Next-generation AI workspace

Updated Version of Apertus Evals for Apertus 1.5 Post-Training

Greek Dataset Production from PDF+

streamline the fine-tuning process for multimodal models: PaliGemma 2, Florence-2, and Qwen2.5-VL

Generate LoRA Adapters from documents

PDF-to-Obsidian pipeline using MLX LLaMA with custom LoRA adapters for multi-perspective paper summaries (ELI5, Executive, Intuitive)

Awesome LLM pre-training resources, including data, frameworks, and methods.

An end to end LoRA example using Llama 3.2:1b

A demonstration of my experiments to deliver BOAT with the computational notebook Jupyter, so far deploying JupyterLab, served via JupyterLite and GitHub Pages.

Ongoing research training transformer models at scale

KVarN is a native vLLM KV-cache quantization backend for your agents: 3-5x more context, throughput above FP16, and FP16-level accuracy. Calibration-free, one flag.

A collection of 150+ surveys on LLMs

LAmbda MCP: teach your LLM to do Grasshopper tricks

We introduce MKQA, an open-domain question answering evaluation set comprising 10k question-answer pairs aligned across 26 typologically diverse languages (260k question-answer pairs in total). The…

Connect Your Agents And Harnesses With Any Provider 🦚

Repo for the GovTech Hackathon 2026 challenge

This gateway is a standalone service that proxies LLM requests with API key management, budget enforcement, usage tracking, and OpenAI-compatible endpoints.

Pretraining Efficiently on S2ORC!

Starter Code (R and Python) for all CSV data sets of Team Data Shop, Statistical Office, Canton Zurich

Automatically generates starter code notebooks in Python and R from opendata.muenchen.de

MCP server for the Swiss I14Y Interoperability Platform

A project to collect, archive, and publish robots.txt files from across the internet - with a focus on government websites

One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks

Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build with Nemotron models

OSS AI Legal Platform merged with BetterCallClaude