Junchen(Kevin) Zhao's repositories
LinguaLinked-Inference
Distributed On-Device LLM Inference
OpenVaccine-COVID-19-mRNA-Vaccine-Degradation-
We are designing a model using CNN+GCN to predict the likely degradation rates at each base of an RNA molecule, trained on a subset of an Eterna dataset comprising over 3000 RNA molecules (which span a panoply of sequences and structures) and their degradation rates at each position. We will then score our models on a second generation of RNA sequences that have just been devised by Eterna players for COVID-19 mRNA vaccines.
BQ_PROJECT
Apply a Transformer-based model for financial data prediction.
My-Data-Science-Projects
This Repository consists of my past Data Science project works as a showcase of my professional skills.
onnxruntime-training-examples
Examples for using ONNX Runtime for model training.
UCI-CS241-Advanced-Compiler-main
UCI-CS241-Advanced-Compiler-W23
Dist-Course-Enroll
UCI CS230 Winter 2023 Course Project
Imperial-College-London-Computing-MEng-Individual-Project-Multi-agent-Apprenticeship-Learning
As the rapid development of Artifical Intelligence in the current technology field, the Rein- forcement Learning has been proven to be a powerful technique that allows autonomous agents to learn optimal behaviors (called policies) in unknown and complex environments through models of rewards and penalizations. However, in order to make this technique (Reinforcement Learning) work correctly and get the precise reward function which returns feedback to the learning agent about when the agent behaves correctly or not, the reward function needs to be thoroughly specified. As a result, in real-world complex environments, such as autonomous driving, specifying a correct reward function could be one of the hard tasks to tackle for the Reinforcement Learn- ing model designers. To this end, Apprenticeship Learning techniques such as Inverse Re- inforcement Learning, in which technique the agent infers a reward function from expert behaviors, are of high interest due to the fact that they could result in highly specified reward function efficiently. However, for critical tasks such as autonomous driving, we need to critically consider about the safety-related issues, so as to we need to build techniques to automatically check and ensure that the inferred rewards functions and policies that resulted from the Reinforcement Learning model system fulfill the needed safety requirements of the critical tasks that we have mentioned previously. In order to have a well-designed Reinforcement Learning model system, which is able to gen- erate the highly-specified reward function and ensure the safety-related considerations, we are applying the Reinforcement Learning technique mentioned in the background section called Apprenticeship Learning, which will be introduced in detail in the later section. Our objective of this project is to make the extra extension based on the technique men- tioned in the paper "Safety-aware Apprenticeship Learning" written by Weichao Zhou and Wenchao Li[3] to improve the utility and the efficiency of the existing Reinforcement Learn- ing model system from single-agent learning setting to multi-agent setting framework.
JunchenZhao.github.io
A beautiful, simple, clean, and responsive Jekyll theme for academics
KVQuant
KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
UCI-CS169-Project-Code
UCI CS169 Project Code
WizardLM
Family of instruction-following LLMs powered by Evol-Instruct: WizardLM, WizardCoder