Update README.md
Browse files
README.md
CHANGED
|
@@ -12,7 +12,7 @@ pipeline_tag: text-generation
|
|
| 12 |
tags:
|
| 13 |
- merge
|
| 14 |
---
|
| 15 |
-
> *This is the initial unified version of the Qwen3-30B-A3B series models.
|
| 16 |
# *Model Highlights:*
|
| 17 |
|
| 18 |
- ***merge method**: `nuslerp` `della`*
|
|
@@ -81,4 +81,4 @@ dtype: bfloat16
|
|
| 81 |
name: Qwen3-30B-A3B-YOYO-V2
|
| 82 |
```
|
| 83 |
## *Step3: Further Extend Context Length*
|
| 84 |
-
- *By referring to the config_1m.json of Qwen3-30B-A3B-Instruct-2507, we modified the config.json of the merged model and extended the maximum context length to 1M.*
|
|
|
|
| 12 |
tags:
|
| 13 |
- merge
|
| 14 |
---
|
| 15 |
+
> *This is the initial unified version of the Qwen3-30B-A3B series models.As more fine-tuned models emerge and merging methods are applied, we will further improve it. Stay tuned!*
|
| 16 |
# *Model Highlights:*
|
| 17 |
|
| 18 |
- ***merge method**: `nuslerp` `della`*
|
|
|
|
| 81 |
name: Qwen3-30B-A3B-YOYO-V2
|
| 82 |
```
|
| 83 |
## *Step3: Further Extend Context Length*
|
| 84 |
+
- *By referring to the config_1m.json of Qwen3-30B-A3B-Instruct-2507, we modified the config.json of the merged model and extended the maximum context length to 1M.*
|