Upload folder using huggingface_hub
Browse files- README.md +5 -7
- config.json +1 -1
- mergekit_config.yml +3 -5
- model-00001-of-00001.safetensors +2 -2
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
base_model:
|
| 3 |
-
- coffiee/s17
|
| 4 |
- coffiee/s18
|
|
|
|
| 5 |
library_name: transformers
|
| 6 |
tags:
|
| 7 |
- mergekit
|
|
@@ -20,8 +20,8 @@ This model was merged using the SLERP merge method.
|
|
| 20 |
### Models Merged
|
| 21 |
|
| 22 |
The following models were included in the merge:
|
| 23 |
-
* [coffiee/s17](https://huggingface.co/coffiee/s17)
|
| 24 |
* [coffiee/s18](https://huggingface.co/coffiee/s18)
|
|
|
|
| 25 |
|
| 26 |
### Configuration
|
| 27 |
|
|
@@ -29,12 +29,11 @@ The following YAML configuration was used to produce this model:
|
|
| 29 |
|
| 30 |
```yaml
|
| 31 |
|
| 32 |
-
|
| 33 |
slices:
|
| 34 |
- sources:
|
| 35 |
- model: coffiee/s18
|
| 36 |
layer_range: [0, 24]
|
| 37 |
-
- model:
|
| 38 |
layer_range: [0, 24]
|
| 39 |
merge_method: slerp
|
| 40 |
base_model: coffiee/s18
|
|
@@ -44,8 +43,7 @@ parameters:
|
|
| 44 |
value: [0, 0.5, 0.3, 0.7, 1]
|
| 45 |
- filter: mlp
|
| 46 |
value: [1, 0.5, 0.7, 0.3, 0]
|
| 47 |
-
- value: 0.
|
| 48 |
-
dtype:
|
| 49 |
-
|
| 50 |
|
| 51 |
```
|
|
|
|
| 1 |
---
|
| 2 |
base_model:
|
|
|
|
| 3 |
- coffiee/s18
|
| 4 |
+
- Sumail/Goat_Derrick12
|
| 5 |
library_name: transformers
|
| 6 |
tags:
|
| 7 |
- mergekit
|
|
|
|
| 20 |
### Models Merged
|
| 21 |
|
| 22 |
The following models were included in the merge:
|
|
|
|
| 23 |
* [coffiee/s18](https://huggingface.co/coffiee/s18)
|
| 24 |
+
* [Sumail/Goat_Derrick12](https://huggingface.co/Sumail/Goat_Derrick12)
|
| 25 |
|
| 26 |
### Configuration
|
| 27 |
|
|
|
|
| 29 |
|
| 30 |
```yaml
|
| 31 |
|
|
|
|
| 32 |
slices:
|
| 33 |
- sources:
|
| 34 |
- model: coffiee/s18
|
| 35 |
layer_range: [0, 24]
|
| 36 |
+
- model: Sumail/Goat_Derrick12
|
| 37 |
layer_range: [0, 24]
|
| 38 |
merge_method: slerp
|
| 39 |
base_model: coffiee/s18
|
|
|
|
| 43 |
value: [0, 0.5, 0.3, 0.7, 1]
|
| 44 |
- filter: mlp
|
| 45 |
value: [1, 0.5, 0.7, 0.3, 0]
|
| 46 |
+
- value: 0.8
|
| 47 |
+
dtype: bfloat16
|
|
|
|
| 48 |
|
| 49 |
```
|
config.json
CHANGED
|
@@ -21,7 +21,7 @@
|
|
| 21 |
"rope_scaling": null,
|
| 22 |
"rope_theta": 10000,
|
| 23 |
"tie_word_embeddings": false,
|
| 24 |
-
"torch_dtype": "
|
| 25 |
"transformers_version": "4.39.2",
|
| 26 |
"use_cache": false,
|
| 27 |
"use_qkv_bias": true,
|
|
|
|
| 21 |
"rope_scaling": null,
|
| 22 |
"rope_theta": 10000,
|
| 23 |
"tie_word_embeddings": false,
|
| 24 |
+
"torch_dtype": "bfloat16",
|
| 25 |
"transformers_version": "4.39.2",
|
| 26 |
"use_cache": false,
|
| 27 |
"use_qkv_bias": true,
|
mergekit_config.yml
CHANGED
|
@@ -1,10 +1,9 @@
|
|
| 1 |
|
| 2 |
-
|
| 3 |
slices:
|
| 4 |
- sources:
|
| 5 |
- model: coffiee/s18
|
| 6 |
layer_range: [0, 24]
|
| 7 |
-
- model:
|
| 8 |
layer_range: [0, 24]
|
| 9 |
merge_method: slerp
|
| 10 |
base_model: coffiee/s18
|
|
@@ -14,6 +13,5 @@ parameters:
|
|
| 14 |
value: [0, 0.5, 0.3, 0.7, 1]
|
| 15 |
- filter: mlp
|
| 16 |
value: [1, 0.5, 0.7, 0.3, 0]
|
| 17 |
-
- value: 0.
|
| 18 |
-
dtype:
|
| 19 |
-
|
|
|
|
| 1 |
|
|
|
|
| 2 |
slices:
|
| 3 |
- sources:
|
| 4 |
- model: coffiee/s18
|
| 5 |
layer_range: [0, 24]
|
| 6 |
+
- model: Sumail/Goat_Derrick12
|
| 7 |
layer_range: [0, 24]
|
| 8 |
merge_method: slerp
|
| 9 |
base_model: coffiee/s18
|
|
|
|
| 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: 0.8
|
| 17 |
+
dtype: bfloat16
|
|
|
model-00001-of-00001.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:740858a9571a089d67f0e35b02ee22f54fed8aced3bbcbec5ea7ea48ea2233f5
|
| 3 |
+
size 3289069520
|