task (text generation, image, audio) - Library (Transformers, PEFT, etc.) - License - Languages

bash pip install transformers torch python from transformers import pipeline pipe = pipeline("text-generation", model="meta-llama/Llama-3.1-8B-Instruct") print(pipe("Hello, ", maxlength=50))

Don't want to run locally? Use HF inference: python from huggingfacehub import InferenceClient client = InferenceClient(token="hf...") response = client.textgeneration( model="meta-llama/Llama-3.1-405B-Instruct", prompt="Hello", ) print(response)

python from datasets import loaddataset ds = loaddataset("imdb") print(ds["train"][0]) Browse: huggingface.co/datasets.

Deploy demos for free: 1. Click "New Space" 2. Choose Gradio or Streamlit 3. Push code 4. Get hosted URL Free CPU tier; GPU paid ($0.05-2/hour).

Fine-Tuning with AutoTrain

GUI-based fine-tuning: 1. Upload dataset 2. Pick base model 3. Choose hyperparameters 4. Train 5. Push to Hub No code required.

Transformers Library Patterns

Tokenization python from transformers import AutoTokenizer tokenizer = AutoTokenizer.frompretrained("bert-base-uncased") inputs = tokenizer("Hello world", returntensors="pt") Model Loading python from transformers import AutoModel model = AutoModel.frompretrained("bert-base-uncased") Quantization python from transformers import BitsAndBytesConfig quantconfig = BitsAndBytesConfig(loadin4bit=True) model = AutoModelForCausalLM.frompretrained("...", quantizationconfig=quantconfig)

PEFT (Parameter-Efficient Fine-Tuning)

python from peft import LoraConfig, getpeftmodel peftconfig = LoraConfig(r=8, loraalpha=16, targetmodules=["qproj", "vproj"]) model = getpeftmodel(model, peftconfig)

How to Use Hugging Face 2026 — Guide

Q: What It Is

Hub: model + dataset host (1M+ models) - Transformers: Python library - Spaces: deploy demos - Inference API: hosted inference - AutoTrain: no-code fine-tuning

How to Use Hugging Face 2026

Hugging Face is the GitHub for AI. This guide covers everything you need. What It Is - Hub: model + dataset host 1M+ models - Transformers: Python library - Spaces: deploy demos - Inference API: hosted inference - AutoTrain: no-code fine-tuning Sign Up huggingface.co → email signup. Free tier generous. Browse Models huggingface.co/models. Filter by: - Task text generation, image, audio - Library…

All guides

Related guides

How to Start AI SaaS 2026
How to Use v0 by Vercel 2026 — Complete Walkthrough
How to Become a Vibe Coder: 2026 Roadmap
How to Build an AI Agent 2026
How to Build a Chatbot 2026