Crosslingual Generalization through Multitask Finetuning

The ParroT framework to enhance and regulate the Translation Abilities during Chat based on open-sourced LLMs (e.g., LLaMA-7b, Bloomz-7b1-mt) and human written translation and evaluation data.

使用qlora对中文大语言模型进行微调，包含ChatGLM、Chinese-LLaMA-Alpaca、BELLE

Finetuning a small BLOOMZ model (bloomz-560m) on a small dataset and with limited resources.

ChatSakura：Open-source multilingual conversational model.（开源多语言对话大模型）

LLM application: fine tuned model to generate social media posts from technical blogposts. I used the documentation in https://numpy.org/numpy-tutorials/index.html to build a synthetic dataset and used that dataset to fine-tune an open source model.

Research POC on the mitigation of bias in large language models (FLAN-T5 and Bloomz) through fine-tuning.