Official release of InternLM2.5 base and chat models. 1M context support

A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。

Simple Python version management

A trainable PyTorch reproduction of AlphaFold 3.

AlphaFold 3 inference pipeline.

OSX (macOS) inside a Docker container.

A playbook for effectively prompting post-trained LLMs

Official PyTorch implementation of DistiLLM: Towards Streamlined Distillation for Large Language Models (ICML 2024)

Windows inside a Docker container.

Prompt tuning app heavily inspired by Anthropic Console Workbench. Built using Mesop.

UI for testing prompts across various datasets locally

A framework for the evaluation of autoregressive code generation language models.

Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024

cog implementation of All-In-One Music Structure Analyzer

Please see the readme file as well as our 2019 EMNLP paper linked here -->

An LLM-powered repository agent designed to assist developers and teams in generating documentation and understanding repositories quickly.

Utility scripts for preprocessing Wikipedia texts for NLP

MediaWiki Categories Model

Library for reading and writing Jcat files

LLM framework exploring ergonomic, lightweight multi-agent orchestration. Forked from OpenAI Solution team.

A new bootable USB solution.

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"

Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.

Code for 'Multi-level Logit Distillation' (CVPR2023)

A framework for serving and evaluating LLM routers - save LLM costs without compromising quality!

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

pgEdge Distributed Postgres