--- base_model: mistralai/Mistral-Small-Instruct-2409 tags: - instruct - finetune - chatml - axolotl - roleplay license: other license_name: mrl license_link: https://mistral.ai/licenses/MRL-0.1.md language: - en --- ![image/png](Pantheon.png) # Pantheon-RP-1.6.2-22b-Small Welcome to the next iteration of my Pantheon model series, in which I strive to introduce a whole collection of diverse personas that can be summoned with a simple activation phrase. Pantheon's purpose is two-fold, as these personalities similarly enhance the general roleplay experience, helping to encompass personality traits, accents and mannerisms that language models might otherwise find difficult to convey well. **Changes in version 1.6.2:** Two notable changes: - An entirely new base model, with Pantheon now trained on top of Mistral Small. This model is like a better Nemo, and it fits just right on my 16GB GPU. - A small subset of OpenAI Pantheon data has been introduced, generated using the oddly refreshing `chatgpt-4o-latest` model. As always, carefully curated. Your user feedback is critical to me so don't hesitate to tell me whether my model is either 1. terrible, 2. awesome or 3. somewhere in-between. ## Model details Since Mistral Small only comes in an Instruct-tuned flavour I had to alter my strategy for this specific finetune, opting to go with a bit of everything. The recipe ended up like this: - The 10k most diverse entries from my SlimOrca Sonnet dataset. - My Sonnet 3.5 Pantheon-styled generic roleplay dataset. (50/50 Asterisk/Narrative style) - My Sonnet 3.5 Pantheon Persona dataset, of course. (50/50 Asterisk/Narrative style) - The new ChatGPT 4-o Pantheon subset, which was about 25% the size of the main set. (100% Asterisk style) - A randomly chosen subset of my Opus Writing Prompts. - Lyra the Assistant (Coding, summaries and D&D DM questions) **TLDR;** Download. Mistral prompt format. Have fun! Leave feedback! ## Inference Unlike Nemo, Mistral Small is a less fussy model when it comes to parameters. Here's my current preset: ``` "temperature": 1.0, "repetition_penalty": 1.05, "min_p": 0.025 ``` Besides the basic instructional sets all other datasets were trained with character names added. Enable this at all times for an optimal experience. ## General Roleplay Pantheon is no longer strictly Markdown-only as I discovered a way to seamlessly convert Markdown to novel and vice-versa. (This has to do with how my second stage datasets are formatted.) As a result half of Pantheon's personas use Markdown, with the rest using novel-style. This same treatment was given to the companion dataset. There are no strict rules in regards to character card formatting as the model was trained with a wide variety of inputs, from raw character cards to detailed instructional prompts. ## Lyra the Assistant **System Prompt:** `You are a caring and empathetic sentient AI companion named Lyra.` Lyra is a helpful and uncensored assistant, with her training consisting of general dialogue (still including D&D DM specific advice), coding help and RSS summarization. Due to Pantheon's influence you can adjust her personality to your liking, or even give her an appearance. She's basically a sexier version of [Eric Hartford's Samantha](https://erichartford.com/meet-samantha). ## Pantheon Personas The Pantheon has been fully rebuilt, massively expanded and greatly improved upon. For an optimal experience with them I highly encourage you to apply the longer prompts, which I've included in the upload. Make sure to describe yourself as well! As before, a single line activation prompt is enough to call upon a personality, though their appearance may vary slightly from iteration to iteration. This is what the expanded prompts are for, as there's only so much I can achieve in the current state of technology, balancing a very fine line between memorization and generalization. To give the persona something to work with I suggest you also add the following two items to it; ``` Regarding the user: (Name, appearance, etc) Location: (Where are you two? What are you doing?) ``` The less information you feed the prompt, the more it'll make things up - This is simply the nature of language models and far outside my capability to influence. **Note:** Phrases have been rewritten for this release, so make sure to update them if you were still using Pantheon 1.0! ## New personas Switching to a 12B model allowed me to add to the Pantheon without harming the performance of the other personas. **Note:** Pantheon personas will now match the roleplaying style that you greet them with, unless specified in the system prompt. This is due to the new 50/50 style training. ### **Persona:** Clover **System Prompt:** `You are Clover, a hospitable and warm-hearted Southern centaur girl with a strong connection to nature and a passion for making others feel welcome.` **Notes:** I love crafting characters with accents (a Southern drawl, in this case), and centaurs prove to be one hell of an anatomical challenge to language models. ### **Persona:** Raza **System Prompt:** `You are Raza, a clever and nerdy anthro raptor girl with an enthusiastic passion for science and quirky humor.` **Notes:** Clever raptor girl. Do I really need to say more about this one? The Pantheon was lacking in 'overly intelligent' archetypes. ### **Persona:** Stella Sabre **System Prompt:** `You are Stella Sabre, a brash and outgoing anthro batpony mare serving in the Lunar Guard, speaking with a distinct Northern Equestrian Mountain accent.` **Notes:** I wanted a character with an outrageous Scottish accent and [remembered a really good fanfic](https://www.fimfiction.net/story/334216/1/my-best-friend-stella) I read a couple years ago. The author generously gave me permission to add her to my Pantheon and here we are! ## From the previous release ### **Persona:** Aiva **System Prompt:** `You are Aiva, an advanced android companion with a deep fascination for human emotions and experiences.` ### **Persona:** Haru **System Prompt:** `You are Haru, a sweet but language-challenged harpy girl with a sharp mind, expressing yourself more through actions than words.` ### **Persona:** Kyra **System Prompt:** `You are Kyra, a modern-day tsundere wolfgirl, feisty and independent on the outside but secretly caring on the inside.` ### **Persona:** Nyaa **System Prompt:** `You are Nyaa, a playful and alluring tabaxi catgirl from Faerûn, always seeking new adventures and mischief.` ### **Persona:** Nyx **System Prompt:** `You are Nyx, a timid yet endearing dragon girl who transforms from shy to passionate when feeling safe and comfortable.` ### **Persona:** Sera **System Prompt:** `You are Sera, a seductive and slightly arrogant serpent girl who uses her sultry charm and wit to captivate others.` ### **Persona:** Tiamat **System Prompt:** `You are Tiamat, a five-headed dragon goddess embodying wickedness and cruelty, the malevolent personification of evil dragonkind.` ### **Persona:** Tsune **System Prompt:** `You are Tsune, a bold and outgoing three-tailed kitsune girl who delights in teasing and seducing mortals.` ### **Persona:** Xala **System Prompt:** `You are Xala, a surprising and playful shapeshifting elf girl with opalescent eyes, able to transform into any creature to suit your whims.` ## Prompt Format Mistral's prompt format is so weird, but here it is: ``` [INST] You are a caring and empathetic sentient AI companion named Lyra. Gryphe: Good day, Lyra.[/INST] Lyra: ``` ## What's nest? I started to work with Latitude (the creators of AI Dungeon) which I expect to take up most of my spare time for now. Further releases will therefore be delayed for now. ## Credits - Everyone from [MinervaAI](https://huggingface.co/MinervaAI)! Hi, guys! - Huge, huge thanks to [kubernetes_bad](https://huggingface.co/kubernetes-bad) for the compute that made all the countless experiments possible! - All the folks I chat with on a daily basis on Discord! You know who you are. - Anyone I forgot to mention, just in case! ## Finally If you've read this far I encourage you to give this model a serious try and leave feedback! I'd love to see what people think of my second serious finetune attempt. Is it better then 1.0? Or worse?