Delete README.md
Browse files
README.md
DELETED
|
@@ -1,61 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
base_model: []
|
| 3 |
-
library_name: transformers
|
| 4 |
-
tags:
|
| 5 |
-
- mergekit
|
| 6 |
-
- merge
|
| 7 |
-
|
| 8 |
-
---
|
| 9 |
-
# FuseChat-7B-Ties-VaRM-comb1-top0.1
|
| 10 |
-
|
| 11 |
-
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 12 |
-
|
| 13 |
-
## Merge Details
|
| 14 |
-
### Merge Method
|
| 15 |
-
|
| 16 |
-
This model was merged using the ties_varm merge method using /data/wanfq/fusechat/models/openchat_3.5 as a base.
|
| 17 |
-
|
| 18 |
-
### Models Merged
|
| 19 |
-
|
| 20 |
-
The following models were included in the merge:
|
| 21 |
-
* /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-Mixtral
|
| 22 |
-
* /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-NHSolar
|
| 23 |
-
* /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-Qwen
|
| 24 |
-
* /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-internlm
|
| 25 |
-
* /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-Starling
|
| 26 |
-
|
| 27 |
-
### Configuration
|
| 28 |
-
|
| 29 |
-
The following YAML configuration was used to produce this model:
|
| 30 |
-
|
| 31 |
-
```yaml
|
| 32 |
-
models:
|
| 33 |
-
- model: /data/wanfq/fusechat/models/openchat_3.5
|
| 34 |
-
# no parameters necessary for base model
|
| 35 |
-
- model: /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-internlm
|
| 36 |
-
parameters:
|
| 37 |
-
density: 0.1 # density gradient
|
| 38 |
-
weight: 0.2
|
| 39 |
-
- model: /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-Qwen
|
| 40 |
-
parameters:
|
| 41 |
-
density: 0.5
|
| 42 |
-
weight: 0.2 # weight gradient
|
| 43 |
-
- model: /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-Mixtral
|
| 44 |
-
parameters:
|
| 45 |
-
density: 0.5
|
| 46 |
-
weight: 0.2 # weight gradient
|
| 47 |
-
- model: /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-Starling
|
| 48 |
-
parameters:
|
| 49 |
-
density: 0.5
|
| 50 |
-
weight: 0.2 # weight gradient
|
| 51 |
-
- model: /data/wanfq/agno_fusion/fusechat_models/OpenChat-3.5-7B-NHSolar
|
| 52 |
-
parameters:
|
| 53 |
-
density: 0.5
|
| 54 |
-
weight: 0.2 # weight gradient
|
| 55 |
-
merge_method: ties_varm
|
| 56 |
-
base_model: /data/wanfq/fusechat/models/openchat_3.5
|
| 57 |
-
parameters:
|
| 58 |
-
normalize: true
|
| 59 |
-
dtype: bfloat16
|
| 60 |
-
|
| 61 |
-
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|