Upload folder using huggingface_hub
Browse files- README.md +34 -23
- config.json +1 -1
- mergekit_config.yml +24 -12
- model-00001-of-00001.safetensors +1 -1
README.md
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
---
|
| 2 |
base_model:
|
| 3 |
-
- mllm-dev/
|
|
|
|
| 4 |
- mllm-dev/gpt2_f_experiment_5
|
| 5 |
-
- mllm-dev/gpt2_f_experiment_0
|
| 6 |
- mllm-dev/gpt2_f_experiment_7
|
| 7 |
- mllm-dev/gpt2_f_experiment_9
|
| 8 |
-
- mllm-dev/
|
| 9 |
-
- mllm-dev/gpt2_f_experiment_3
|
| 10 |
- mllm-dev/gpt2_f_experiment_8
|
| 11 |
-
- mllm-dev/
|
|
|
|
| 12 |
- mllm-dev/gpt2_f_experiment_6
|
| 13 |
library_name: transformers
|
| 14 |
tags:
|
|
@@ -23,20 +23,19 @@ This is a merge of pre-trained language models created using [mergekit](https://
|
|
| 23 |
## Merge Details
|
| 24 |
### Merge Method
|
| 25 |
|
| 26 |
-
This model was merged using the [
|
| 27 |
|
| 28 |
### Models Merged
|
| 29 |
|
| 30 |
The following models were included in the merge:
|
| 31 |
-
* [mllm-dev/
|
|
|
|
| 32 |
* [mllm-dev/gpt2_f_experiment_5](https://huggingface.co/mllm-dev/gpt2_f_experiment_5)
|
| 33 |
-
* [mllm-dev/gpt2_f_experiment_0](https://huggingface.co/mllm-dev/gpt2_f_experiment_0)
|
| 34 |
* [mllm-dev/gpt2_f_experiment_7](https://huggingface.co/mllm-dev/gpt2_f_experiment_7)
|
| 35 |
* [mllm-dev/gpt2_f_experiment_9](https://huggingface.co/mllm-dev/gpt2_f_experiment_9)
|
| 36 |
-
* [mllm-dev/
|
| 37 |
-
* [mllm-dev/gpt2_f_experiment_3](https://huggingface.co/mllm-dev/gpt2_f_experiment_3)
|
| 38 |
* [mllm-dev/gpt2_f_experiment_8](https://huggingface.co/mllm-dev/gpt2_f_experiment_8)
|
| 39 |
-
* [mllm-dev/
|
| 40 |
* [mllm-dev/gpt2_f_experiment_6](https://huggingface.co/mllm-dev/gpt2_f_experiment_6)
|
| 41 |
|
| 42 |
### Configuration
|
|
@@ -44,68 +43,80 @@ The following models were included in the merge:
|
|
| 44 |
The following YAML configuration was used to produce this model:
|
| 45 |
|
| 46 |
```yaml
|
|
|
|
|
|
|
|
|
|
| 47 |
dtype: float16
|
| 48 |
-
merge_method:
|
|
|
|
|
|
|
| 49 |
slices:
|
| 50 |
- sources:
|
| 51 |
- layer_range: [0, 12]
|
| 52 |
model:
|
| 53 |
model:
|
| 54 |
path: mllm-dev/gpt2_f_experiment_0
|
| 55 |
-
parameters:
|
| 56 |
-
weight: 1.0
|
| 57 |
- layer_range: [0, 12]
|
| 58 |
model:
|
| 59 |
model:
|
| 60 |
path: mllm-dev/gpt2_f_experiment_1
|
| 61 |
parameters:
|
| 62 |
-
|
|
|
|
| 63 |
- layer_range: [0, 12]
|
| 64 |
model:
|
| 65 |
model:
|
| 66 |
path: mllm-dev/gpt2_f_experiment_2
|
| 67 |
parameters:
|
| 68 |
-
|
|
|
|
| 69 |
- layer_range: [0, 12]
|
| 70 |
model:
|
| 71 |
model:
|
| 72 |
path: mllm-dev/gpt2_f_experiment_3
|
| 73 |
parameters:
|
| 74 |
-
|
|
|
|
| 75 |
- layer_range: [0, 12]
|
| 76 |
model:
|
| 77 |
model:
|
| 78 |
path: mllm-dev/gpt2_f_experiment_4
|
| 79 |
parameters:
|
| 80 |
-
|
|
|
|
| 81 |
- layer_range: [0, 12]
|
| 82 |
model:
|
| 83 |
model:
|
| 84 |
path: mllm-dev/gpt2_f_experiment_5
|
| 85 |
parameters:
|
| 86 |
-
|
|
|
|
| 87 |
- layer_range: [0, 12]
|
| 88 |
model:
|
| 89 |
model:
|
| 90 |
path: mllm-dev/gpt2_f_experiment_6
|
| 91 |
parameters:
|
| 92 |
-
|
|
|
|
| 93 |
- layer_range: [0, 12]
|
| 94 |
model:
|
| 95 |
model:
|
| 96 |
path: mllm-dev/gpt2_f_experiment_7
|
| 97 |
parameters:
|
| 98 |
-
|
|
|
|
| 99 |
- layer_range: [0, 12]
|
| 100 |
model:
|
| 101 |
model:
|
| 102 |
path: mllm-dev/gpt2_f_experiment_8
|
| 103 |
parameters:
|
| 104 |
-
|
|
|
|
| 105 |
- layer_range: [0, 12]
|
| 106 |
model:
|
| 107 |
model:
|
| 108 |
path: mllm-dev/gpt2_f_experiment_9
|
| 109 |
parameters:
|
| 110 |
-
|
|
|
|
| 111 |
```
|
|
|
|
| 1 |
---
|
| 2 |
base_model:
|
| 3 |
+
- mllm-dev/gpt2_f_experiment_2
|
| 4 |
+
- mllm-dev/gpt2_f_experiment_4
|
| 5 |
- mllm-dev/gpt2_f_experiment_5
|
|
|
|
| 6 |
- mllm-dev/gpt2_f_experiment_7
|
| 7 |
- mllm-dev/gpt2_f_experiment_9
|
| 8 |
+
- mllm-dev/gpt2_f_experiment_1
|
|
|
|
| 9 |
- mllm-dev/gpt2_f_experiment_8
|
| 10 |
+
- mllm-dev/gpt2_f_experiment_3
|
| 11 |
+
- mllm-dev/gpt2_f_experiment_0
|
| 12 |
- mllm-dev/gpt2_f_experiment_6
|
| 13 |
library_name: transformers
|
| 14 |
tags:
|
|
|
|
| 23 |
## Merge Details
|
| 24 |
### Merge Method
|
| 25 |
|
| 26 |
+
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [mllm-dev/gpt2_f_experiment_0](https://huggingface.co/mllm-dev/gpt2_f_experiment_0) as a base.
|
| 27 |
|
| 28 |
### Models Merged
|
| 29 |
|
| 30 |
The following models were included in the merge:
|
| 31 |
+
* [mllm-dev/gpt2_f_experiment_2](https://huggingface.co/mllm-dev/gpt2_f_experiment_2)
|
| 32 |
+
* [mllm-dev/gpt2_f_experiment_4](https://huggingface.co/mllm-dev/gpt2_f_experiment_4)
|
| 33 |
* [mllm-dev/gpt2_f_experiment_5](https://huggingface.co/mllm-dev/gpt2_f_experiment_5)
|
|
|
|
| 34 |
* [mllm-dev/gpt2_f_experiment_7](https://huggingface.co/mllm-dev/gpt2_f_experiment_7)
|
| 35 |
* [mllm-dev/gpt2_f_experiment_9](https://huggingface.co/mllm-dev/gpt2_f_experiment_9)
|
| 36 |
+
* [mllm-dev/gpt2_f_experiment_1](https://huggingface.co/mllm-dev/gpt2_f_experiment_1)
|
|
|
|
| 37 |
* [mllm-dev/gpt2_f_experiment_8](https://huggingface.co/mllm-dev/gpt2_f_experiment_8)
|
| 38 |
+
* [mllm-dev/gpt2_f_experiment_3](https://huggingface.co/mllm-dev/gpt2_f_experiment_3)
|
| 39 |
* [mllm-dev/gpt2_f_experiment_6](https://huggingface.co/mllm-dev/gpt2_f_experiment_6)
|
| 40 |
|
| 41 |
### Configuration
|
|
|
|
| 43 |
The following YAML configuration was used to produce this model:
|
| 44 |
|
| 45 |
```yaml
|
| 46 |
+
base_model:
|
| 47 |
+
model:
|
| 48 |
+
path: mllm-dev/gpt2_f_experiment_0
|
| 49 |
dtype: float16
|
| 50 |
+
merge_method: ties
|
| 51 |
+
parameters:
|
| 52 |
+
normalize: 1.0
|
| 53 |
slices:
|
| 54 |
- sources:
|
| 55 |
- layer_range: [0, 12]
|
| 56 |
model:
|
| 57 |
model:
|
| 58 |
path: mllm-dev/gpt2_f_experiment_0
|
|
|
|
|
|
|
| 59 |
- layer_range: [0, 12]
|
| 60 |
model:
|
| 61 |
model:
|
| 62 |
path: mllm-dev/gpt2_f_experiment_1
|
| 63 |
parameters:
|
| 64 |
+
density: 0.9
|
| 65 |
+
weight: 0.1
|
| 66 |
- layer_range: [0, 12]
|
| 67 |
model:
|
| 68 |
model:
|
| 69 |
path: mllm-dev/gpt2_f_experiment_2
|
| 70 |
parameters:
|
| 71 |
+
density: 0.9
|
| 72 |
+
weight: 0.1
|
| 73 |
- layer_range: [0, 12]
|
| 74 |
model:
|
| 75 |
model:
|
| 76 |
path: mllm-dev/gpt2_f_experiment_3
|
| 77 |
parameters:
|
| 78 |
+
density: 0.9
|
| 79 |
+
weight: 0.1
|
| 80 |
- layer_range: [0, 12]
|
| 81 |
model:
|
| 82 |
model:
|
| 83 |
path: mllm-dev/gpt2_f_experiment_4
|
| 84 |
parameters:
|
| 85 |
+
density: 0.9
|
| 86 |
+
weight: 0.1
|
| 87 |
- layer_range: [0, 12]
|
| 88 |
model:
|
| 89 |
model:
|
| 90 |
path: mllm-dev/gpt2_f_experiment_5
|
| 91 |
parameters:
|
| 92 |
+
density: 0.9
|
| 93 |
+
weight: 0.1
|
| 94 |
- layer_range: [0, 12]
|
| 95 |
model:
|
| 96 |
model:
|
| 97 |
path: mllm-dev/gpt2_f_experiment_6
|
| 98 |
parameters:
|
| 99 |
+
density: 0.9
|
| 100 |
+
weight: 0.1
|
| 101 |
- layer_range: [0, 12]
|
| 102 |
model:
|
| 103 |
model:
|
| 104 |
path: mllm-dev/gpt2_f_experiment_7
|
| 105 |
parameters:
|
| 106 |
+
density: 0.9
|
| 107 |
+
weight: 0.1
|
| 108 |
- layer_range: [0, 12]
|
| 109 |
model:
|
| 110 |
model:
|
| 111 |
path: mllm-dev/gpt2_f_experiment_8
|
| 112 |
parameters:
|
| 113 |
+
density: 0.9
|
| 114 |
+
weight: 0.1
|
| 115 |
- layer_range: [0, 12]
|
| 116 |
model:
|
| 117 |
model:
|
| 118 |
path: mllm-dev/gpt2_f_experiment_9
|
| 119 |
parameters:
|
| 120 |
+
density: 0.9
|
| 121 |
+
weight: 0.1
|
| 122 |
```
|
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "mllm-dev/
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2ForSequenceClassification"
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "mllm-dev/gpt2_f_experiment_0",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2ForSequenceClassification"
|
mergekit_config.yml
CHANGED
|
@@ -1,64 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
| 1 |
dtype: float16
|
| 2 |
-
merge_method:
|
|
|
|
|
|
|
| 3 |
slices:
|
| 4 |
- sources:
|
| 5 |
- layer_range: [0, 12]
|
| 6 |
model:
|
| 7 |
model:
|
| 8 |
path: mllm-dev/gpt2_f_experiment_0
|
| 9 |
-
parameters:
|
| 10 |
-
weight: 1.0
|
| 11 |
- layer_range: [0, 12]
|
| 12 |
model:
|
| 13 |
model:
|
| 14 |
path: mllm-dev/gpt2_f_experiment_1
|
| 15 |
parameters:
|
| 16 |
-
|
|
|
|
| 17 |
- layer_range: [0, 12]
|
| 18 |
model:
|
| 19 |
model:
|
| 20 |
path: mllm-dev/gpt2_f_experiment_2
|
| 21 |
parameters:
|
| 22 |
-
|
|
|
|
| 23 |
- layer_range: [0, 12]
|
| 24 |
model:
|
| 25 |
model:
|
| 26 |
path: mllm-dev/gpt2_f_experiment_3
|
| 27 |
parameters:
|
| 28 |
-
|
|
|
|
| 29 |
- layer_range: [0, 12]
|
| 30 |
model:
|
| 31 |
model:
|
| 32 |
path: mllm-dev/gpt2_f_experiment_4
|
| 33 |
parameters:
|
| 34 |
-
|
|
|
|
| 35 |
- layer_range: [0, 12]
|
| 36 |
model:
|
| 37 |
model:
|
| 38 |
path: mllm-dev/gpt2_f_experiment_5
|
| 39 |
parameters:
|
| 40 |
-
|
|
|
|
| 41 |
- layer_range: [0, 12]
|
| 42 |
model:
|
| 43 |
model:
|
| 44 |
path: mllm-dev/gpt2_f_experiment_6
|
| 45 |
parameters:
|
| 46 |
-
|
|
|
|
| 47 |
- layer_range: [0, 12]
|
| 48 |
model:
|
| 49 |
model:
|
| 50 |
path: mllm-dev/gpt2_f_experiment_7
|
| 51 |
parameters:
|
| 52 |
-
|
|
|
|
| 53 |
- layer_range: [0, 12]
|
| 54 |
model:
|
| 55 |
model:
|
| 56 |
path: mllm-dev/gpt2_f_experiment_8
|
| 57 |
parameters:
|
| 58 |
-
|
|
|
|
| 59 |
- layer_range: [0, 12]
|
| 60 |
model:
|
| 61 |
model:
|
| 62 |
path: mllm-dev/gpt2_f_experiment_9
|
| 63 |
parameters:
|
| 64 |
-
|
|
|
|
|
|
| 1 |
+
base_model:
|
| 2 |
+
model:
|
| 3 |
+
path: mllm-dev/gpt2_f_experiment_0
|
| 4 |
dtype: float16
|
| 5 |
+
merge_method: ties
|
| 6 |
+
parameters:
|
| 7 |
+
normalize: 1.0
|
| 8 |
slices:
|
| 9 |
- sources:
|
| 10 |
- layer_range: [0, 12]
|
| 11 |
model:
|
| 12 |
model:
|
| 13 |
path: mllm-dev/gpt2_f_experiment_0
|
|
|
|
|
|
|
| 14 |
- layer_range: [0, 12]
|
| 15 |
model:
|
| 16 |
model:
|
| 17 |
path: mllm-dev/gpt2_f_experiment_1
|
| 18 |
parameters:
|
| 19 |
+
density: 0.9
|
| 20 |
+
weight: 0.1
|
| 21 |
- layer_range: [0, 12]
|
| 22 |
model:
|
| 23 |
model:
|
| 24 |
path: mllm-dev/gpt2_f_experiment_2
|
| 25 |
parameters:
|
| 26 |
+
density: 0.9
|
| 27 |
+
weight: 0.1
|
| 28 |
- layer_range: [0, 12]
|
| 29 |
model:
|
| 30 |
model:
|
| 31 |
path: mllm-dev/gpt2_f_experiment_3
|
| 32 |
parameters:
|
| 33 |
+
density: 0.9
|
| 34 |
+
weight: 0.1
|
| 35 |
- layer_range: [0, 12]
|
| 36 |
model:
|
| 37 |
model:
|
| 38 |
path: mllm-dev/gpt2_f_experiment_4
|
| 39 |
parameters:
|
| 40 |
+
density: 0.9
|
| 41 |
+
weight: 0.1
|
| 42 |
- layer_range: [0, 12]
|
| 43 |
model:
|
| 44 |
model:
|
| 45 |
path: mllm-dev/gpt2_f_experiment_5
|
| 46 |
parameters:
|
| 47 |
+
density: 0.9
|
| 48 |
+
weight: 0.1
|
| 49 |
- layer_range: [0, 12]
|
| 50 |
model:
|
| 51 |
model:
|
| 52 |
path: mllm-dev/gpt2_f_experiment_6
|
| 53 |
parameters:
|
| 54 |
+
density: 0.9
|
| 55 |
+
weight: 0.1
|
| 56 |
- layer_range: [0, 12]
|
| 57 |
model:
|
| 58 |
model:
|
| 59 |
path: mllm-dev/gpt2_f_experiment_7
|
| 60 |
parameters:
|
| 61 |
+
density: 0.9
|
| 62 |
+
weight: 0.1
|
| 63 |
- layer_range: [0, 12]
|
| 64 |
model:
|
| 65 |
model:
|
| 66 |
path: mllm-dev/gpt2_f_experiment_8
|
| 67 |
parameters:
|
| 68 |
+
density: 0.9
|
| 69 |
+
weight: 0.1
|
| 70 |
- layer_range: [0, 12]
|
| 71 |
model:
|
| 72 |
model:
|
| 73 |
path: mllm-dev/gpt2_f_experiment_9
|
| 74 |
parameters:
|
| 75 |
+
density: 0.9
|
| 76 |
+
weight: 0.1
|
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:ac2d223e322da400f17b562a754f1a096a848b97d0f1bc42731b7a370dc0d4ef
|
| 3 |
size 248902264
|