Upload folder using huggingface_hub
Browse files- README.md +8 -8
- mergekit_config.yml +3 -3
- model-00001-of-00001.safetensors +1 -1
README.md
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
---
|
| 2 |
base_model:
|
| 3 |
-
- mllm-dev/gpt2_f_experiment_2
|
| 4 |
-
- mllm-dev/gpt2_f_experiment_4
|
| 5 |
-
- mllm-dev/gpt2_f_experiment_3
|
| 6 |
- mllm-dev/gpt2_f_experiment_0
|
| 7 |
- mllm-dev/gpt2_f_experiment_1
|
|
|
|
|
|
|
|
|
|
| 8 |
library_name: transformers
|
| 9 |
tags:
|
| 10 |
- mergekit
|
|
@@ -23,10 +23,10 @@ This model was merged using the linear [DARE](https://arxiv.org/abs/2311.03099)
|
|
| 23 |
### Models Merged
|
| 24 |
|
| 25 |
The following models were included in the merge:
|
| 26 |
-
* [mllm-dev/
|
| 27 |
* [mllm-dev/gpt2_f_experiment_4](https://huggingface.co/mllm-dev/gpt2_f_experiment_4)
|
| 28 |
* [mllm-dev/gpt2_f_experiment_3](https://huggingface.co/mllm-dev/gpt2_f_experiment_3)
|
| 29 |
-
* [mllm-dev/
|
| 30 |
|
| 31 |
### Configuration
|
| 32 |
|
|
@@ -53,7 +53,7 @@ slices:
|
|
| 53 |
model:
|
| 54 |
path: mllm-dev/gpt2_f_experiment_1
|
| 55 |
parameters:
|
| 56 |
-
weight: 1.
|
| 57 |
- layer_range: [0, 12]
|
| 58 |
model:
|
| 59 |
model:
|
|
@@ -65,11 +65,11 @@ slices:
|
|
| 65 |
model:
|
| 66 |
path: mllm-dev/gpt2_f_experiment_3
|
| 67 |
parameters:
|
| 68 |
-
weight: 0.
|
| 69 |
- layer_range: [0, 12]
|
| 70 |
model:
|
| 71 |
model:
|
| 72 |
path: mllm-dev/gpt2_f_experiment_4
|
| 73 |
parameters:
|
| 74 |
-
weight: 0.
|
| 75 |
```
|
|
|
|
| 1 |
---
|
| 2 |
base_model:
|
|
|
|
|
|
|
|
|
|
| 3 |
- mllm-dev/gpt2_f_experiment_0
|
| 4 |
- mllm-dev/gpt2_f_experiment_1
|
| 5 |
+
- mllm-dev/gpt2_f_experiment_4
|
| 6 |
+
- mllm-dev/gpt2_f_experiment_3
|
| 7 |
+
- mllm-dev/gpt2_f_experiment_2
|
| 8 |
library_name: transformers
|
| 9 |
tags:
|
| 10 |
- mergekit
|
|
|
|
| 23 |
### Models Merged
|
| 24 |
|
| 25 |
The following models were included in the merge:
|
| 26 |
+
* [mllm-dev/gpt2_f_experiment_1](https://huggingface.co/mllm-dev/gpt2_f_experiment_1)
|
| 27 |
* [mllm-dev/gpt2_f_experiment_4](https://huggingface.co/mllm-dev/gpt2_f_experiment_4)
|
| 28 |
* [mllm-dev/gpt2_f_experiment_3](https://huggingface.co/mllm-dev/gpt2_f_experiment_3)
|
| 29 |
+
* [mllm-dev/gpt2_f_experiment_2](https://huggingface.co/mllm-dev/gpt2_f_experiment_2)
|
| 30 |
|
| 31 |
### Configuration
|
| 32 |
|
|
|
|
| 53 |
model:
|
| 54 |
path: mllm-dev/gpt2_f_experiment_1
|
| 55 |
parameters:
|
| 56 |
+
weight: 1.3
|
| 57 |
- layer_range: [0, 12]
|
| 58 |
model:
|
| 59 |
model:
|
|
|
|
| 65 |
model:
|
| 66 |
path: mllm-dev/gpt2_f_experiment_3
|
| 67 |
parameters:
|
| 68 |
+
weight: 0.2
|
| 69 |
- layer_range: [0, 12]
|
| 70 |
model:
|
| 71 |
model:
|
| 72 |
path: mllm-dev/gpt2_f_experiment_4
|
| 73 |
parameters:
|
| 74 |
+
weight: 0.2
|
| 75 |
```
|
mergekit_config.yml
CHANGED
|
@@ -18,7 +18,7 @@ slices:
|
|
| 18 |
model:
|
| 19 |
path: mllm-dev/gpt2_f_experiment_1
|
| 20 |
parameters:
|
| 21 |
-
weight: 1.
|
| 22 |
- layer_range: [0, 12]
|
| 23 |
model:
|
| 24 |
model:
|
|
@@ -30,10 +30,10 @@ slices:
|
|
| 30 |
model:
|
| 31 |
path: mllm-dev/gpt2_f_experiment_3
|
| 32 |
parameters:
|
| 33 |
-
weight: 0.
|
| 34 |
- layer_range: [0, 12]
|
| 35 |
model:
|
| 36 |
model:
|
| 37 |
path: mllm-dev/gpt2_f_experiment_4
|
| 38 |
parameters:
|
| 39 |
-
weight: 0.
|
|
|
|
| 18 |
model:
|
| 19 |
path: mllm-dev/gpt2_f_experiment_1
|
| 20 |
parameters:
|
| 21 |
+
weight: 1.3
|
| 22 |
- layer_range: [0, 12]
|
| 23 |
model:
|
| 24 |
model:
|
|
|
|
| 30 |
model:
|
| 31 |
path: mllm-dev/gpt2_f_experiment_3
|
| 32 |
parameters:
|
| 33 |
+
weight: 0.2
|
| 34 |
- layer_range: [0, 12]
|
| 35 |
model:
|
| 36 |
model:
|
| 37 |
path: mllm-dev/gpt2_f_experiment_4
|
| 38 |
parameters:
|
| 39 |
+
weight: 0.2
|
model-00001-of-00001.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 248902264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0985f810e843ad6e3cbeed498215211277ab07182b770c5eda9db14011f2c24a
|
| 3 |
size 248902264
|