Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,11 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
---
|
| 4 |
+
### Instruction
|
| 5 |
+
this model is trained on 50G chinese and english instruction datasets,the Moses25/Llama-3-8B-chat-32K is based on it with about 180K instruction dataset.
|
| 6 |
+
You can download Moses25/Instruct-dataset11M dataset to train you custom model.The github repo is [fintune-repo](https://github.com/moseshu/llama-recipes)
|
| 7 |
+
|
| 8 |
+
```
|
| 9 |
+
git clone https://github.com/moseshu/llama-recipes
|
| 10 |
+
cd llama-recipes/src && sh ft.sh
|
| 11 |
+
```
|