Upload folder using huggingface_hub
Browse files- README.md +5 -5
- mergekit_config.yml +1 -1
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
README.md
CHANGED
@@ -1,10 +1,10 @@
|
|
1 |
---
|
2 |
base_model:
|
3 |
-
- chuanli11/Llama-3.2-3B-Instruct-uncensored
|
4 |
-
- meta-llama/Llama-3.2-3B
|
5 |
- bunnycore/Llama-3.2-3B-ProdigyPlusPlus
|
6 |
- huihui-ai/Llama-3.2-3B-Instruct-abliterated
|
|
|
7 |
- meta-llama/Llama-3.2-3B-Instruct
|
|
|
8 |
library_name: transformers
|
9 |
tags:
|
10 |
- mergekit
|
@@ -18,15 +18,15 @@ This is a merge of pre-trained language models created using [mergekit](https://
|
|
18 |
## Merge Details
|
19 |
### Merge Method
|
20 |
|
21 |
-
This model was merged using the [
|
22 |
|
23 |
### Models Merged
|
24 |
|
25 |
The following models were included in the merge:
|
26 |
-
* [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B)
|
27 |
* [bunnycore/Llama-3.2-3B-ProdigyPlusPlus](https://huggingface.co/bunnycore/Llama-3.2-3B-ProdigyPlusPlus)
|
28 |
* [huihui-ai/Llama-3.2-3B-Instruct-abliterated](https://huggingface.co/huihui-ai/Llama-3.2-3B-Instruct-abliterated)
|
29 |
* [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)
|
|
|
30 |
|
31 |
### Configuration
|
32 |
|
@@ -38,7 +38,7 @@ base_model:
|
|
38 |
layer_range:
|
39 |
- 0
|
40 |
- 28
|
41 |
-
merge_method:
|
42 |
merge_method_sequence:
|
43 |
- dare_ties
|
44 |
- ties
|
|
|
1 |
---
|
2 |
base_model:
|
|
|
|
|
3 |
- bunnycore/Llama-3.2-3B-ProdigyPlusPlus
|
4 |
- huihui-ai/Llama-3.2-3B-Instruct-abliterated
|
5 |
+
- chuanli11/Llama-3.2-3B-Instruct-uncensored
|
6 |
- meta-llama/Llama-3.2-3B-Instruct
|
7 |
+
- meta-llama/Llama-3.2-3B
|
8 |
library_name: transformers
|
9 |
tags:
|
10 |
- mergekit
|
|
|
18 |
## Merge Details
|
19 |
### Merge Method
|
20 |
|
21 |
+
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [chuanli11/Llama-3.2-3B-Instruct-uncensored](https://huggingface.co/chuanli11/Llama-3.2-3B-Instruct-uncensored) as a base.
|
22 |
|
23 |
### Models Merged
|
24 |
|
25 |
The following models were included in the merge:
|
|
|
26 |
* [bunnycore/Llama-3.2-3B-ProdigyPlusPlus](https://huggingface.co/bunnycore/Llama-3.2-3B-ProdigyPlusPlus)
|
27 |
* [huihui-ai/Llama-3.2-3B-Instruct-abliterated](https://huggingface.co/huihui-ai/Llama-3.2-3B-Instruct-abliterated)
|
28 |
* [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)
|
29 |
+
* [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B)
|
30 |
|
31 |
### Configuration
|
32 |
|
|
|
38 |
layer_range:
|
39 |
- 0
|
40 |
- 28
|
41 |
+
merge_method: ties
|
42 |
merge_method_sequence:
|
43 |
- dare_ties
|
44 |
- ties
|
mergekit_config.yml
CHANGED
@@ -3,7 +3,7 @@ base_model:
|
|
3 |
layer_range:
|
4 |
- 0
|
5 |
- 28
|
6 |
-
merge_method:
|
7 |
merge_method_sequence:
|
8 |
- dare_ties
|
9 |
- ties
|
|
|
3 |
layer_range:
|
4 |
- 0
|
5 |
- 28
|
6 |
+
merge_method: ties
|
7 |
merge_method_sequence:
|
8 |
- dare_ties
|
9 |
- ties
|
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4998794944
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28f7de1dd4d1c949758eb83255f3bfdbae8d108cef7c956d784822f2e53671f4
|
3 |
size 4998794944
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2214739072
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3b20e109c5d1a0f6c42f1b2d003432b4687bc2cd0844225e13d2436e29af335
|
3 |
size 2214739072
|