Update README.md
Browse files
README.md
CHANGED
@@ -1,14 +1,15 @@
|
|
1 |
---
|
2 |
library_name: transformers
|
|
|
3 |
base_model:
|
4 |
-
- Qwen/Qwen2.5-
|
5 |
license: apache-2.0
|
6 |
---
|
7 |
-
# Replete-LLM-V2.5-
|
8 |
|
9 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/ihnWXDEgV-ZKN_B036U1J.png)
|
10 |
|
11 |
-
Replete-LLM-V2.5-Qwen-
|
12 |
|
13 |
This version of the model shows higher performance than the original instruct and base models.
|
14 |
|
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
+
|
4 |
base_model:
|
5 |
+
- Qwen/Qwen2.5-1.5B-Instruct
|
6 |
license: apache-2.0
|
7 |
---
|
8 |
+
# Replete-LLM-V2.5-1.5b
|
9 |
|
10 |
![image/png](https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/ihnWXDEgV-ZKN_B036U1J.png)
|
11 |
|
12 |
+
Replete-LLM-V2.5-Qwen-1.5b is a continues finetuned version of Qwen2.5-1.5B. I noticed recently that the Qwen team did not learn from my methods of continuous finetuning, the great benefits, and no downsides of it. So I took it upon myself to merge the instruct model with the base model myself using the *Ties* merge method
|
13 |
|
14 |
This version of the model shows higher performance than the original instruct and base models.
|
15 |
|