#
wead-hsu
Follow
Starred repositories
DSPy: The framework for programming—not prompting—foundation models
A high-throughput and memory-efficient inference and serving engine for LLMs
A guidance language for controlling large language models.
SGLang is yet another fast serving framework for large language models and vision language models.
PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)
[ICML 2024 Best Paper] Discrete Diffusion Modeling by Estimating the Ratios of the Data Distribution (https://arxiv.org/abs/2310.16834)
KPQA is an evaluation metric for generative question answering. (NAACL-21)
An Open-source Framework for Data-centric, Self-evolving Autonomous Language Agents
ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].
Unified Interface for Constructing and Managing Workflows on different workflow engines, such as Argo Workflows, Tekton Pipelines, and Apache Airflow.
The official repo of Qwen (通义千问) chat & pretrained large language model proposed by Alibaba Cloud.
The official repo of INF-34B models trained by INF Technology.
A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具，支持PDF/网页/多格式电子书提取。
Setup AI2Apps at local system so you can use your own OpenAI key or make more back-end features.
Language Savant. If your repository's language is being reported incorrectly, send us a pull request!
A large-scale simulation framework for LLM inference
Mix of Minimal Optimal Sets (MMOS) of dataset has two advantages for two aspects, higher performance and lower construction costs on math reasoning.
A central, open resource for data and tools related to chain-of-thought reasoning in large language models. Developed @ Samwald research group: https://samwald.info/
Data and code for EMNLP 2021 paper "FinQA: A Dataset of Numerical Reasoning over Financial Data"
DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence
Codes and Data for ACL 2024 Paper "Faithful Logical Reasoning via Symbolic Chain-of-Thought".
The project page for "LOGIC-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning"
Multiple paper open-source codes of the Microsoft Research Asia DKI group