RP-Stew-3.0-34B

An (as of right now) experimental/testing merge and exl2 quant to try and upgrade RP-Stew's reasoning capabilities and make it more personable sounding, as well as improve the instruction format slightly. May or may not be better than either of the v2 variants.

trust-remote-code must be turned on for this version (will probably do a version later without needing to do this) also be sure to turn on "Trim Spaces" otherwise the formatting might mess up on occasion.

Prompt Format: Chat-Vicuna-1.1

SYSTEM: {system_prompt}<|end|>
USER: {prompt}<|end|>
ASSISTANT: {output}<|end|>

Models Merged

The following models were included in the merge:

https://huggingface.co/NousResearch/Nous-Capybara-34B

https://huggingface.co/migtissera/Tess-34B-v1.5b

https://huggingface.co/jondurbin/nontoxic-bagel-34b-v0.2

https://huggingface.co/maywell/PiVoT-SUS-RP

https://huggingface.co/Sao10K/NyakuraV2-34B-Yi-Llama

https://huggingface.co/NeverSleep/CausalLM-RP-34B

https://huggingface.co/NousResearch/Nous-Hermes-2-Yi-34B

https://huggingface.co/adamo1139/Yi-34b-200K-AEZAKMI-RAW-TOXIC-2702