🍣 국내 스시 오마카세 맛집 리스트

Qwen2.5 is the large language model series developed by Qwen team, Alibaba Cloud.

DSPy: The framework for programming—not prompting—foundation models

Your first AI prompt engineer

Plumb a PDF for detailed information about each char, rectangle, line, et cetera — and easily extract text and tables.

The official code release for Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization

Zero shot pdf OCR with gpt-4o-mini

symspellpy를 한글 특성에 맞춰서 수정한 라이브러리. 음소분해를 이용해 더 정확한 오타교정을 해준다.

언어모델을 학습하기 위한 공개 한국어 instruction dataset들을 모아두었습니다.

A task runner that works well with poetry.

Optional static typing for Python

Fast, correct Python JSON library supporting dataclasses, datetimes, and numpy

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

aider is AI pair programming in your terminal

Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist

KoLLaVA: Korean Large Language-and-Vision Assistant (feat.LLaVA)

LLM101n: Let's build a Storyteller

Fast and memory-efficient exact attention

Improved file parsing for LLM’s

Developer APIs to Accelerate LLM Projects

Convert any URL to an LLM-friendly input with a simple prefix https://r.jina.ai/

Codebase accompanying the Summary of a Haystack paper.

A framework for few-shot evaluation of language models.

4M: Massively Multimodal Masked Modeling

A modular graph-based Retrieval-Augmented Generation (RAG) system

MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems

LDB: A Large Language Model Debugger via Verifying Runtime Execution Step by Step

ToRA is a series of Tool-integrated Reasoning LLM Agents designed to solve challenging mathematical reasoning problems by interacting with tools [ICLR'24].

[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models