This is a merge of pre-trained language models created using mergekit.

Hello everyone this is Dampf, creator of the Destroyer series!

This time, I'm introducing you to 8B-Ultra-Instruct. It is a small general purpose model that combines the most powerful instruct models with enticing roleplaying models. It will introduce better RAG capabilities in the form of Bagel to Llama 3 8B Instruct as well as German multilanguage, higher general intelligence and vision support. A model focused on Biology adds knowledge in the medical field.

As for roleplay, it features two of the hottest models right now. Those are known to be high quality and for being uncensored. So this model might put out harmful responses. We are not responsible for what you do with this model and please take everything the model says with a huge grain of salt. Lastly, you might notice I'm conversative with the weight values in the final merge. This is because I believe L8B Instruct is a very dense model that's already great and doesn't need a lot more data. So instead of reaching the weight value of 1 in a ties merge, I'm only using a total of 0,65. This is to preserve Llama Instruct's intelligence and knowledge, while adding a little bit of the aforementioned models as salt in the soup.

A huge thank you for all the creators of the datasets. Those include Undi95, Jon Durbin, Aaditya, VAGOsolutions, Teknium, Camel and many more. They deserve all the credit. And of course, thank you Elinas for providing the compute.

This model was merged using the DARE TIES merge method using Undi95/Meta-Llama-3-8B-Instruct-hf as a base.

The following models were included in the merge:

The following YAML configuration was used to produce this model:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{input}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

{output}<|eot_id|>

Detailed results can be found here