Ex_y
commited on
Commit
•
3fe73e3
1
Parent(s):
a6b0a0e
Update README.md
Browse files
README.md
CHANGED
|
@@ -7,6 +7,10 @@ quantized_by: Ex_y
|
|
| 7 |
base_model_relation: quantized
|
| 8 |
---
|
| 9 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
# Join our Discord! https://discord.gg/Nbv9pQ88Xb
|
| 11 |
|
| 12 |
### Works on [Kobold 1.74](https://github.com/LostRuins/koboldcpp/releases/tag/v1.74)!
|
|
|
|
| 7 |
base_model_relation: quantized
|
| 8 |
---
|
| 9 |
|
| 10 |
+
EXL2 quants of [TheDrummer/Hubble-4B-v1](https://huggingface.co/TheDrummer/Hubble-4B-v1)
|
| 11 |
+
|
| 12 |
+
Default parameter. 6.5bpw and 8.0 bpw uses 8 bit lm_head layer, while 4.25bpw and 5.0bpw uses 6 bit lm_head layer.
|
| 13 |
+
|
| 14 |
# Join our Discord! https://discord.gg/Nbv9pQ88Xb
|
| 15 |
|
| 16 |
### Works on [Kobold 1.74](https://github.com/LostRuins/koboldcpp/releases/tag/v1.74)!
|