Update README.md
Browse files
README.md
CHANGED
|
@@ -1,10 +1,12 @@
|
|
| 1 |
---
|
| 2 |
-
base_model:
|
|
|
|
|
|
|
| 3 |
library_name: transformers
|
| 4 |
tags:
|
| 5 |
- mergekit
|
| 6 |
- merge
|
| 7 |
-
|
| 8 |
---
|
| 9 |
|
| 10 |
This is a merge of Bytedance Seed-OSS-36B Base and Instruct, using the karcher-means method in [mergekit](https://github.com/cg123/mergekit), with the idea being to get Bytedance Instruct to 'feel' and write more like a raw continuation model.
|
|
@@ -33,8 +35,6 @@ The following YAML configuration was used to produce this model:
|
|
| 33 |
|
| 34 |
```yaml
|
| 35 |
models:
|
| 36 |
-
# - model: /home/alpha/Models/Raw/Qwen_Qwen2.5-14B
|
| 37 |
-
# No parameters necessary for base model
|
| 38 |
- model: /home/alpha/Models/Raw/ByteDance-Seed_Seed-OSS-36B-Base
|
| 39 |
- model: /home/alpha/Models/Raw/ByteDance-Seed_Seed-OSS-36B-Instruct
|
| 40 |
merge_method: karcher
|
|
@@ -45,4 +45,4 @@ parameters:
|
|
| 45 |
int8_mask: true
|
| 46 |
dtype: bfloat16
|
| 47 |
|
| 48 |
-
```
|
|
|
|
| 1 |
---
|
| 2 |
+
base_model:
|
| 3 |
+
- ByteDance-Seed/Seed-OSS-36B-Instruct
|
| 4 |
+
- ByteDance-Seed/Seed-OSS-36B-Base
|
| 5 |
library_name: transformers
|
| 6 |
tags:
|
| 7 |
- mergekit
|
| 8 |
- merge
|
| 9 |
+
license: apache-2.0
|
| 10 |
---
|
| 11 |
|
| 12 |
This is a merge of Bytedance Seed-OSS-36B Base and Instruct, using the karcher-means method in [mergekit](https://github.com/cg123/mergekit), with the idea being to get Bytedance Instruct to 'feel' and write more like a raw continuation model.
|
|
|
|
| 35 |
|
| 36 |
```yaml
|
| 37 |
models:
|
|
|
|
|
|
|
| 38 |
- model: /home/alpha/Models/Raw/ByteDance-Seed_Seed-OSS-36B-Base
|
| 39 |
- model: /home/alpha/Models/Raw/ByteDance-Seed_Seed-OSS-36B-Instruct
|
| 40 |
merge_method: karcher
|
|
|
|
| 45 |
int8_mask: true
|
| 46 |
dtype: bfloat16
|
| 47 |
|
| 48 |
+
```
|