rombodawg commited on
Commit
0f57a61
1 Parent(s): 7e37a73

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +21 -0
README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ base_model:
4
+ - Qwen/Qwen2.5-3B-Instruct
5
+ license: other
6
+ license_name: qwen-research
7
+ license_link: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct/blob/main/LICENSE
8
+ ---
9
+ # Rombos-LLM-V2.5-Qwen-3b
10
+
11
+ ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/-HJ445rpCH5BTZgWv1Gvd.jpeg)
12
+
13
+ Rombos-LLM-V2.5-Qwen-3b is a continues finetuned version of Qwen2.5-3B. 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
14
+
15
+ This version of the model shows higher performance than the original instruct and base models.
16
+
17
+ Quants:
18
+
19
+ GGUF: https://huggingface.co/bartowski/Replete-LLM-V2.5-Qwen-3b-GGUF
20
+
21
+ Benchmarks: (Coming soon)