Stars
An edge-native Multimodal Android Agent that integrates multimodal perception, memory and action
Extracting time features from text using a Finite State Transducer (FST) in Python
Enhancement suite for Gemini, AI Studio, Claude & ChatGPT — plus a prompt manager for any web UI, DeepSeek Harness included. / 面向 Gemini、AI Studio、Claude 与 ChatGPT 的增强套件；提示词管理器可用于任意 Web UI，含 DeepSe…
A framework for evaluating Machine Translation models.
Training an LLM to use a calculator with multi-turn reinforcement learning, achieving a **62% absolute increase in evaluation accuracy**.
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
The media player for language learning, with dual subtitles, AI-generated subtitles, real-time translation, and more!
A personalized language-learning tool that combines Duolingo-style lessons with your own curated vocabulary lists. Seamlessly add words from books, articles, or videos, and revisit them through in…
Recommend new arxiv papers of your interest daily according to your Zotero libarary.
imfile-io / imfile-desktop
Forked from agalwood/MotrixA full-featured download manager.
为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…
主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题
A repo lists papers related to LLM based agent
Must-read Papers on Large Language Model (LLM) Planning.
optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052
Papers & Works for large languange models (OpenAI GPT-4, Meta Llama, etc.).
NTREX -- News Test References for MT Evaluation
A playbook for systematically maximizing the performance of deep learning models.
Explore Python's charms by asking WHY questions
chinese NLP corpus of chinese science fiction,chinese science fiction corpus : About 4675 Chinese science fiction novels 大约有4675本科幻小说，中文科幻小说自然语言处理语料库，中文科幻小说文本语料库，中文科幻小说文本数据库，科幻小说语料
python 更加方便的多线程库，以最小的代码侵入，做到最高效的多线程、线程池 coding 效率。在不改变源代码的情况下，一行代码即可实现线程池操作。
Graphic notes on Gilbert Strang's "Linear Algebra for Everyone"
This is a code repository for the ACL 2022 paper "Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation"