Update README.md
Browse files
README.md
CHANGED
@@ -2,7 +2,7 @@ EXL2 quants of [Sheared-LLaMA-1.3B](https://huggingface.co/princeton-nlp/Sheared
|
|
2 |
This is a pruned and further pre-trained version of Llama2-7B
|
3 |
|
4 |
[2.50 bits per weight](https://huggingface.co/turboderp/Sheared-Llama2-1.3B-exl2/tree/2.5bpw)
|
5 |
-
[2.70 bits per weight](https://huggingface.co/turboderp/Sheared-Llama2-1.3B-exl2/tree/2.
|
6 |
[3.00 bits per weight](https://huggingface.co/turboderp/Sheared-Llama2-1.3B-exl2/tree/3.0bpw)
|
7 |
[3.50 bits per weight](https://huggingface.co/turboderp/Sheared-Llama2-1.3B-exl2/tree/3.5bpw)
|
8 |
[4.00 bits per weight](https://huggingface.co/turboderp/Sheared-Llama2-1.3B-exl2/tree/4.0bpw)
|
|
|
2 |
This is a pruned and further pre-trained version of Llama2-7B
|
3 |
|
4 |
[2.50 bits per weight](https://huggingface.co/turboderp/Sheared-Llama2-1.3B-exl2/tree/2.5bpw)
|
5 |
+
[2.70 bits per weight](https://huggingface.co/turboderp/Sheared-Llama2-1.3B-exl2/tree/2.7bpw)
|
6 |
[3.00 bits per weight](https://huggingface.co/turboderp/Sheared-Llama2-1.3B-exl2/tree/3.0bpw)
|
7 |
[3.50 bits per weight](https://huggingface.co/turboderp/Sheared-Llama2-1.3B-exl2/tree/3.5bpw)
|
8 |
[4.00 bits per weight](https://huggingface.co/turboderp/Sheared-Llama2-1.3B-exl2/tree/4.0bpw)
|