-
Notifications
You must be signed in to change notification settings - Fork 1
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
可以提供一下微调的checkpoint吗? #1
Comments
您好,预训练模型可以直接从huggingface下载,链接在:https://github.com/loveisp/KDD_2024_AQA/tree/main/infer_with_pretrained 这里给出了。 微调后的模型的 lora 在这里:https://github.com/loveisp/KDD_2024_AQA/tree/main/finetune/sfr_finetuned ,按照:https://github.com/loveisp/KDD_2024_AQA/tree/main/finetune 给出的方法合并模型并做推断即可。 |
您好,合并后的模型权重可以从百度网盘下载: |
另外还有一些得到最后预测所需要的中间数据文件(主要是 faiss 计算得到的 D 和 I 矩阵),我也放到了百度网盘: |
好的,都已经看到。 |
五个模型在两个阶段的分数如下表所示:
奇怪的一点是:微调后的SFR-Embedding-Mistral在第一阶段的分数很高,但在第二阶段分数又比其他模型低,是因为过拟合了吗? |
我是kdd比赛组织人员,为了复现下最终结果。
The text was updated successfully, but these errors were encountered: