Commit
•
2738441
1
Parent(s):
88a3b5a
Update README.md
Browse files
README.md
CHANGED
|
@@ -25,7 +25,7 @@ This model trained by SFT, DPO, RLHF(reward model & PPO)
|
|
| 25 |
|
| 26 |
It's have coding, reasoing, chinese QA and safe-refusal function.
|
| 27 |
|
| 28 |
-
You
|
| 29 |
|
| 30 |
I published mix-instruction alpaca-style dataset '[xiaodongguaAIGC/alpaca_en_zh_ruozhiba](https://huggingface.co/datasets/xiaodongguaAIGC/alpaca_en_zh_ruozhiba)'
|
| 31 |
|
|
|
|
| 25 |
|
| 26 |
It's have coding, reasoing, chinese QA and safe-refusal function.
|
| 27 |
|
| 28 |
+
You could test this model with [Colab](https://colab.research.google.com/drive/1FQXumJcnzcvYcszxj6O-D7QFgjfMPnei?usp=sharing)
|
| 29 |
|
| 30 |
I published mix-instruction alpaca-style dataset '[xiaodongguaAIGC/alpaca_en_zh_ruozhiba](https://huggingface.co/datasets/xiaodongguaAIGC/alpaca_en_zh_ruozhiba)'
|
| 31 |
|