Commit
•
931fb5f
1
Parent(s):
858395d
Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
---
|
| 4 |
+
Directly quantized 4bit model with `bitsandbytes`.
|
| 5 |
+
|
| 6 |
+
Unsloth can finetune LLMs with QLoRA 2.2x faster and use 62% less memory!
|
| 7 |
+
|
| 8 |
+
We have a Google Colab Tesla T4 notebook for TinyLlama with 4096 max sequence length RoPE Scaling here: https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing
|