Pinned Repositories
alpaca-lora
Instruct-tuning LLaMA on consumer hardware
AMT-webm
process webm videos collected from AMT
amtvideos_rating
R scripts and markdown files for analyzing human rating data on amt videos.
asap
ASAP: A Chinese Review Dataset Towards Aspect Category Sentiment Analysis and Rating Prediction
asap_sas
R scripts to process ASAP_SAS data
dl_response_rater
using DL, e.g., CNN or LSTM on rating responses automatically
interview_hs
R scripts wrote for parsing and analying our IV2014 data set.
keras_attn_reader
Keras implementation of an attention reader (using LSTM or GRU RNN)
mxnet_osx1011_mbp
A simple guide to install mxnet on a MBP using OSX 10.11
leocnj's Repositories
leocnj/keras_attn_reader
Keras implementation of an attention reader (using LSTM or GRU RNN)
leocnj/alpaca-lora
Instruct-tuning LLaMA on consumer hardware
leocnj/asap
ASAP: A Chinese Review Dataset Towards Aspect Category Sentiment Analysis and Rating Prediction
leocnj/attention
some attention implements
leocnj/call2018
leocnj/cv_flask
flask server running CV tasks.
leocnj/deep-learning-conda-envs
This repo contains Anaconda environment.yml files for different deep learning frameworks (i.e. TensorFlow, PyTorch, Theano, etc.)
leocnj/DeepSpeedExamples
Example models using DeepSpeed
leocnj/dlib_try
Try dlib, cv2 funcitons.
leocnj/docker-images
Dockerfiles for some multimodal toolkits
leocnj/docker-openpose
leocnj/docker-pyaa
Dockerfile for pyAudioAnalysis
leocnj/ecom-rakuten
Winning solution for the Rakuten Data Challenge, as part of SIGIR eCom '18.
leocnj/face-classification-js
Face classification on JavaScript
leocnj/ichiba_imgs
leocnj/kaldi-dnn-ali-gop
Forced alignment and Goodness of Pronunciation (GOP) with DNN support. Bases on Kaldi.
leocnj/KOBE
Source code and dataset for KDD 2019 paper "Towards Knowledge-Based Personalized Product Description Generation in E-commerce"
leocnj/leocnj.github.io
leocnj/lm-evaluation-harness
A framework for few-shot evaluation of language models.
leocnj/LongLoRA
Efficient long-context fine-tuning, supervised fine-tuning, LongQA dataset.
leocnj/Megatron-LM
Ongoing research training transformer models at scale
leocnj/MixMatch-pytorch
Code for "MixMatch - A Holistic Approach to Semi-Supervised Learning"
leocnj/nanotron
Minimalistic large language model 3D-parallelism training
leocnj/pytorch-kaldi-old
pytorch-kaldi is a project for developing state-of-the-art DNN/RNN hybrid speech recognition systems. The DNN part is managed by pytorch, while feature extraction, label computation, and decoding are performed with the kaldi toolkit.
leocnj/pytorch-StarGAN-VC
Fully reproduce the paper of StarGAN-VC. Stable training and Better audio quality .
leocnj/RAG_learn
A learning project of RAG and LLM
leocnj/StarGAN-Voice-Conversion
This is a pytorch implementation of the paper: StarGAN-VC: Non-parallel many-to-many voice conversion with star generative adversarial networks
leocnj/Video-Expression-Recognition
Recognising expression/emotion of unique faces in a video
leocnj/video_proc_docker
run openface (in a docker) on a video dir
leocnj/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs