Chinese-Vicuna
/

Chinese-Vicuna-lora-7b-chatv1

Model card Files Files and versions Community

lu-vae commited on May 10, 2023

Commit

33c6f26

•

1 Parent(s): 7bc9a93

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -9,8 +9,8 @@ language:
 This is a Chinese instruction-tuning lora checkpoint based on llama-7B from [this repo's work](https://github.com/Facico/Chinese-Vicuna)
-We finetune it on the combination of [alpaca_chinese_dataset](https://github.com/hikariming/alpaca_chinese_dataset.git) and the Chinese part of sharegpt-90k data.
-We finetune it for 3 epochs use a single 4090 with ctxlen=2048.
 You can use it like this:
 ```python

 This is a Chinese instruction-tuning lora checkpoint based on llama-7B from [this repo's work](https://github.com/Facico/Chinese-Vicuna)
+We use the 50k Chinese data, which is the combination of [alpaca_chinese_instruction_dataset](https://github.com/hikariming/alpaca_chinese_dataset.git) and the Chinese conversation data from sharegpt-90k data.
+We finetune the model for 3 epochs use a single 4090 with ctxlen=2048.
 You can use it like this:
 ```python