From b26405dac3778eaec5a50536a993ae829f97420c Mon Sep 17 00:00:00 2001 From: ZHU QIHAO <18811325956@163.com> Date: Tue, 14 Nov 2023 12:16:26 +0800 Subject: [PATCH] Update README.md --- README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index a019fe4..bf1cbcc 100644 --- a/README.md +++ b/README.md @@ -265,12 +265,12 @@ In the following scenario, the DeepSeek-Coder-6.7B model effectively calls a cla ### 5. How to Fine-tune DeepSeek-Coder -We provide script `finetune_deepseekcoder.py` for users to finetune our models on downstream tasks. +We provide script `finetune/finetune_deepseekcoder.py` for users to finetune our models on downstream tasks. The script supports the training with [DeepSpeed](https://github.com/microsoft/DeepSpeed). You need install required packages by: ```bash -pip install -r requirements.txt +pip install -r finetune/requirements.txt ``` Please follow [Sample Dataset Format](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) to prepare your training data. @@ -285,7 +285,7 @@ DATA_PATH="" OUTPUT_PATH="" MODEL="deepseek-ai/deepseek-coder-6.7b-instruct" -deepspeed finetune_deepseekcoder.py \ +cd finetune && deepspeed finetune_deepseekcoder.py \ --model_name_or_path $MODEL_PATH \ --data_path $DATA_PATH \ --output_dir $OUTPUT_PATH \