shimmyshimmer commited on
Commit
ceb474a
1 Parent(s): d415357

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -14,6 +14,9 @@ tags:
14
  - vision
15
  ---
16
 
 
 
 
17
  # Finetune Llama 3.2, Qwen 2.5, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!
18
 
19
  We have a free Google Colab Tesla T4 notebook for Qwen2-VL (7B) here: https://colab.research.google.com/drive/1whHb54GNZMrNxIsi2wm2EY_-Pvo2QyKh?usp=sharing
 
14
  - vision
15
  ---
16
 
17
+ ### ***Unsloth's [Dynamic 4-bit Quants](https://unsloth.ai/blog/dynamic-4bit) selectively avoids quantizing certain parameters, greatly improving accuracy while keeping VRAM usage similar to BnB 4-bit.<br>See our full collection of Unsloth quants on [Hugging Face here.](https://huggingface.co/collections/unsloth/unsloth-4-bit-dynamic-quants-67503bb873f89e15276c44e7)***
18
+ <br>
19
+
20
  # Finetune Llama 3.2, Qwen 2.5, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!
21
 
22
  We have a free Google Colab Tesla T4 notebook for Qwen2-VL (7B) here: https://colab.research.google.com/drive/1whHb54GNZMrNxIsi2wm2EY_-Pvo2QyKh?usp=sharing