Update README.md
Browse files
README.md
CHANGED
@@ -14,4 +14,6 @@ library_name: transformers
|
|
14 |
|
15 |
This is a linear merge of [Qwen/Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct) at weight `0.6` and [Qwen/Qwen2.5-72B](https://huggingface.co/Qwen/Qwen2.5-72B) at weight `0.4`.
|
16 |
|
17 |
-
The resulting model is 60% Instruct and 40% base model, hence the name **`0.6x-Instruct`**.
|
|
|
|
|
|
14 |
|
15 |
This is a linear merge of [Qwen/Qwen2.5-72B-Instruct](https://huggingface.co/Qwen/Qwen2.5-72B-Instruct) at weight `0.6` and [Qwen/Qwen2.5-72B](https://huggingface.co/Qwen/Qwen2.5-72B) at weight `0.4`.
|
16 |
|
17 |
+
The resulting model is 60% Instruct and 40% base model, hence the name **`0.6x-Instruct`**.
|
18 |
+
|
19 |
+
The goal of the merge was to make the Instruct model more flexible and less rigid. After some initial testing, I think the resulting model meets this goal, and I find it useful and interesting enough to warrant publishing.
|