Skip to content
View sunshine-JLU's full-sized avatar
  • Hong Kong University
  • Hongkong

Block or report sunshine-JLU

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.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
sunshine-JLU/README.md

Hi, I'm Runheng Cai πŸ‘‹

AI/ML learner focusing on Large Language Models (LLMs).


πŸš€ Current Focus

  • LLM Alignment: RL & MLLM

πŸŽ“ Education

Master@HKU Computer Science, The University of Hong Kong (HKU)

Bachelor@JLU Information Engineering, Jilin University (JLU)

πŸ’Œ Contact Me

GitHub Contribution Graph

Pinned Loading

  1. cis_grpo cis_grpo Public

    CIS-GRPO: Contrastive Image Sampling for GRPO training of VLMs

    Python 1

  2. deepseek-janus-pro-lora deepseek-janus-pro-lora Public

    The objective of this project is to demonstrate how to fine-tune deepseek-janus-pro-lora.

    Python 41 5

  3. AnyLLM-to-VLM AnyLLM-to-VLM Public

    Turn any text-only LLM into a Vision-Language Model through efficient training.

    Python 24 2

  4. deepseek-r1-distill-llama-8b-lora deepseek-r1-distill-llama-8b-lora Public

    The objective of this project is to demonstrate how to fine-tune deepseek-r1-distill-llama-8b.

    Jupyter Notebook 17 5

  5. Who_is_the_undercover_agent_LLM Who_is_the_undercover_agent_LLM Public

    The function of this project is to have different large models play the game of who is the undercover agent

    HTML 1

  6. deepseek-r1-distill-qwen-7B-lora deepseek-r1-distill-qwen-7B-lora Public

    The objective of this project is to demonstrate how to fine-tune deepseek-r1-distill-qwen-7B.

    Jupyter Notebook 3