Update README.md
Browse files
README.md
CHANGED
|
@@ -26,6 +26,8 @@ base_model: unsloth/llama-3-8b-bnb-4bit
|
|
| 26 |
|
| 27 |
- The mode usually tries to follow this format, it may mix it up a little but usually it almost always reflects in someway. Especially if you tell it to think step by step
|
| 28 |
|
|
|
|
|
|
|
| 29 |
- **Developed by:** cookinai
|
| 30 |
- **License:** apache-2.0
|
| 31 |
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
|
|
|
|
| 26 |
|
| 27 |
- The mode usually tries to follow this format, it may mix it up a little but usually it almost always reflects in someway. Especially if you tell it to think step by step
|
| 28 |
|
| 29 |
+
- Intrestingly enough, when finetuned on mistral 7b, I could not get the model CoT at all, with only one epoch llama 3 got it instantly
|
| 30 |
+
|
| 31 |
- **Developed by:** cookinai
|
| 32 |
- **License:** apache-2.0
|
| 33 |
- **Finetuned from model :** unsloth/llama-3-8b-bnb-4bit
|