# Role-playing Enhancement

Shisa V2 is a series of Japanese-English bilingual general chat models trained by Shisa.AI, focusing on Japanese task performance while maintaining strong English capabilities.

A merged model based on Nitral-AI and LatitudeGames' two 12B parameter models, using the slerp fusion method, with powerful text generation capabilities

Hathor is an extended version trained on the Llama 3 8B instruction model, incorporating private data, synthetic instruction data, a mix of light/classic novel data, and role-playing dialogue pairs.

Llama3-70B-Chinese-Chat is a large bilingual language model developed based on Meta-Llama-3-70B-Instruct, specifically designed for Chinese and English users, with capabilities such as role-playing, tool usage, and mathematical computation.

This is a hybrid model based on Llama-2-13B, incorporating features from multiple models including Tiefighter, MedLLaMA, and limarp-v2, suitable for various text generation tasks.

DialoGPT-small is a pre-trained dialogue generation model released by Microsoft, optimized for multi-turn dialogue scenarios based on the GPT architecture.