automerger
commited on
Upload folder using huggingface_hub
Browse files- README.md +18 -12
- config.json +1 -1
- mergekit_config.yml +13 -9
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
README.md
CHANGED
@@ -1,33 +1,39 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
tags:
|
4 |
- merge
|
5 |
- mergekit
|
6 |
- lazymergekit
|
7 |
- automerger
|
8 |
base_model:
|
9 |
-
- rwitz/experiment26-truthy-iter-
|
|
|
10 |
---
|
11 |
|
12 |
# Experiment26Experiment26-7B
|
13 |
|
14 |
Experiment26Experiment26-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration.
|
15 |
-
* [rwitz/experiment26-truthy-iter-
|
|
|
16 |
|
17 |
## 🧩 Configuration
|
18 |
|
19 |
```yaml
|
20 |
-
|
21 |
-
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
merge_method: dare_ties
|
28 |
base_model: rwitz/experiment26-truthy-iter-0
|
29 |
parameters:
|
30 |
-
|
|
|
|
|
|
|
|
|
|
|
31 |
dtype: bfloat16
|
32 |
random_seed: 0
|
33 |
```
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
tags:
|
4 |
- merge
|
5 |
- mergekit
|
6 |
- lazymergekit
|
7 |
- automerger
|
8 |
base_model:
|
9 |
+
- rwitz/experiment26-truthy-iter-0
|
10 |
+
- yam-peleg/Experiment26-7B
|
11 |
---
|
12 |
|
13 |
# Experiment26Experiment26-7B
|
14 |
|
15 |
Experiment26Experiment26-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration.
|
16 |
+
* [rwitz/experiment26-truthy-iter-0](https://huggingface.co/rwitz/experiment26-truthy-iter-0)
|
17 |
+
* [yam-peleg/Experiment26-7B](https://huggingface.co/yam-peleg/Experiment26-7B)
|
18 |
|
19 |
## 🧩 Configuration
|
20 |
|
21 |
```yaml
|
22 |
+
slices:
|
23 |
+
- sources:
|
24 |
+
- model: rwitz/experiment26-truthy-iter-0
|
25 |
+
layer_range: [0, 32]
|
26 |
+
- model: yam-peleg/Experiment26-7B
|
27 |
+
layer_range: [0, 32]
|
28 |
+
merge_method: slerp
|
|
|
29 |
base_model: rwitz/experiment26-truthy-iter-0
|
30 |
parameters:
|
31 |
+
t:
|
32 |
+
- filter: self_attn
|
33 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
34 |
+
- filter: mlp
|
35 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
36 |
+
- value: 0.5
|
37 |
dtype: bfloat16
|
38 |
random_seed: 0
|
39 |
```
|
config.json
CHANGED
@@ -20,7 +20,7 @@
|
|
20 |
"sliding_window": 4096,
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
-
"transformers_version": "4.
|
24 |
"use_cache": true,
|
25 |
"vocab_size": 32000
|
26 |
}
|
|
|
20 |
"sliding_window": 4096,
|
21 |
"tie_word_embeddings": false,
|
22 |
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.39.0",
|
24 |
"use_cache": true,
|
25 |
"vocab_size": 32000
|
26 |
}
|
mergekit_config.yml
CHANGED
@@ -1,15 +1,19 @@
|
|
1 |
|
2 |
-
|
3 |
-
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
merge_method: dare_ties
|
10 |
base_model: rwitz/experiment26-truthy-iter-0
|
11 |
parameters:
|
12 |
-
|
|
|
|
|
|
|
|
|
|
|
13 |
dtype: bfloat16
|
14 |
random_seed: 0
|
15 |
|
|
|
1 |
|
2 |
+
slices:
|
3 |
+
- sources:
|
4 |
+
- model: rwitz/experiment26-truthy-iter-0
|
5 |
+
layer_range: [0, 32]
|
6 |
+
- model: yam-peleg/Experiment26-7B
|
7 |
+
layer_range: [0, 32]
|
8 |
+
merge_method: slerp
|
|
|
9 |
base_model: rwitz/experiment26-truthy-iter-0
|
10 |
parameters:
|
11 |
+
t:
|
12 |
+
- filter: self_attn
|
13 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
14 |
+
- filter: mlp
|
15 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
16 |
+
- value: 0.5
|
17 |
dtype: bfloat16
|
18 |
random_seed: 0
|
19 |
|
model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9942981696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c2040230cbe78f2d058b7866da799b07a846eb7bb8ae405b4a29330bf44e587
|
3 |
size 9942981696
|
model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4540516344
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:135770e8e6aed94e95184c999e8e081160cf9d0f551353d8565cc510ede4e382
|
3 |
size 4540516344
|