gnh1201/Open-Llama
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update readme

Browse Source
This commit is contained in:
LiangSong 2023-04-29 20:30:24 +08:00
parent fc21a75d1e
commit 52cd09f664
2 changed files with 4 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@ -2,7 +2,7 @@
* @Author: LiangSong(sl12160010@gmail.com) * @Author: LiangSong(sl12160010@gmail.com)
* @Date: 2023-03-10 21:18:35 * @Date: 2023-03-10 21:18:35
* @LastEditors: LiangSong(sl12160010@gmail.com) * @LastEditors: LiangSong(sl12160010@gmail.com)
* @LastEditTime: 2023-04-29 12:30:47 * @LastEditTime: 2023-04-29 20:29:31
* @FilePath: /Open-Llama/README.md * @FilePath: /Open-Llama/README.md
* @Description: * @Description:
* *
@ -72,6 +72,7 @@ print(tokenizer.decode(pred.cpu()[0]).strip())
3. 统一预训练和指令微调训练入口为train_lm.py 3. 统一预训练和指令微调训练入口为train_lm.py
4. 提供更方便的配置，可见configs/pretrain_config.yaml 4. 提供更方便的配置，可见configs/pretrain_config.yaml
5. 提供基于其他预训练模型补充词表，继续预训练功能 5. 提供基于其他预训练模型补充词表，继续预训练功能
6. 支持从中断点继续训练，包括加载优化器参数/学习率和跳过重复数据
[2023.4.16] Release v1.0 [2023.4.16] Release v1.0

3
README_en.md
View File

@ -2,7 +2,7 @@
* @Author: LiangSong(sl12160010@gmail.com) * @Author: LiangSong(sl12160010@gmail.com)
* @Date: 2023-03-10 21:18:35 * @Date: 2023-03-10 21:18:35
* @LastEditors: LiangSong(sl12160010@gmail.com) * @LastEditors: LiangSong(sl12160010@gmail.com)
* @LastEditTime: 2023-04-29 12:31:00 * @LastEditTime: 2023-04-29 20:30:12
* @FilePath: /Open-Llama/README_en.md * @FilePath: /Open-Llama/README_en.md
* @Description: * @Description:
* *
@ -72,6 +72,7 @@ This update mainly includes the following aspects, increasing the effective trai
3. Unify the pre-training and instruction fine-tuning training entry to train_lm.py 3. Unify the pre-training and instruction fine-tuning training entry to train_lm.py
4. Provide more convenient configuration, see configs/pretrain_config.yaml 4. Provide more convenient configuration, see configs/pretrain_config.yaml
5. Provide functionality to continue pre-training based on other pre-trained models and supplementing vocabulary 5. Provide functionality to continue pre-training based on other pre-trained models and supplementing vocabulary
6. Resuming training from a checkpoint is supported, including loading optimizer parameters/learning rate and skipping duplicate data
[2023.4.16] Release v1.0 [2023.4.16] Release v1.0