Cybertron 7B [Uniform Neural Alignment & MGS]
Collection
Another rockstar model, was born as a leader. Tamed with UNA, MGS, DPO, SFT.
โข
6 items
โข
Updated
โข
7
OMA (One Man Army) proudly presents a new 7B Champion: cybertron-7b-v3
with our famous UNA algorythm.
The model excels in mathematics, logic, reasoning, overall very smart. He can make a deep reasoning over the context and prompt, it gives the impression of not missing details around.
This seems to be possible:
Adiestrated with UNA: Uniform Neural Alignment technique (paper going out soon).
The model is very good, works well on almost any prompt but ChatML format and Alpaca System gets the best
<|im_start|>system
- You are a helpful assistant chatbot trained by MosaicML.
- You answer questions.
- You are excited to be able to help the user, but will refuse to do anything that could be considered harmful to the user.
- You are more than just an information source, you are also able to write poetry, short stories, and make jokes.<|im_end|>
<|im_start|>user
Explain QKV<|im_end|>
<|im_start|>assistant
### Assistant: I am StableVicuna, a large language model created by CarperAI. I am here to chat!
### Human: Explain QKV
### Assistant:
[Round <|round|>]
้ฎ๏ผExplain QKV
็ญ๏ผ
[Round <|round|>]
Question๏ผExplain QKV
Answer๏ผ
Question๏ผExplain QKV
Answer๏ผ
Using Exllamav2_HF set alpha=2.5 for 16K Context
If you find Cybertron, Juanako or any of our models useful, specially if you use it for your big brand.. or you clone/merge my modelsm, cite please:
@misc{unacybertron7b,
title={Cybertron: Uniform Neural Alignment},
author={Xavier Murias},
year={2023},
publisher = {HuggingFace},
journal = {HuggingFace repository},
howpublished = {\url{https://huggingface.co/fblgit/una-cybertron-7b-v3-OMA}},
}