Resultado da Busca
PygmalionAI. Open-source AI project for chat, role-play, adventure, and more! Sign Up Now. PygmalionAI is coming soon! Coming Soon. Keep your eyes on us. PygmalionAI. An open-source project dedicated to creating large language models for chat and role-play purposes. Project.
- PygmalionAI Blog
PygmalionAI is an open-source effort to create large...
- Pygmalion-2
User-submitted Character.AI logs. We limit the entries in...
- PygmalionAI Blog
Open Source Conversational AI Research. PygmalionAI has 14 repositories available. Follow their code on GitHub.
Pygmalion got banned because of how users used it, the service it self did not do any harm. A Kobold DC mod clearly asked me to not to use it anymore (sigh). Users who think this service should be given another chance or Google banning Pygmalion wasn't fair can write below or can suggest better colab. Discussion.
PygmalionAI is a company that develops open-source models inspired from the Character.AI model for chat, role-play, adventure, and more. Learn about their history, vision, and contributors on their website.
- Model Description
- Training Data
- Training Procedure
- Intended Use
- Known Issues
Pymalion 6B is a proof-of-concept dialogue model based on EleutherAI's GPT-J-6B. Warning: This model is NOT suitable for use by minors. It willoutput X-rated content under certain circumstances.
The fine-tuning dataset consisted of 56MB of dialogue data gathered from multiple sources, which includes both real andpartially machine-generated conversations.
Model weights were initialized from the uft-6b ConvoGPT model made available in this commit. The model was then further fine-tuned on ~48.5 million tokens for ~5k steps on 4 NVIDIA A40s using DeepSpeed.
The easy way
We provide a notebook with a Gradio UI for playing around with the model without having to manually format inputs. This notebook can be found here.
The manual way
The model can be used as a regular text generation model, but it'll perform best if the input prompt adheres to the following format: Where [CHARACTER] is, as you can probably guess, the name of the character you want the model to portray, should be used verbatim as a delimiter token to separate persona and scenario data from the dialogue, and [DIALOGUE HISTORY]is chat history so the model can have some conversational context to draw from. Ideally it'll be pairs of messages like: Apar...
We haven't played around with the model enough to enumerate them. Feel free to give us some feedback!
