Torchcode Pytorch Interview Practice
If you're prepping for ML engineering interviews or just want to sharpen your PyTorch fundamentals, this gives you 40 LeetCode-style problems focused on implementing everything from ReLU and softmax to multi-head attention and GPT-2 components from scratch. The torch_judge package auto-grades your implementations with correctness checks, gradient verification, and timing feedback. You can run it in Colab, Hugging Face Spaces, or locally via Docker. The problems range from numerical stability tricks in softmax to full transformer blocks, and each notebook includes templates plus reference solutions. It's honestly the kind of drilling that separates people who can use PyTorch from people who understand what's happening under the hood.
- skills.sh installs
- 753
- GitHub stars
- 61
- last updated
- Jul 14, 2026
Install
$ npx -y skills add aradotso/trending-skills --skill torchcode-pytorch-interview-practice --agent claude-codeInstalls into .claude/skills of the current project.
Files
TorchCode — PyTorch Interview Practice
Skill by ara.so — Daily 2026 Skills collection.
TorchCode is a Jupyter-based, self-hosted coding practice environment for ML engineers. It provides 40 curated problems covering PyTorch fundamentals and architectures (softmax, LayerNorm, MultiHeadAttention, GPT-2, etc.) with an automated judge that gives instant pass/fail feedback, gradient verification, and timing — like LeetCode but for tensors.
Installation & Setup
Option 1: Online (zero install)
- Hugging Face Spaces: https://huggingface.co/spaces/duoan/TorchCode
- Google Colab: Every notebook has an "Open in Colab" badge
Option 2: pip (for use inside Colab or existing environment)
pip install torch-judge
Option 3: Docker (pre-built image)
docker run -p 8888:8888 -e PORT=8888 ghcr.io/duoan/torchcode:latest
# Open http://localhost:8888
Option 4: Build locally
git clone https://github.com/duoan/TorchCode.git
cd TorchCode
make run
# Open http://localhost:8888
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/aradotso/trending-skills
- Category
- Data Science & ML
- First seen
- May 16, 2026
More from aradotso/trending-skills
All 251- Codex Session Patcher750
- Learn Docker K8s Game746
- Claude Better Cli744
- Ministack Aws Emulator743
- Wildworld Dataset739
- Phantom Ai Coworker729
- Kordoc Korean Document Parser727
- Claw Code Harness721
- Clawd Code Python Port714
- See Through Anime Layer Decomposition706
- Open Agent Sdk701
- Openclaude Multi Llm673
- Emdash Cms672
- Cc Gateway Ai Proxy668
- Open Multi Agent Orchestration665
- Pretext Text Measurement649
- Claude Code Source Recovery648
- Sheets Terminal Spreadsheet646
- Omnivoice Tts627
- Metatron Pentest Assistant602
- Tong Jincheng Relationship Skill595
- Awesome Design Md Jp594
- Parlor On Device Ai588
- Paper2code Arxiv Implementation585
Recommended
More Data Science & ML
car-sales-data-engineering-analyticsaradotso/data-skillscar sales data engineering analytics713skills.sh installspaper2code-arxiv-implementationaradotso/trending-skillspaper2code arxiv implementation585skills.sh installs
xgboost-lightgbmtondevrel/scientific-agent-skillsIndustry-standard gradient boosting libraries for tabular data and structured datasets. XGBoost and LightGBM excel at classification and regression tasks on tab488skills.sh installs
statistics-mathpluginagentmarketplace/custom-plugin-data-engineerStatistics, probability, linear algebra, and mathematical foundations for data science433skills.sh installs
ml-expertpersonamanagmentlayer/pclExpert-level machine learning, deep learning, model training, and MLOps365skills.sh installs