Update README.md
Browse files
README.md
CHANGED
|
@@ -12,8 +12,9 @@ tags:
|
|
| 12 |
- unsloth
|
| 13 |
- transformers
|
| 14 |
---
|
| 15 |
-
|
| 16 |
## ***See [our collection](https://huggingface.co/collections/unsloth/llama-32-66f46afde4ca573864321a22) for all versions of Llama 3.2 including GGUF, 4-bit and original 16-bit formats.***
|
|
|
|
|
|
|
| 17 |
|
| 18 |
# Finetune Llama 3.2, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!
|
| 19 |
|
|
|
|
| 12 |
- unsloth
|
| 13 |
- transformers
|
| 14 |
---
|
|
|
|
| 15 |
## ***See [our collection](https://huggingface.co/collections/unsloth/llama-32-66f46afde4ca573864321a22) for all versions of Llama 3.2 including GGUF, 4-bit and original 16-bit formats.***
|
| 16 |
+
*Dynamic 4-bit: Unsloth's [Dynamic 4-bit Quants](https://unsloth.ai/blog/dynamic-4bit) selectively avoids quantizing certain parameters, greatly increase accuracy than standard 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)*
|
| 17 |
+
<br>
|
| 18 |
|
| 19 |
# Finetune Llama 3.2, Gemma 2, Mistral 2-5x faster with 70% less memory via Unsloth!
|
| 20 |
|