Update README.md
Browse files
README.md
CHANGED
|
@@ -9,7 +9,7 @@ tags:
|
|
| 9 |
- not-for-all-audiences
|
| 10 |
- nsfw
|
| 11 |
---
|
| 12 |
-
# IceCaffeLatteRP-7b
|
| 13 |
|
| 14 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 15 |
|
|
@@ -21,7 +21,7 @@ This model was merged using the SLERP merge method.
|
|
| 21 |
### Models Merged
|
| 22 |
|
| 23 |
The following models were included in the merge:
|
| 24 |
-
* IceLatteRP
|
| 25 |
* IceMochaccinoRP-7b
|
| 26 |
|
| 27 |
### Configuration
|
|
@@ -33,11 +33,11 @@ slices:
|
|
| 33 |
- sources:
|
| 34 |
- model: IceMochaccinoRP-7b
|
| 35 |
layer_range: [0, 32]
|
| 36 |
-
- model: IceLatteRP
|
| 37 |
layer_range: [0, 32]
|
| 38 |
|
| 39 |
merge_method: slerp
|
| 40 |
-
base_model: IceLatteRP
|
| 41 |
parameters:
|
| 42 |
t:
|
| 43 |
- filter: self_attn
|
|
|
|
| 9 |
- not-for-all-audiences
|
| 10 |
- nsfw
|
| 11 |
---
|
| 12 |
+
# IceCaffeLatteRP-7b-4.2bpw-exl2
|
| 13 |
|
| 14 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 15 |
|
|
|
|
| 21 |
### Models Merged
|
| 22 |
|
| 23 |
The following models were included in the merge:
|
| 24 |
+
* IceLatteRP-7b
|
| 25 |
* IceMochaccinoRP-7b
|
| 26 |
|
| 27 |
### Configuration
|
|
|
|
| 33 |
- sources:
|
| 34 |
- model: IceMochaccinoRP-7b
|
| 35 |
layer_range: [0, 32]
|
| 36 |
+
- model: IceLatteRP-7b
|
| 37 |
layer_range: [0, 32]
|
| 38 |
|
| 39 |
merge_method: slerp
|
| 40 |
+
base_model: IceLatteRP-7b
|
| 41 |
parameters:
|
| 42 |
t:
|
| 43 |
- filter: self_attn
|