Update README.md
Browse files
README.md
CHANGED
|
@@ -15,6 +15,9 @@ tags:
|
|
| 15 |
- vision
|
| 16 |
---
|
| 17 |
|
|
|
|
|
|
|
|
|
|
| 18 |
# Finetune Llama 3.2, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!
|
| 19 |
|
| 20 |
We have a free Google Colab Tesla T4 notebook for Llama 3.2 Vision (11B) here: https://colab.research.google.com/drive/1j0N4XTY1zXXy7mPAhOC1_gMYZ2F2EBlk?usp=sharing
|
|
|
|
| 15 |
- vision
|
| 16 |
---
|
| 17 |
|
| 18 |
+
## ***Unsloth's [Dynamic 4-bit Quants](https://unsloth.ai/blog/dynamic-4bit) selectively avoid quantizing certain parameters, greatly improving accuracy while keeping VRAM usage similar to BnB 4-bit. See our full collection on [Hugging Face here.](https://huggingface.co/collections/unsloth/unsloth-4-bit-dynamic-quants-67503bb873f89e15276c44e7)***
|
| 19 |
+
<br>
|
| 20 |
+
|
| 21 |
# Finetune Llama 3.2, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!
|
| 22 |
|
| 23 |
We have a free Google Colab Tesla T4 notebook for Llama 3.2 Vision (11B) here: https://colab.research.google.com/drive/1j0N4XTY1zXXy7mPAhOC1_gMYZ2F2EBlk?usp=sharing
|