justheuristic
commited on
Commit
•
c171514
1
Parent(s):
f13e222
typo
Browse files
README.md
CHANGED
@@ -12,7 +12,7 @@ tags:
|
|
12 |
An official quantization of [meta-llama/Llama-2-7b](https://huggingface.co/meta-llama/Llama-2-7b) using [PV-Tuning](https://arxiv.org/abs/2405.14852) on top of [AQLM](https://arxiv.org/abs/2401.06118).
|
13 |
|
14 |
|
15 |
-
For this quantization, we used 2
|
16 |
|
17 |
|
18 |
| Model | AQLM scheme | WikiText 2 PPL | Model size, Gb | Hub link |
|
|
|
12 |
An official quantization of [meta-llama/Llama-2-7b](https://huggingface.co/meta-llama/Llama-2-7b) using [PV-Tuning](https://arxiv.org/abs/2405.14852) on top of [AQLM](https://arxiv.org/abs/2401.06118).
|
13 |
|
14 |
|
15 |
+
For this quantization, we used 2 codebooks of 8 bits each for groups of 8 weights.
|
16 |
|
17 |
|
18 |
| Model | AQLM scheme | WikiText 2 PPL | Model size, Gb | Hub link |
|