Update README.md
Browse files
README.md
CHANGED
|
@@ -3,4 +3,9 @@ license: apache-2.0
|
|
| 3 |
---
|
| 4 |
This model is trained on 60G chinese and english instruction,a base model which enhances chiense capacity.
|
| 5 |
You can dowload Moses25/Instruct-dataset11M dataset to train your own model with 32K context length.
|
| 6 |
-
My Moses25/Mistral-7B-chat-32k is trained based on Moses25/Instruct-dataset11M dataset
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
This model is trained on 60G chinese and english instruction,a base model which enhances chiense capacity.
|
| 5 |
You can dowload Moses25/Instruct-dataset11M dataset to train your own model with 32K context length.
|
| 6 |
+
My Moses25/Mistral-7B-chat-32k is trained based on Moses25/Instruct-dataset11M dataset
|
| 7 |
+
|
| 8 |
+
```
|
| 9 |
+
git clone https://github.com/moseshu/llama-recipes
|
| 10 |
+
sh ft.sh
|
| 11 |
+
```
|