koalazf99

tacube

The data and code for EMNLP 2022 paper "TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data"

CS385Projects

Independent Projects for SJTU CS385

amber-train

Pre-training code for Amber 7B LLM

awesome-llm-powered-agent

Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...

CodeQwen1.5

CodeQwen1.5 is the code version of Qwen, the large language model series developed by Qwen team, Alibaba Cloud.

cs2916

datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

datatrove

Freeing data processing from scripting madness by providing a set of platform-agnostic customizable pipeline processing blocks.

dbt-test

koalazf99.github.io

Personal Page

LLM-Agent-Survey

openai-cookbook

Examples and guides for using the OpenAI API

dspy

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

k2-train

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

open-interpreter

OpenAI's Code Interpreter in your terminal, running locally

prismatic-vlms

A flexible and efficient codebase for training visually-conditioned language models (VLMs)

sailcraft

Data Toolkit for Sailor Language Models

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.