sreeramajay/TinyLlama-1.1B-orca-v1.0

The sreeramajay/TinyLlama-1.1B-orca-v1.0 is a 1.1 billion parameter language model, based on the TinyLlama architecture, fine-tuned using Direct Preference Optimization (DPO) on the orca_dpo_pairs dataset. This experimental model is designed for chat-based interactions, leveraging its DPO training to align with human preferences. It offers a compact solution for conversational AI tasks, providing a balance between size and performance for specific natural language processing applications.