Update README.md
Browse files
README.md
CHANGED
|
@@ -7,8 +7,20 @@ library_name: transformers
|
|
| 7 |
tags:
|
| 8 |
- mergekit
|
| 9 |
- merge
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
# stacked_model
|
| 13 |
|
| 14 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
|
@@ -55,4 +67,4 @@ slices:
|
|
| 55 |
merge_method: passthrough
|
| 56 |
dtype: bfloat16
|
| 57 |
|
| 58 |
-
```
|
|
|
|
| 7 |
tags:
|
| 8 |
- mergekit
|
| 9 |
- merge
|
| 10 |
+
- llama
|
| 11 |
+
license: apache-2.0
|
| 12 |
+
datasets:
|
| 13 |
+
- OpenAssistant/oasst1
|
| 14 |
+
language:
|
| 15 |
+
- en
|
| 16 |
+
- es
|
| 17 |
+
- ru
|
| 18 |
---
|
| 19 |
+
|
| 20 |
+
Simple merges of my diffrent models, then finetuned for 500 steps using lora and oasst1.
|
| 21 |
+
|
| 22 |
+
Merge kit info below:
|
| 23 |
+
|
| 24 |
# stacked_model
|
| 25 |
|
| 26 |
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
|
|
|
| 67 |
merge_method: passthrough
|
| 68 |
dtype: bfloat16
|
| 69 |
|
| 70 |
+
```
|