# Open-domain dialogue

A fine-tuned version based on Gensyn/Qwen2.5-0.5B-Instruct, trained using the TRL framework and GRPO algorithm, suitable for instruction-following tasks.

This is a hierarchical SLERP merged model based on multiple excellent open-source models (including OpenHermes-2.5, neural-chat-7b, MetaMath-Mistral-7B, and openchat-3.5), designed to serve as a powerful foundation model for various downstream tasks.

ReMM-SLERP is a reconstructed version of the original MythoMax-L2-13B, utilizing SLERP technology to integrate multiple updated 13B parameter models, including Chronos-Beluga, Airoboros, and Huginn.

IDEFICS is an open-source multimodal model capable of processing both image and text inputs to generate text outputs, serving as an open-source reproduction of Deepmind's Flamingo model.

BlenderBot is an open-domain chatbot model focused on multi-turn dialogue and the integration of various conversational skills.

GPT-Neo 1.3B is a 1.3 billion parameter autoregressive language model developed by EleutherAI, based on the GPT-3 architecture, excelling in text generation tasks

GPT-Neo 125M is a Transformer model based on the GPT-3 architecture, developed by EleutherAI, with 125 million parameters, primarily used for English text generation tasks.