NVIDIA released a smaller version, Nemotron-Mini-4B-Instruct
- Optimized for roleplay, RAG QA, and function calling in English.
- Supports context length of 4,096 tokens.
- Commercial use allows
It is a fine-tuned version of nvidia's Minitron-4B-Base, which was pruned and distilled from Nemotron-4 15B using their LLM compression technique
@nvidiadeveloper