# DPO reinforcement learning

Bielik-1.5B-v3-Instruct is a 1.6 billion parameter Polish generative text model, fine-tuned for instructions based on Bielik-1.5B-v3, developed by SpeakLeash in collaboration with ACK Cyfronet AGH.

Advanced language model fine-tuned based on Qwen/Qwen2.5-72B-Instruct, excelling in natural language understanding and generation

An 8B parameter model based on the Llama 3 architecture, trained with various DPO datasets, focused on text generation tasks

An 8B parameter large language model developed based on winglian/Llama-3-8b-64k-PoSE, using PoSE technology to extend context length to 64k and optimized with DPO fine-tuning

Thai instruction-optimized model fine-tuned from Typhoon-7B using Direct Preference Optimization (DPO) technology

A 200-million-parameter Chinese causal language model based on the Phi2 architecture, supporting text generation tasks