hllj

cosine_learning_metric_pytorch

My implementation for Cosine Learning Metric using for DeepSort

hello-world-project-esp32

Create a hello world project - a stimulator of harmonic motion by using TensorFlow Lite to train and learn a sinusoid model and deploy on ESP32 Board.

hllj.github.io

:triangular_ruler: Jekyll theme for building a personal site, blog, project documentation, or portfolio.

nlp-crawler

Vietnamese popular site Crawler with Scrapy

rag-ops

RAG - Ops: RAG with Operations. We help you to deploy RAG with changing in datasources.

simple-id-card-regconition

My Implementation for ID Card Regconition using Image Processing and OCR.

Vistral-V

Vistral-V: Visual Instruction Tuning for Vistral - Vietnamese Large Vision-Language Model.

ZaloAIChallenge-2022

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

Vista

This is the official repository for Vista dataset - A Vietnamese multimodal dataset contains more than 700,000 samples of conversations and images

Elementary-Math-Solving-Zalo-AI-2023

Baseline for ZaloAI Challenge 2023 Elementary Math Solving

hllj/Vistral-V

Vistral-V: Visual Instruction Tuning for Vistral - Vietnamese Large Vision-Language Model.

hllj/rag-ops

RAG - Ops: RAG with Operations. We help you to deploy RAG with changing in datasources.

hllj/nlp-crawler

Vietnamese popular site Crawler with Scrapy

hllj/simple-id-card-regconition

My Implementation for ID Card Regconition using Image Processing and OCR.

hllj/FPT-AI-Challenges-2023

FPT AI Challenges 2023 - Challenge 2

hllj/synthetic-text-embedding

hllj/TensorRT-LLM

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

hllj/vi-llama-recipes

Training Vietnamese with Llama 2 model - Just a playground

hllj/big-graph-lab-1

hllj/hllj.github.io

:triangular_ruler: Jekyll theme for building a personal site, blog, project documentation, or portfolio.

hllj/alignment-handbook

Robust recipes for to align language models with human and AI preferences

hllj/AutoAWQ

AutoAWQ implements the AWQ algorithm for 4-bit quantization with a 2x speedup during inference. Documentation:

hllj/axolotl

Go ahead and axolotl questions

hllj/cp-llama

Competitive Programming with CodeLlama

hllj/Cyclone

Unify Efficient Fine-tuning of 100+ LLMs

hllj/EditAnything

Edit anything in images powered by segment-anything, ControlNet, StableDiffusion, etc.

hllj/fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

hllj/Inpaint-Anything

Inpaint anything using Segment Anything and inpainting models.

hllj/Kaggle-ASL-2023

My solution for Kaggle Competition Google - Isolated Sign Language Recognition

hllj/llama-2-jax

JAX implementation of the Llama 2 model

hllj/LLM-Merging

LLM-Merging: Building LLMs Efficiently through Merging

hllj/open_clip

An open source implementation of CLIP.

hllj/peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

hllj/projectai1

The first project of AI Funtamentals Course

hllj/pytorch-image-models

PyTorch image models, scripts, pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNet-V3/V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

hllj/server

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

hllj/tensorrt_backend

The Triton backend for TensorRT.

hllj/text-generation-streaming-service

hllj/torchtune

A Native-PyTorch Library for LLM Fine-tuning

hllj/vllm

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