Add 8.0 link
Browse files
README.md
CHANGED
|
@@ -41,6 +41,8 @@ Conversion was done using VMWareOpenInstruct.parquet as calibration dataset.
|
|
| 41 |
Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.
|
| 42 |
|
| 43 |
Original model: https://huggingface.co/jondurbin/bagel-dpo-7b-v0.1
|
|
|
|
|
|
|
| 44 |
|
| 45 |
## Download instructions
|
| 46 |
|
|
|
|
| 41 |
Default arguments used except when the bits per weight is above 6.0, at that point the lm_head layer is quantized at 8 bits per weight instead of the default 6.
|
| 42 |
|
| 43 |
Original model: https://huggingface.co/jondurbin/bagel-dpo-7b-v0.1
|
| 44 |
+
|
| 45 |
+
<a href="https://huggingface.co/bartowski/bagel-dpo-7b-v0.1-exl2/tree/8_0">8.0 bits per weight</a>
|
| 46 |
|
| 47 |
## Download instructions
|
| 48 |
|