Skip to content
View cheungdaven's full-sized avatar
🎯
Focusing
🎯
Focusing

Organizations

@DS3Lab @d2l-ai

Block or report cheungdaven

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

Flexible and powerful framework for managing multiple AI agents and handling complex conversations

TypeScript 2,916 203 Updated Dec 11, 2024

The Memory layer for your AI apps

Python 23,338 2,152 Updated Dec 13, 2024

Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

Python 4,304 223 Updated Dec 12, 2024

Fast inference from large lauguage models via speculative decoding

Python 602 63 Updated Aug 22, 2024

A curated list for Efficient Large Language Models

Python 1,323 94 Updated Dec 9, 2024

NVTabular is a feature engineering and preprocessing library for tabular data designed to quickly and easily manipulate terabyte scale datasets used to train deep learning based recommender systems.

Python 1,057 143 Updated Sep 3, 2024

Academic Homepage Template

JavaScript 56 13 Updated Oct 27, 2024

[ACL'24] Selective Reflection-Tuning: Student-Selected Data Recycling for LLM Instruction-Tuning

Python 342 30 Updated Sep 6, 2024

The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.

LLVM 29,602 12,240 Updated Dec 14, 2024

FlashInfer: Kernel Library for LLM Serving

Cuda 1,548 153 Updated Dec 13, 2024

Retrieval-Augmented Generation in 3 Lines of Code!

Python 30 7 Updated Dec 5, 2024

TimesFM (Time Series Foundation Model) is a pretrained time-series foundation model developed by Google Research for time-series forecasting.

Python 3,865 332 Updated Dec 12, 2024

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

Python 2,683 215 Updated Dec 13, 2024

This is an implementation of the paper: Searching for Best Practices in Retrieval-Augmented Generation (EMNLP2024)

Python 237 14 Updated Sep 25, 2024

Discovering Bias in Latent Space: An Unsupervised Debiasing Approach (ICML 2024)

Jupyter Notebook 7 1 Updated Jun 20, 2024

Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.

Python 6,013 518 Updated Sep 6, 2024

Ongoing research training transformer models at scale

Python 10,805 2,416 Updated Dec 13, 2024

PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)

Python 12 2 Updated Jun 14, 2024

Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

Python 1,396 58 Updated Aug 15, 2024

Structured state space sequence models

Jupyter Notebook 2,497 299 Updated Jul 17, 2024

LogAI - An open-source library for log analytics and intelligence

Python 465 67 Updated Nov 14, 2024

CaMML:Context-Aware MultiModal Learner for Large Models (ACL 2024)

Python 12 Updated Jun 18, 2024

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

Python 4,256 405 Updated Dec 13, 2024

Finetune mistral-7b-instruct for sentence embeddings

Python 74 17 Updated May 2, 2024

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…

Jupyter Notebook 15,579 2,251 Updated Dec 12, 2024

CoMM: Collaborative Multi-Agent, Multi-Reasoning-Path Prompting for Complex Problem Solving (NAACL 2024 Findings))

Python 14 Updated Apr 26, 2024

Get up and running with Llama 3.3, Mistral, Gemma 2, and other large language models.

Go 102,647 8,195 Updated Dec 14, 2024

Generative Representational Instruction Tuning

Jupyter Notebook 573 41 Updated Nov 18, 2024

Code for "SemDeDup", a simple method for identifying and removing semantic duplicates from a dataset (data pairs which are semantically similar, but not exactly identical).

Python 117 13 Updated Oct 1, 2023
Next