MarinaraSpaghetti

Okay, I tried really hard to improve my ChatML merges, but that has gone terribly wrong. Everyone is adding special tokens with different IDs so can't even make a proper union tokenizer for them, damn. Not to mention, I made some... interesting discoveres in regards to some models' context lenghts. You can watch the breakdown of how it went down here: https://www.captiongenerator.com/v/2303039/marinaraspaghetti's-merging-experience. This one feels a bit different to my previous attempts and seems less prone to repetition, especially on higher contexts, which is great for me! I'll probably improve on it even further, but for now, it feels rather nice. Great for RP and storytelling. All credits and thanks go to the amazing MistralAI, Intervitens, Sao10K and Nbeerbower for their amazing models! Plus, special shoutouts to Parasitic Rogue for ideas and Prodeus Unity and Statuo for cool exl2 quants of my previous merges. Cheers to folks over at the Drummer's server! Have a good one, everyone. UPDATE: WE HAD THE WRONG FORMAT ALL ALONG, JUST RECEIVED HOW IT'S SUPPOSED TO LOOK LIKE FROM THE OFFICIAL MISTRALAI TEAM MEMBER. ...This had made me question everything I thought I knew. I recommend running Temperature 1.0-1.25 with 0.1 Top A or 0.01-0.1 Min P, and with 0.8/1.75/2/0 DRY. Also works with lower Temperatures below 1.0. Nothing more needed. You can use my exact settings from here (use the ones from the Mistral Base/Customized folder, I also recommend checking the Mistral Improved folder): https://huggingface.co/MarinaraSpaghetti/SillyTavern-Settings/tree/main. This is a merge of pre-trained language models created using mergekit. This model was merged using the dellalinear merge method using E:\mergekit\mistralaiMistral-Nemo-Base-2407 as a base. The following models were included in the merge: E:\mergekit\intervitensmini-magnum-12b-v1.1 E:\mergekit\nbeerbowermistral-nemo-bophades-12B E:\mergekit\Sao10KMN-12B-Lyra-v1 E:\mergekit\nbeerbowermistral-nemo-gutenberg-12B E:\mergekit\mistralaiMistral-Nemo-Instruct-2407 The following YAML configuration was used to produce this model: Ko-fi Enjoying what I do? Consider donating here, thank you!

Base model: [] Library name: transformers Tags:

Base model: [] Library name: transformers Tags:

I will be uploading my custom and basic Story Strings, Instructs and Parameters templates for SillyTavern here. 1. General Chat Completion 2. Gemini (newest version 4.5) 3. ChatML 4. Mistral Nemo 5. Mistral Small 6. Metharmer/Pygmalion 7. Alpaca 8. Gemma 2 9. Nemotron Basic folder contains Story String and Instruct templates which do not contain customized prompts for my specific use case. Recommended if you want to build upon the base yourself. Customized folder contains Story String and Instruct templates with customized for my specific use case prompts. Go for them if you want a plug-and-go experience, or edit them slightly to your need. Parameters folder contains different samplers. You can play around with them to find the one which suits you best; some will produce more creative outputs than others. 1. Open SillyTavern. 2. Go to the "A" tab at the top bar. 3. Follow the instructions below. 1. Open SillyTavern. 2. Connect to the selected model via "Connection" tab at the top bar. 3. Go to the "A" tab. 4. Follow the instructions below. 1. Open SillyTavern. 2. Go to the "A" tab at the top bar. 3. Follow the instructions below. 1. Open SillyTavern. 2. Go to the "sliders: tab the top bar, the first one from the left. 3. Follow the instructions below. Ko-fi Enjoying what I do? Consider donating here, thank you! https://ko-fi.com/spicymarinara