Upload folder using huggingface_hub
Browse files- README.md +11 -11
- mergekit_config.yml +6 -6
- model-00001-of-00001.safetensors +1 -1
README.md
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
---
|
2 |
base_model:
|
3 |
-
- mllm-dev/gpt2_f_experiment_0_1000
|
4 |
-
- mllm-dev/gpt2_f_experiment_4_1000
|
5 |
-
- mllm-dev/gpt2_f_experiment_1_1000
|
6 |
- mllm-dev/gpt2_f_experiment_2_1000
|
|
|
|
|
|
|
7 |
- mllm-dev/gpt2_f_experiment_3_1000
|
8 |
library_name: transformers
|
9 |
tags:
|
@@ -23,9 +23,9 @@ This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](
|
|
23 |
### Models Merged
|
24 |
|
25 |
The following models were included in the merge:
|
26 |
-
* [mllm-dev/gpt2_f_experiment_4_1000](https://huggingface.co/mllm-dev/gpt2_f_experiment_4_1000)
|
27 |
-
* [mllm-dev/gpt2_f_experiment_1_1000](https://huggingface.co/mllm-dev/gpt2_f_experiment_1_1000)
|
28 |
* [mllm-dev/gpt2_f_experiment_2_1000](https://huggingface.co/mllm-dev/gpt2_f_experiment_2_1000)
|
|
|
|
|
29 |
* [mllm-dev/gpt2_f_experiment_3_1000](https://huggingface.co/mllm-dev/gpt2_f_experiment_3_1000)
|
30 |
|
31 |
### Configuration
|
@@ -52,26 +52,26 @@ slices:
|
|
52 |
path: mllm-dev/gpt2_f_experiment_1_1000
|
53 |
parameters:
|
54 |
density: 0.8
|
55 |
-
weight: 0.
|
56 |
- layer_range: [0, 12]
|
57 |
model:
|
58 |
model:
|
59 |
path: mllm-dev/gpt2_f_experiment_2_1000
|
60 |
parameters:
|
61 |
-
density: 0.
|
62 |
-
weight: 0.
|
63 |
- layer_range: [0, 12]
|
64 |
model:
|
65 |
model:
|
66 |
path: mllm-dev/gpt2_f_experiment_3_1000
|
67 |
parameters:
|
68 |
-
density: 0.
|
69 |
-
weight: 0.
|
70 |
- layer_range: [0, 12]
|
71 |
model:
|
72 |
model:
|
73 |
path: mllm-dev/gpt2_f_experiment_4_1000
|
74 |
parameters:
|
75 |
density: 0.8
|
76 |
-
weight: 0.
|
77 |
```
|
|
|
1 |
---
|
2 |
base_model:
|
|
|
|
|
|
|
3 |
- mllm-dev/gpt2_f_experiment_2_1000
|
4 |
+
- mllm-dev/gpt2_f_experiment_1_1000
|
5 |
+
- mllm-dev/gpt2_f_experiment_4_1000
|
6 |
+
- mllm-dev/gpt2_f_experiment_0_1000
|
7 |
- mllm-dev/gpt2_f_experiment_3_1000
|
8 |
library_name: transformers
|
9 |
tags:
|
|
|
23 |
### Models Merged
|
24 |
|
25 |
The following models were included in the merge:
|
|
|
|
|
26 |
* [mllm-dev/gpt2_f_experiment_2_1000](https://huggingface.co/mllm-dev/gpt2_f_experiment_2_1000)
|
27 |
+
* [mllm-dev/gpt2_f_experiment_1_1000](https://huggingface.co/mllm-dev/gpt2_f_experiment_1_1000)
|
28 |
+
* [mllm-dev/gpt2_f_experiment_4_1000](https://huggingface.co/mllm-dev/gpt2_f_experiment_4_1000)
|
29 |
* [mllm-dev/gpt2_f_experiment_3_1000](https://huggingface.co/mllm-dev/gpt2_f_experiment_3_1000)
|
30 |
|
31 |
### Configuration
|
|
|
52 |
path: mllm-dev/gpt2_f_experiment_1_1000
|
53 |
parameters:
|
54 |
density: 0.8
|
55 |
+
weight: 0.3
|
56 |
- layer_range: [0, 12]
|
57 |
model:
|
58 |
model:
|
59 |
path: mllm-dev/gpt2_f_experiment_2_1000
|
60 |
parameters:
|
61 |
+
density: 0.6
|
62 |
+
weight: 0.1
|
63 |
- layer_range: [0, 12]
|
64 |
model:
|
65 |
model:
|
66 |
path: mllm-dev/gpt2_f_experiment_3_1000
|
67 |
parameters:
|
68 |
+
density: 0.6
|
69 |
+
weight: 0.1
|
70 |
- layer_range: [0, 12]
|
71 |
model:
|
72 |
model:
|
73 |
path: mllm-dev/gpt2_f_experiment_4_1000
|
74 |
parameters:
|
75 |
density: 0.8
|
76 |
+
weight: 0.3
|
77 |
```
|
mergekit_config.yml
CHANGED
@@ -17,25 +17,25 @@ slices:
|
|
17 |
path: mllm-dev/gpt2_f_experiment_1_1000
|
18 |
parameters:
|
19 |
density: 0.8
|
20 |
-
weight: 0.
|
21 |
- layer_range: [0, 12]
|
22 |
model:
|
23 |
model:
|
24 |
path: mllm-dev/gpt2_f_experiment_2_1000
|
25 |
parameters:
|
26 |
-
density: 0.
|
27 |
-
weight: 0.
|
28 |
- layer_range: [0, 12]
|
29 |
model:
|
30 |
model:
|
31 |
path: mllm-dev/gpt2_f_experiment_3_1000
|
32 |
parameters:
|
33 |
-
density: 0.
|
34 |
-
weight: 0.
|
35 |
- layer_range: [0, 12]
|
36 |
model:
|
37 |
model:
|
38 |
path: mllm-dev/gpt2_f_experiment_4_1000
|
39 |
parameters:
|
40 |
density: 0.8
|
41 |
-
weight: 0.
|
|
|
17 |
path: mllm-dev/gpt2_f_experiment_1_1000
|
18 |
parameters:
|
19 |
density: 0.8
|
20 |
+
weight: 0.3
|
21 |
- layer_range: [0, 12]
|
22 |
model:
|
23 |
model:
|
24 |
path: mllm-dev/gpt2_f_experiment_2_1000
|
25 |
parameters:
|
26 |
+
density: 0.6
|
27 |
+
weight: 0.1
|
28 |
- layer_range: [0, 12]
|
29 |
model:
|
30 |
model:
|
31 |
path: mllm-dev/gpt2_f_experiment_3_1000
|
32 |
parameters:
|
33 |
+
density: 0.6
|
34 |
+
weight: 0.1
|
35 |
- layer_range: [0, 12]
|
36 |
model:
|
37 |
model:
|
38 |
path: mllm-dev/gpt2_f_experiment_4_1000
|
39 |
parameters:
|
40 |
density: 0.8
|
41 |
+
weight: 0.3
|
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:ffa5be5a108f5d58195275264465e23384d2041a0f7d691bee44b49c60585fa1
|
3 |
size 248902264
|