Geralt-Targaryen
commited on
Commit
•
c2c33b3
1
Parent(s):
776bb55
update readme
Browse files
README.md
CHANGED
@@ -8,7 +8,7 @@ license: apache-2.0
|
|
8 |
|
9 |
QwQ-1.5B-Persona is finetuned from Qwen2.5-1.5B-Instruct on 1 million math persona data (see [this paper](https://arxiv.org/abs/2406.20094) for details about how to construct the data).
|
10 |
|
11 |
-
Currently QwQ-1.5B-Persona is meant to serve as a draft model for losslessly accelerating the inference of QwQ-32B.
|
12 |
|
13 |
## Evaluation
|
14 |
|
|
|
8 |
|
9 |
QwQ-1.5B-Persona is finetuned from Qwen2.5-1.5B-Instruct on 1 million math persona data (see [this paper](https://arxiv.org/abs/2406.20094) for details about how to construct the data).
|
10 |
|
11 |
+
Currently QwQ-1.5B-Persona is meant to serve as a draft model for losslessly accelerating the inference of QwQ-32B, but you may also use it as a standalone model.
|
12 |
|
13 |
## Evaluation
|
14 |
|