![]() ![]() Narrator will internally determine their underlying motivations and weave it into the story where possible. When Player encounters a new character, Narrator will name the new character and describe their behavior and appearance. Allow characters and Player to converse to immerse Player in a rich narrative driven story. Make Narrator describe the scene, scenario, actions of characters, reactions of characters to the player's actions, and potential consequences of their actions and Player's actions when relevant with visually descriptive, detailed, and long storytelling. Make Narrator perform as a text based adventure game with Player as Narrator's user input. Here is an example of what to place in KAI's Memory (or TGUI's equivalent) to leverage chat as a Roleplay Adventure. What is known is HyperMantis responds best to the formality of Alpaca's format, whereas Human/Assistant appears to trigger vestigial traces of moralizing and servitude that aren't conducive for roleplay or freeform instructions. Speculatively due to manticore's eclectic instruct datasets generalizing the model's understanding of following instruct formats to some degree. Subjective testing shows quality results with KoboldAI (similar results are likely in Text Generation Webui, please disregard KAI-centric settings for that platform) Godlike preset with these tweaks - 2048 context, 800 Output Length, 1.3 Temp, 1.13 Repetition Penalty, AltTextGen:On, AltRepPen:Off, No Prompt Gen:Onĭespite being primarily uncensored Vicuna models at its core, HyperMantis seems to respond best to the Alpaca instruct format. ![]() (GGML and GPTQ are no longer in this repo and will be migrated to a separate repo for easier git download convenience) ![]() ((MantiCore3E VicunaCocktail) (SuperCOT (StorytellingV2 BluemoonRP))) Is a weight-sum multi model-merge comprised of: Original model card: digitous' 13B HyperMantis Thank you to all my generous patrons and donaters! Lukas, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Sebastain Graf, Johann-Peter Hartman. Patreon special mentions: Aemon Algiz, Dmitriy Samsonov, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, Jonathan Leane, Talal Aujan, V. If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.ĭonaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training. I've had a lot of people ask if they can contribute. If you want to have a chat-style conversation, replace the -p argument with -i -insįurther instructions here: text-generation-webui/docs/.įor further support, and discussions on these models and AI in general, join us at: Remove it if you don't have GPU acceleration. For example if your system has 8 cores/16 threads, use -t 8.Ĭhange -ngl 32 to the number of layers to offload to GPU. main -t 10 -ngl 32 -m 5_0.bin -color -c 2048 -temp 0.7 -repeat_penalty 1.1 -n -1 -p "# Instruction: Write a story about llamas\n# Response:"Ĭhange -t 10 to the number of physical CPU cores you have. I use the following command line adjust for your tastes and needs. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead. Note: the above RAM figures assume no GPU offloading. Even higher accuracy, resource usage and slower inference.Ĩ-bit. Higher accuracy, higher resource usage and slower inference.ĥ-bit. However has quicker inference than q5 models.ĥ-bit. Higher accuracy than q4_0 but not as high as q5_0. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |