BaoLocPham

tutorials

This repository contains tutorials and examples for Triton Inference Server

attentions

PyTorch implementation of some attentions for Deep Learning Researchers.

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

Awesome-Language-Model-on-Graphs

A curated list of papers and resources based on "Large Language Models on Graphs: A Comprehensive Survey".

pytriton

PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.

graph-of-thoughts

Official Implementation of "Graph of Thoughts: Solving Elaborate Problems with Large Language Models"

open-llms

📋 A list of open LLMs available for commercial use.

optimum-nvidia

SeaLLMs

[ACL 2024 Demo] SeaLLMs - Large Language Models for Southeast Asia

solution-predict-ai-model-runtime

Databricks_LLM102x

This project contains the lab notebooks from course: Large Language Models: Foundation Models from the Ground Up

DeepSeek-LLM

DeepSeek LLM: Let there be answers

trulens

Evaluation and Tracking for LLM Experiments

flash-attention

Fast and memory-efficient exact attention

PhoGPT

PhoGPT: Generative Pre-training for Vietnamese (2023)

ZaloAIChallenge-2022

Top 2 Solution for Zalo AI Challenge 2022 - Liveness Detection track

train_ddp_bert

deepspeed_llama2

PokemonRedExperiments

Playing Pokemon Red with Reinforcement Learning

commonlit-summaries-competition

Source code for the 8th place solution to the CommonLit - Evaluate Student Summaries competition on Kaggle.

transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Sophia

Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.

Vietnamese-medical-chatbot-based

A simple Vietnamese Medical Chatbot Based

AWP

Codes for NeurIPS 2020 paper "Adversarial Weight Perturbation Helps Robust Generalization"

DeepSpeed

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

what_are_embeddings

A deep dive into embeddings starting from fundamentals

openai-python-enterprise-logging

wipeout-rewrite

ml-interviews-book

https://huyenchip.com/ml-interviews-book/

generative_agents

Generative Agents: Interactive Simulacra of Human Behavior