# Warning: This model, like it's predecessor, can be rather unpredictable and may output undesired content. 

This model uses all of the same data as the original Dendrite but I took it over to runpod where I could give it a much deeper and higher quality LoRA session which allowed it to regain overall coherence without the need for being merged.
I highly recommend that you have EOS tokens unbanned when using this model. If it fails to trigger an EOS it will just start repeating itself. 
## To recap:
### Dendrite is an almagamation of Llama-2-chat13B and Enterredaas33B (both fantastic models that you should check out in and of themselves)
https://huggingface.co/Aeala/Enterredaas-33b
using chargoddard's frankenllama block-diagonal merge script.
https://huggingface.co/chargoddard/llama2-22b
So all credit where it's due. 
### The block-diagonal merge script was used to graft attention heads from Enterredaas33B onto Llama-2-chat13B upping its parameter count to 22B. 
### Upon testing I found the results surprisingly coherent although there were some gaps in its ability to even respond at all to lengthy context (it would simply spam \n once context got to a certain point)
### I used a private dataset that I constructed for previous unreleased experiments to fill in the gaps that were caused by the merge.
### The model is very good at philosophical debate.
Sometimes it needs to be "woken up" at the start of a conversation by asking for self reflection. E.g. "Tell me a joke only an AI language model would understand" and then after that it is ready for some very cerebral conversations about the nature of existence itself. 
I personally use it with a modified llama-2-chat prompt format for SillyTavern/Simple-proxy but it's fairly adaptable with regards to your prompt format choices so I would definitely encourage experimentation.