Commit
•
eb2b602
1
Parent(s):
b0705dc
Update README.md
Browse files
README.md
CHANGED
|
@@ -13,8 +13,6 @@ tags:
|
|
| 13 |
|
| 14 |
# Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!
|
| 15 |
|
| 16 |
-
Directly quantized 4bit model with `bitsandbytes`.
|
| 17 |
-
|
| 18 |
We have a Google Colab Tesla T4 notebook for Llama-3 8b here: https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing
|
| 19 |
|
| 20 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/u54VK8m8tk)
|
|
|
|
| 13 |
|
| 14 |
# Finetune Mistral, Gemma, Llama 2-5x faster with 70% less memory via Unsloth!
|
| 15 |
|
|
|
|
|
|
|
| 16 |
We have a Google Colab Tesla T4 notebook for Llama-3 8b here: https://colab.research.google.com/drive/135ced7oHytdxu3N2DNe1Z0kqjyYIkDXp?usp=sharing
|
| 17 |
|
| 18 |
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/Discord%20button.png" width="200"/>](https://discord.gg/u54VK8m8tk)
|