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 …

Sep 2, 2023 · The result is a model named Mythmalion-13B, a versatile and powerful roleplay model combining MythoMax’s stability and intelligence with Pygmalion-2’s raw creative power.

Pygmalion We are a group dedicated to creating open dialogue models that anyone can freely use. You can find our website here. We also develop Aphrodite Engine. In addition, you can …

Sep 5, 2023 · Pygmalion-2 13B is part of a broader family of models curated by PygmalionAI, which includes additional fine-tuned, merged, and quantized variants designed for specific …

KoboldCPP A AI backend for text generation, designed for GGML/GGUF models (GPU+CPU). Oobabooga A frontend/backend based off Stable Diffusion's WebUI for text generation.

Jun 14, 2025 · This model was trained by doing supervised fine-tuning over a mixture of regular instruction data alongside roleplay, fictional stories and conversations with synthetically …

Meet Pygmalion-2 13B, a powerful AI model that’s all about creative writing and conversation. It’s based on Llama-2 13B, but with a twist: it’s been fine-tuned to excel at fiction writing, …

The long-awaited release of our new models based on Llama-2 is finally here. Pygmalion-2 13B (formerly known as Metharme) is based on Llama-2 13B released by Meta AI.

Sep 4, 2023 · This model was trained by doing supervised fine-tuning over a mixture of regular instruction data alongside roleplay, fictional stories, and conversations with synthetically …

What is PygmalionAI? PygmalionAI is a community dedicated to creating open-source large language models (LLM s) based on EleutherAI's GPT-J 6B { target="_blank" } and Meta's …