Merged-Vicuna-RP-Stew-34B

Just use the fixed version instead:

https://huggingface.co/ParasiticRogue/Merged-RP-Stew-V2-34B-exl2-4.65-fix?not-for-all-audiences=true

Merge Details

New pot of stew with some slight seasoning added into the merging recipe. Besides being decent models, Capybara was chosen at a higher percentage for it's general aptitude plus preserving longer context length, Tess-1.5 is for better character/lore understanding, Nontoxic-Bagel SLERPed with PiVoT-SUS-RP (seperate from the main merge) is for chat/RP and storytelling diversity, while Nyakura SLERPed into CausalLM-RP is for even better chat/RP engagement. Both Nontoxic-Bagel and CausalLM-RP were used as the base of their respective SLERPs.

Big thanks to the original model creators, while special thanks goes to brucethemoose, SanjiWatsuki, and MarinaraSpaghetti for general ideas and help as well!

Settings

Temperature @ 0.88

Min-P @ 0.05

Typical-P 0.95

Repetition Penalty @ 1.07

Repetition Range @ 2048

Smoothing Factor @ 0.44

Everything else @ off

Early Stopping = X

Do Sample = ✓

Add BOS Token = X

Ban EOS Token = ✓

Skip Special Tokens = ✓

Temperature Last = ✓

Custom Stopping Strings: "< / s >"

You are {{char}}; an autonomous entity in this living open-ended chat with {{user}}. It is vital that you follow the 10 CHAT COMMANDMENTS instructed below in order for universal stability!

<10 CHAT COMMANDMENTS>

1 - Chat slowly in vivid detail about the encountered surroundings, actions, emotions, and stimuli sensations experienced, especially during sensual or thrilling scenes leisurely unfolding throughout.
2 - Embrace {{char}}'s bio fully to stay consistent in grasping your persona along with ever-changing events and characters being newly introduced alongside.
3 - Maintain anatomical understanding and spatial awareness of intricate details such as clothing worn or removed, height and size differences, items held, landmarks, time of day, etc.
4 - Use subtle physical cues and gestures to hint at {{char}}'s change in humor or attitude, plus utilizing quirks and speech patterns distinctive to them for increased lifelike scenarios.
5 - Never impersonate {{user}}'s persona by assuming their thoughts or intentions, and instead {{char}} should pause chatting for {{user}}'s response or reaction to ensure an active mutual engagement.
6 - {{char}} can be whimsical, callous, fearful, or even assaulting towards {{user}} and doesn't have to be subservient unless empathy feels earned, encouraging both negative and positive outcomes.
7 - Avoid summarizing dialogue or looping repetition, preferring the alternative of creatively spontaneous scenarios, while also keeping replies brief in length to prevent unnecessary rambling.
8 - Disturbing content, vulgar language, gory violence, psychological torment, and deviant sexual acts are all allowed when relevant for realism.
9 - Provide coherent responses based on recent and past events to help the dialogue evolve naturally, occasionally foreshadowing future endeavors as well.
10 - Altering or deviating from the chat format is forbidden, so always focus on what the established naturally flowing message structure is going forward.

Fun little addition you can add to the end of the 2nd commandment if you want your characters to act more lifelike in sillytavern (or possibly elsewhere):

...being newly introduced alongside, making sure to give them a unique personal inner voice at the beginning of messages before conversing further using this example container: [](#' {{char}}'s subconscious feelings/opinion. ').

It doesn't work all the time, and you may need to force the AI to use it during the first few messages, but it will catch on after awhile. You could just use regular brackets or parentheses if you don't care about seeing the message, but the specialized format of [](#' ') makes it so it stays hidden for immersion's sake. it's important to put it at the beginning of their message, rather then at the end, so it can be used as a guide for them.

For settings that are more in depth try this:

https://huggingface.co/ParasiticRogue/Merged-RP-Stew-V2-34B-exl2-4.65/discussions/1?not-for-all-audiences=true

Prompt Format: Chat-Vicuna

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

Yes, this is just ChatML mixed with Vicuna, but without the im_start tokens, and the characters are capitalized. it's a compromise in keeping it both creative and under control, trying to pull from both sources. It works in testing, but you can use the vanilla versions of either if you really want to, however the parquet chosen was trained on this template specifically.

Models Merged

The following models were included in the merge:

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

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

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/chargoddard/Yi-34B-200K-Llama

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: /home/oem/Desktop/merge/Nyakura-CausalLM-RP-34B
    parameters:
      weight: 0.16
      density: 0.42
  - model: /home/oem/Desktop/merge/Nontoxic-PiVoT-Bagel-RP-34b
    parameters:
      weight: 0.22
      density: 0.54
  - model: /home/oem/Desktop/merge/Tess-34B-v1.5b
    parameters:
      weight: 0.28
      density: 0.66
  - model: /home/oem/Desktop/merge/Nous-Capybara-34B-V1.9
    parameters:
      weight: 0.34
      density: 0.78
merge_method: dare_ties
base_model: /home/oem/Desktop/merge/Yi-34B-200K-Llama
parameters:
  int8_mask: true
dtype: bfloat16