# Role-playing

A Japanese language model optimized for AI Virtual YouTuber (AI VTuber) conversations, developed based on Google's gemma-3-4b-it

A 70B-parameter large language model trained based on Llama 3.3 Instruct, specializing in dialogue generation and creative content creation

The Llamacpp imatrix quantization version of Aion-RP-Llama-3.1-8B, offering multiple quantization options to meet different hardware requirements.

A pre-trained language model merged using the mergekit tool, combining features from multiple Llama-3 variant models

A personalized dialogue model fine-tuned via LoRA based on the Phi-2 model, supporting natural language generation with character settings

HoloSumika-7B Test Version is a large language model created by merging Erosumika-7B-v3-0.2 and Mistral-7B-Holodeck-1 using LazyMergekit

Tiefighter is a 13B-parameter large language model achieved by merging two different LoRAs on top of an existing mature merged model, excelling in creative writing and role-playing.

Based on the 13B parameter version of the LLaMA v2 base model, it excels in chatting, role-playing, and story creation, and has excellent reasoning and logical abilities.

4-bit (int4) quantized version of Chronos-13B, focused on chat, role-playing, and story creation, supporting long text generation

DialoGPT is a dialogue generation model based on the GPT architecture, focusing on generating natural and fluent conversational content.

A Harry Potter-themed dialogue generation model based on the DialoGPT architecture, capable of simulating conversations with characters from the Harry Potter series.

A dialogue generation model based on the DialoGPT architecture, featuring the style of anime character Asuna Yuuki