Update README.md
Browse files
README.md
CHANGED
|
@@ -6,7 +6,6 @@ language:
|
|
| 6 |
## Information
|
| 7 |
|
| 8 |
This is a Exl2 quantized version of [LLaMA2-13B-Tiefighter](https://huggingface.co/KoboldAI/LLaMA2-13B-Tiefighter)
|
| 9 |
-
The respository has a v1 appended for clarity's sake.
|
| 10 |
|
| 11 |
Please refer to the original creator for more information.
|
| 12 |
|
|
@@ -18,9 +17,11 @@ Calibration dataset: [wikitext](https://huggingface.co/datasets/wikitext/tree/re
|
|
| 18 |
- 4bpw: 4 bits per weight
|
| 19 |
- 5bpw: 5 bits per weight
|
| 20 |
- 6bpw: 6 bits per weight
|
|
|
|
| 21 |
|
| 22 |
## Notes
|
| 23 |
|
|
|
|
| 24 |
- Please ask for more bpws in the community tab if necessary.
|
| 25 |
|
| 26 |
## Donate?
|
|
|
|
| 6 |
## Information
|
| 7 |
|
| 8 |
This is a Exl2 quantized version of [LLaMA2-13B-Tiefighter](https://huggingface.co/KoboldAI/LLaMA2-13B-Tiefighter)
|
|
|
|
| 9 |
|
| 10 |
Please refer to the original creator for more information.
|
| 11 |
|
|
|
|
| 17 |
- 4bpw: 4 bits per weight
|
| 18 |
- 5bpw: 5 bits per weight
|
| 19 |
- 6bpw: 6 bits per weight
|
| 20 |
+
- 8bpw: 8 bits per weight
|
| 21 |
|
| 22 |
## Notes
|
| 23 |
|
| 24 |
+
- 6bpw is recommended for the best quality to vram usage ratio (assuming you have enough vram).
|
| 25 |
- Please ask for more bpws in the community tab if necessary.
|
| 26 |
|
| 27 |
## Donate?
|