TorchDR - PyTorch Dimensionality Reduction

A Latex style and template for paper preprints (based on NIPS style)

Fully open reproduction of DeepSeek-R1

A framework for few-shot evaluation of language models.

Supercharge Your LLM Application Evaluations 🚀

the LLM vulnerability scanner

Open source alternative to AWS. Elastic compute, block storage (non replicated), firewall and load balancer, managed Postgres, and IAM services in public beta.

UNLP 2025 Shared Task on Detecting Social Media Manipulation

Code for BLT research paper

Python tool for converting files and office documents to Markdown.

Database of Steam video game data from October 2024, including game details, genres, reviews, tags, and SteamSpy insights

Accelerating the development of large multimodal models (LMMs) with one-click evaluation module - lmms-eval.

prime is a framework for efficient, globally distributed training of AI models over the internet.

Qwen2.5-Coder is the code version of Qwen2.5, the large language model series developed by Qwen team, Alibaba Cloud.

Efficient Triton Kernels for LLM Training

Pro-ukrainian LLM-based bot

Шаблон дисертації та звіту у латесі за ДСТУ

Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"

Distributed Training Over-The-Internet

Dictionary of obscene words for Ukrainian language

Together Mixture-Of-Agents (MoA) – 65.1% on AlpacaEval with OSS models

Go ahead and axolotl questions

OCR, layout analysis, reading order, table recognition in 90+ languages

Kolmogorov Arnold Networks

NVIDIA Linux open GPU with P2P support

Training LLMs with QLoRA + FSDP