sandmanbuzz
commited on
Commit
•
b0cc528
1
Parent(s):
115e05d
Update README.md
Browse files
README.md
CHANGED
@@ -8,6 +8,8 @@ tags:
|
|
8 |
---
|
9 |
# Air-Striker-Mixtral-8x7B-ZLoss-Instruct
|
10 |
|
|
|
|
|
11 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
12 |
|
13 |
## Merge Details
|
@@ -19,7 +21,7 @@ This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge
|
|
19 |
|
20 |
The following models were included in the merge:
|
21 |
* [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)
|
22 |
-
*
|
23 |
|
24 |
### Configuration
|
25 |
|
@@ -30,7 +32,7 @@ models:
|
|
30 |
- model: mistralai/Mixtral-8x7B-Instruct-v0.1
|
31 |
parameters:
|
32 |
weight: 0.5
|
33 |
-
- model:
|
34 |
parameters:
|
35 |
weight: 0.5
|
36 |
merge_method: linear
|
|
|
8 |
---
|
9 |
# Air-Striker-Mixtral-8x7B-ZLoss-Instruct
|
10 |
|
11 |
+
So, bro literally posts nothing but exl2s of this model, and it's like, am I some kind of caveman? What am I gonna do with an exl2? Take a picture of it and send it to my mom? So we re-made it from the ground up using the [lora](https://huggingface.co/LoneStriker/Air-Striker-Mixtral-8x7B-ZLoss-LoRA), since at least dude's got that posted.
|
12 |
+
|
13 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
14 |
|
15 |
## Merge Details
|
|
|
21 |
|
22 |
The following models were included in the merge:
|
23 |
* [mistralai/Mixtral-8x7B-Instruct-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-Instruct-v0.1)
|
24 |
+
* [sandmanbuzz/Air-Striker-Mixtral-8x7B-ZLoss](https://huggingface.co/sandmanbuzz/Air-Striker-Mixtral-8x7B-ZLoss)
|
25 |
|
26 |
### Configuration
|
27 |
|
|
|
32 |
- model: mistralai/Mixtral-8x7B-Instruct-v0.1
|
33 |
parameters:
|
34 |
weight: 0.5
|
35 |
+
- model: sandmanbuzz/Air-Striker-Mixtral-8x7B-ZLoss
|
36 |
parameters:
|
37 |
weight: 0.5
|
38 |
merge_method: linear
|