Hugging Face's logo

vicgalle
/
solarized-18B-dpo

Text Generation
Transformers
Safetensors
llama
dpo
18B
Merge
conversational
Eval Results
text-generation-inference
Inference Endpoints
Model card Files Community
1
vicgalle commited on
Commit
5a19f54
•
1 Parent(s): 448a7df

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -5
README.md CHANGED
@@ -6,9 +6,7 @@ datasets:
6
 
7
  # solarized-18B-dpo
8
 
9
- DPO'd from vicgalle/franken-SOLAR-18B-v1.0.
 
10
 
11
- This is a SOLAR-like model upscaled to 18B.
12
- It is a frankenmerge model created using mergekit, alternating layers of Nous-Hermes-2-SOLAR-10.7B and SOLAR-10.7B-Instruct.
13
-
14
- ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5fad8602b8423e1d80b8a965/mMyHMuuftG71_o4at5suy.png)
 
6
 
7
  # solarized-18B-dpo
8
 
9
+ DPO'd from vicgalle/franken-SOLAR-18B-v1.0, a SOLAR-like model upscaled to 18B.
10
+ It is a frankenmerge model created using mergekit, alternating layers of Nous-Hermes-2-SOLAR-10.7B and SOLAR-10.7B-Instruct. Then, we applied DPO over a high-quality preference dataset.
11
 
12
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/5fad8602b8423e1d80b8a965/rNtaTqTKrAoN5-C5DuPgu.png)