# Long-context Processing

Phi-4 Reasoning is a cutting-edge open-weight reasoning model based on Phi-4, fine-tuned with supervised chain-of-thought trajectory datasets and trained via reinforcement learning, specializing in mathematics, science, and programming skills.

A machine translation quality estimation model fine-tuned based on ModernBERT-base, supporting long-context document-level evaluation

Vietnamese RAG-specific large language model fine-tuned from Qwen2-7B-Instruct, supports 8192-token context length

A multimodal model fine-tuned based on LLaVA-v1.6-Mistral-7B, supporting joint understanding and generation of images and text