Dellagi/DeepSeek-R1-Distill-Finetuning

This repository contains code for fine-tuning the DeepSeek-R1-Distill-Llama-8B model on financial data using LoRA (Low-Rank Adaptation). The implementation uses the Unsloth library for efficient training and inference.

语言：Jupyter Notebook · GitHub 星标：9 · Fork：3

在 GitHub 上查看原仓库