Commit
•
f77b4a0
1
Parent(s):
6a59887
Update README.md
Browse files
README.md
CHANGED
|
@@ -12,6 +12,16 @@ tags:
|
|
| 12 |
|
| 13 |
|
| 14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
Merge using the brand new NuSLERP method. Fresh out of the oven. Performance not guaranteed.
|
| 16 |
|
| 17 |
Uses the slightly-unstable EVA and two other finetunes I found. I also turned on both the NuSLERP exclusive mergekit options for fun.
|
|
|
|
| 12 |
|
| 13 |
|
| 14 |
|
| 15 |
+
## EDIT: MAY NOT WORK FOR GGUFs
|
| 16 |
+
|
| 17 |
+
I don't know if its an issue with me or the model, but I can't seem to make quants of this model. I consistently get
|
| 18 |
+
`llama_model_quantize: failed to quantize: tensor 'blk.24.attn_norm.weight' has invalid data`. My whole setup has so
|
| 19 |
+
many stds and idiosynchasies that it may just be my system, but I tried redoing the whole thing and same stuff happened.
|
| 20 |
+
At this point it may be an issue with the NuSLERP method or one of the models I'm using in the merge. Not sure gang. I will
|
| 21 |
+
try swapping out a model or two in the merge and trying again to upload as a v2.0.
|
| 22 |
+
|
| 23 |
+
# info
|
| 24 |
+
|
| 25 |
Merge using the brand new NuSLERP method. Fresh out of the oven. Performance not guaranteed.
|
| 26 |
|
| 27 |
Uses the slightly-unstable EVA and two other finetunes I found. I also turned on both the NuSLERP exclusive mergekit options for fun.
|