Hugging Face's logo

unsloth
/
llama-2-7b-bnb-4bit

Text Generation
Transformers
Safetensors
English
llama
unsloth
llama2
llama-2
text-generation-inference
4-bit precision
bitsandbytes
Model card Files Community
danielhanchen commited on
Commit
704f7cb
·
1 Parent(s): cebece3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -1
README.md CHANGED
@@ -1,4 +1,9 @@
1
  ---
2
  license: llama2
3
  ---
4
- Will add a 4bit quantized upload once https://github.com/huggingface/transformers/pull/26037 gets merged.
 
 
 
 
 
 
1
  ---
2
  license: llama2
3
  ---
4
+
5
+ Directly quantized 4bit model with `bitsandbytes`.
6
+
7
+ Unsloth can finetune LLMs with QLoRA 2.2x faster and use 62% less memory!
8
+
9
+ We have a Google Colab Tesla T4 notebook for Llama 7b here: https://colab.research.google.com/drive/1lBzz5KeZJKXjvivbYvmGarix9Ao6Wxe5?usp=sharing