automerger
commited on
Commit
•
bc58485
1
Parent(s):
7e2cf6b
Upload folder using huggingface_hub
Browse files- README.md +11 -17
- config.json +1 -1
- mergekit_config.yml +10 -14
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
README.md
CHANGED
@@ -1,39 +1,33 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
tags:
|
4 |
- merge
|
5 |
- mergekit
|
6 |
- lazymergekit
|
7 |
- automerger
|
8 |
base_model:
|
9 |
-
- rwitz/experiment26-truthy-iter-1
|
10 |
- chihoonlee10/T3Q-Mistral-Orca-Math-DPO
|
11 |
---
|
12 |
|
13 |
# Experiment26T3q-7B
|
14 |
|
15 |
Experiment26T3q-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration.
|
16 |
-
* [rwitz/experiment26-truthy-iter-1](https://huggingface.co/rwitz/experiment26-truthy-iter-1)
|
17 |
* [chihoonlee10/T3Q-Mistral-Orca-Math-DPO](https://huggingface.co/chihoonlee10/T3Q-Mistral-Orca-Math-DPO)
|
18 |
|
19 |
## 🧩 Configuration
|
20 |
|
21 |
```yaml
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
29 |
-
|
|
|
30 |
parameters:
|
31 |
-
|
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 |
```
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
tags:
|
4 |
- merge
|
5 |
- mergekit
|
6 |
- lazymergekit
|
7 |
- automerger
|
8 |
base_model:
|
|
|
9 |
- chihoonlee10/T3Q-Mistral-Orca-Math-DPO
|
10 |
---
|
11 |
|
12 |
# Experiment26T3q-7B
|
13 |
|
14 |
Experiment26T3q-7B is an automated merge created by [Maxime Labonne](https://huggingface.co/mlabonne) using the following configuration.
|
|
|
15 |
* [chihoonlee10/T3Q-Mistral-Orca-Math-DPO](https://huggingface.co/chihoonlee10/T3Q-Mistral-Orca-Math-DPO)
|
16 |
|
17 |
## 🧩 Configuration
|
18 |
|
19 |
```yaml
|
20 |
+
models:
|
21 |
+
- model: yam-peleg/Experiment26-7B
|
22 |
+
# No parameters necessary for base model
|
23 |
+
- model: chihoonlee10/T3Q-Mistral-Orca-Math-DPO
|
24 |
+
parameters:
|
25 |
+
density: 0.53
|
26 |
+
weight: 0.6
|
27 |
+
merge_method: dare_ties
|
28 |
+
base_model: yam-peleg/Experiment26-7B
|
29 |
parameters:
|
30 |
+
int8_mask: true
|
|
|
|
|
|
|
|
|
|
|
31 |
dtype: bfloat16
|
32 |
random_seed: 0
|
33 |
```
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "yam-peleg/Experiment26-7B",
|
3 |
"architectures": [
|
4 |
"MistralForCausalLM"
|
5 |
],
|
mergekit_config.yml
CHANGED
@@ -1,19 +1,15 @@
|
|
1 |
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
|
|
10 |
parameters:
|
11 |
-
|
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 |
|
|
|
1 |
|
2 |
+
models:
|
3 |
+
- model: yam-peleg/Experiment26-7B
|
4 |
+
# No parameters necessary for base model
|
5 |
+
- model: chihoonlee10/T3Q-Mistral-Orca-Math-DPO
|
6 |
+
parameters:
|
7 |
+
density: 0.53
|
8 |
+
weight: 0.6
|
9 |
+
merge_method: dare_ties
|
10 |
+
base_model: yam-peleg/Experiment26-7B
|
11 |
parameters:
|
12 |
+
int8_mask: true
|
|
|
|
|
|
|
|
|
|
|
13 |
dtype: bfloat16
|
14 |
random_seed: 0
|
15 |
|
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 sha256:25bf360183bc037ce5a8d0f093778cb0c05706d1e9429b2e65294f3a651a00d0
|
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 sha256:9478bb0f8c1e2836a322970e8cd497d8914259e6a06b030e7b0860b8e2fd2c44
|
3 |
size 4540516344
|