model-card

GPT-2 pretrained on Korean datasets.

Open-source toolkit to help companies implement responsible AI workflows.

Published: 2026-10-18

Template for model cards

🧠🃏 Your universal model catalog, everything, everywhere, all at once.

A 6.87 GiB GGUF build of Qwen 3.8 27B — full 27B quality on 8 GB RAM. 96.7% HumanEval, 92.9% MMLU retention, no distillation.

Fully reproducible, Dockerized, step-by-step, tutorial on how to build a custom model card from Google's model card toolkit. Detailed blog post published on Towards Data Science.

An experimental project that examines whether interactivity can augment people's understanding of machine learning models through model cards

How to document an AI/Machine Learning Model

Validate the model card document in a GitHub action

Compact local AI image generation with Clover Image Tiny, Inpaint HQ image editing, LoRA styles, Diffusers, and Core ML for Apple devices.

Shows how to bulk generate model cards for models on 🤗 Hub.

Classify public sector helpdesk tickets using synthetic data and Hugging Face Transformers.

7.6B 中文总指挥模型：把活落到 348 位原生能力 / 30 域，写盘·花钱·出网一律先过人闸，每次调用都留审计留痕 | A 7.6B Chinese "commander" LLM that routes natural language to 348 audited capability bits behind one single gate. 335-item benchmark PASS45 99.10%; per-bit live-run proof included. Python client + 30s demo, zero deps.

Auto-generate ML model cards in Markdown format

Measurements of Apple's on-device model (Core Advanced) on a Mac: model card, runtime, memory, energy, tokenizer

Desktop workspace for quantizing LLMs to GGUF, MLX and ONNX. Watch every tensor change, compare against the original, and publish to Hugging Face with an auto-written model card.

Institutional student loan repayment risk model — with a documented target-leakage post-mortem.

Synthetic public-sector helpdesk ticket classifier using Hugging Face Transformers and safe JSONL training data.

Esqueleto Python da EVA IA com utilitário para publicar um Model Card em repositório privado no Hugging Face.