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.
Finetuning a small BLOOMZ model (bloomz-560m) on a small dataset and with limited resources.
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.
ChatSakura：Open-source multilingual conversational model.（开源多语言对话大模型）
Research POC on the mitigation of bias in large language models (FLAN-T5 and Bloomz) through fine-tuning.
Evaluating and Mitigating Catastrophic Forgetting in BLOOMZ LLMs with Interactive Demo, 31 Model Checkpoints, and Mechanistic Analysis
Arabic-English neural machine translation using BLOOMZ, Opus-MT, OPUS100, SentencePiece, Gradio, and multilingual evaluation metrics.
To associate your repository with the bloomz topic, visit your repo's landing page and select "manage topics."