FinQwen: 致力于构建一个开放、稳定、高质量的金融大模型项目，基于大模型搭建金融场景智能问答系统，利用开源开放来促进「AI+金融」。

Interactively explore unstructured datasets from your dataframe.

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

A framework for few-shot evaluation of language models.

Calculate token/s & GPU memory requirement for any LLM. Supports llama.cpp/ggml/bnb/QLoRA quantization

Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting…

The official Meta Llama 3 GitHub site

MOSS-RLHF

Example models using DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

The official GitHub page for the survey paper "A Survey of Large Language Models".

An annotated implementation of the Transformer paper.

个人中文简历 Latex 源码 https://hijiangtao.github.io/

AI and Memory Wall

Code for "Dynamic Discounted Counterfactual Regret Minimization", ICLR 2024 (Spotlight)

Code for the paper "Deep FTRL-ORW: An Efficient Deep Reinforcement Learning Algorithm for Solving Imperfect Information Extensive-Form Games" presented at AAAI 2023.

Scalable implementation of DREAM - Deep RL for multi-agent imperfect information games

Scalable Implementation of Deep CFR and Single Deep CFR

Code for "Minimizing Weighted Counterfactual Regret with Optimistic Online Mirror Descent", IJCAI 2024 (Oral)

Code for "AutoCFR: Learning to Design Counterfatual Regret Minimization Algorithms", AAAI 2022 (Oral)

Matplotlib styles for scientific plotting

This repository contains demos I made with the Transformers library by HuggingFace.