Hugging Face's logo

Undi95
/
Borealis-10.7B

Text Generation
Transformers
PyTorch
llama
Not-For-All-Audiences
nsfw
text-generation-inference
Model card Files
xet
Community
3
Undi95 commited on
Commit
b2c1ed5
·
verified ·
1 Parent(s): 6ae37b8

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -9,7 +9,7 @@ tags:
9
 
10
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/ieXwQCpyL7AX659Z7ivxA.png)
11
 
12
- Borealis-10.7B is a 10.7B model made of 48 Mistral 7B layers, finetuned for +70h on 2xA6000 on a big RP and Conversational dataset.
13
 
14
  Next step would be to do a DPO train on top, but I don't know if it would be benefical.
15
 
 
9
 
10
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/63ab1241ad514ca8d1430003/ieXwQCpyL7AX659Z7ivxA.png)
11
 
12
+ Borealis-10.7B is a 10.7B model made of 48 Mistral 7B layers, finetuned for +70h on 2xA6000 on a big RP and Conversational dataset with llama2 configuration of Axolotl, like SOLAR.
13
 
14
  Next step would be to do a DPO train on top, but I don't know if it would be benefical.
15