Superior inference efficiency with highest accuracy for scientific and complex math reasoning, coding, tool calling, and instruction following.
Distilled version of Llama 3.1 8B using reasoning data generated by DeepSeek R1 for enhanced performance.
Distilled version of Qwen 2.5 32B using reasoning data generated by DeepSeek R1 for enhanced performance.
Distilled version of Qwen 2.5 14B using reasoning data generated by DeepSeek R1 for enhanced performance.
Distilled version of Qwen 2.5 7B using reasoning data generated by DeepSeek R1 for enhanced performance.
State-of-the-art, high-efficiency LLM excelling in reasoning, math, and coding.
Instruction tuned LLM achieving SoTA performance on reasoning, math and general knowledge capabilities
Chinese and English LLM targeting for language, coding, mathematics, reasoning, etc.
Powerful mid-size code model with a 32K context length, excelling in coding in multiple languages.
Chinese and English LLM targeting for language, coding, mathematics, reasoning, etc.
Supports Chinese and English languages to handle tasks including chatbot, content generation, coding, and translation.
Support Chinese and English chat, coding, math, instruction following, solving quizzes
Advanced LLM for synthetic data generation, distillation, and inference for chatbots, coding, and domain-specific tasks.
A general-purpose LLM with state-of-the-art performance in language understanding, coding, and RAG.
