Jiahao Li

C++ implementation of ChatGLM-6B & ChatGLM2-6B & ChatGLM3 & GLM4(V)

用微信聊天记录训练一个你专属的聊天机器人

Train a tiny LLaMA model from scratch to repeat your words using Reinforcement Learning from Human Feedback (RLHF)

No description provided.

DSNet: A Flexible Detect-to-Summarize Network for Video Summarization

My CSAPP Lab Solutions

An educational PyTorch-like neural network framework based on NumPy

A super-fast Python implementation of seam carving algorithm for intelligent image resizing.

No description provided.

A tiny path tracer accelerated by OpenMP & CUDA.

A simple relational database based on Stanford CS346 RedBase, implemented in elegant modern C++14.

Accelerate LLM preference tuning via prefix sharing with a single line of code

My undergraduate projects at THU-CST

A Python wrapper of the official ROUGE-1.5.5.pl script and a re-implementation of full ROUGE metrics.

A minimal SOCKS5 proxy written in C.

KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA problems

ChatGLM2-6B: An Open Bilingual Chat LLM | 开源双语对话语言模型

ChatGLM-6B: An Open Bilingual Dialogue Language Model | 开源双语对话语言模型

CodeGeeX2: A More Powerful Multilingual Code Generation Model

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

GLM-4 series: Open Multilingual Multimodal Chat LMs | 开源多语言多模态对话模型

Python sync/async framework for Interactive Brokers API (replaces ib_insync)

TensorDict is a pytorch dedicated tensor container.

Separable Structure Modeling for Semi-supervised Video Object Segmentation

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

High throughput synchronous and asynchronous reinforcement learning

Port of Facebook's LLaMA model in C/C++

Tensor library for machine learning

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

Example models using DeepSpeed