[NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs

Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthr…

Autonomous experiment loop extension for pi

[VLDB' 25] ChatTS: Understanding, Chat, Reasoning about Time Series with TS-MLLM

EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).

Wan: Open and Advanced Large-Scale Video Generative Models

Official code for "Interpretable Language Modeling via Induction-head Ngram Models"

Forecast evaluation library

A python module to repair invalid JSON from LLMs

AI agents running research on single-GPU nanochat training automatically

Nanochat in MLX

SleepLM: Natural-Language Intelligence for Human Sleep

OSF: On Pre-training and Scaling of Sleep Foundation Models

Code and website for Self-Flow: Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis

[AAAI-23 Oral] Official implementation of the paper "Are Transformers Effective for Time Series Forecasting?"

Official implementation of the paper "Understanding Language Prior of LVLMs by Contrasting Chain-of-Embedding"

Gas Town - multi-agent workspace manager

Label Studio is a multi-type data labeling and annotation tool with standardized output format

A Training and Evaluation Framework for ECG-Language Models (ELMs)

A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows

Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"

Research-oriented pretraining and evaluation pipelines for ECG-specific neural networks

Image Markov Chain Monte Carlo

Build compute kernels and load them from the Hub.

Set up a specific version of NVIDIA CUDA in GitHub Actions on Linux x86_64, arm64 (Debian and Fedora based distribution) and Windows

Provide with pre-build flash-attention package wheels on Linux and Windows platforms using GitHub Actions

Qwen3.5 is the large language model series developed by Qwen team, Alibaba Cloud.