# philschmid/deep-learning-pytorch-huggingface

Repository: https://github.com/philschmid/deep-learning-pytorch-huggingface
Canonical: https://ross.abutalabs.com/products/deep-learning-pytorch-huggingface
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2025-02-27T14:37:20+00:00

## Health v2 (maintenance only)
Score: 35/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 8, release rhythm 35, longevity 97
- inputs: {"age_days": 1366, "days_push": 552, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1392, forks 262 (observed 2026-08-28T04:04:36.059276+00:00)

## What it is
A collection of Jupyter notebook tutorials and examples for deep learning with PyTorch and Hugging Face libraries like Transformers, Datasets, TRL, and Accelerate. It covers fine-tuning LLMs (FLAN-T5, Llama, Falcon, Gemma), quantization, DPO alignment, embedding models for RAG, and inference techniques.

## Use cases
- learn how to fine-tune LLMs with Hugging Face TRL
- instruction-tune Llama 2 with QLoRA
- fine-tune an embedding model for RAG
- quantize open LLMs with GPTQ
- scale distributed training with FSDP and DeepSpeed
- align LLMs with DPO
- run efficient LLM inference and benchmarks

## When to choose
- you want hands-on, up-to-date notebooks for LLM fine-tuning with PyTorch and Hugging Face
- you need practical examples of LoRA, QLoRA, DPO, or GPTQ quantization
- you are learning distributed training with DeepSpeed or FSDP

## When to avoid
- you need a production-ready training framework rather than tutorials
- you work outside the PyTorch/Hugging Face ecosystem
- you need non-LLM deep learning topics like computer vision

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, deep-learning, llm-training, llm-inference, rag
- domain: deep-learning, large-language-models, machine-learning, tutorials
- platform: python, cross-platform
- tags: pytorch, hugging-face, transformers, jupyter-notebooks, fine-tuning, lora, deepspeed, dpo, quantization, example-code, gpu

## Member repositories
- philschmid/deep-learning-pytorch-huggingface (main) score 35

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:36.059276+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:39:33.216091+00:00, confidence not recorded.
  - readme: https://github.com/philschmid/deep-learning-pytorch-huggingface (fetched 2026-08-28T04:04:36.059276+00:00, sha 84abe288c2a7)
- Data as of 2026-08-30T08:39:29.467469+00:00.