Hugging Face's logo

Kquant03
/
FrankenDPO-4x7B-bf16

Text Generation
Transformers
Safetensors
English
mixtral
Merge
Mixture of Experts
text-generation-inference
Inference Endpoints
Model card Files Community
1
Kquant03 commited on
Commit
924a49a
·
verified ·
1 Parent(s): 2ffcb74

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -1
README.md CHANGED
@@ -6,10 +6,14 @@ tags:
6
  - merge
7
  ---
8
  ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/7JsqBt8QRiZmcMh-ameqH.jpeg)
9
- # It's alive!!!!
10
 
11
  A frankenMoE using only DPO models. To be used with Chat-instruct mode enabled. I will post the evaluations for it. :)
12
 
 
 
 
 
13
  - [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B) - router
14
  - [udkai/Turdus](https://huggingface.co/udkai/Turdus) - expert #1
15
  - [distilabeled-Marcoro14-7B-slerp](https://huggingface.co/argilla/distilabeled-Marcoro14-7B-slerp) - expert #2
 
6
  - merge
7
  ---
8
  ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/7JsqBt8QRiZmcMh-ameqH.jpeg)
9
+ # It's alive!!!! Half the size and better on GSM8k and Winogrande than Mixtral Instruct 8x 7B!
10
 
11
  A frankenMoE using only DPO models. To be used with Chat-instruct mode enabled. I will post the evaluations for it. :)
12
 
13
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/rx1GfLMEIP3T-r3bxqW9r.png)
14
+
15
+ ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6589d7e6586088fd2784a12c/l-rLXLH0dfLj6GzqAbZCT.png)
16
+
17
  - [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B) - router
18
  - [udkai/Turdus](https://huggingface.co/udkai/Turdus) - expert #1
19
  - [distilabeled-Marcoro14-7B-slerp](https://huggingface.co/argilla/distilabeled-Marcoro14-7B-slerp) - expert #2