laconic-llm/LACONIC-DeepSeek-R1-Distill-1.5B-1500

LACONIC-DeepSeek-R1-Distill-1.5B-1500

This repository hosts LACONIC-DeepSeek-R1-Distill-1.5B-1500, a LACONIC-trained variant of DeepSeek-R1-Distill-Qwen-1.5B.

LACONIC is a length-aware reinforcement learning method for making LLM responses substantially shorter while preserving task performance. During training, it combines task reward with an adaptive length-based cost so that the model learns to stay near a target response budget. This checkpoint targets a budget of 1500 tokens.

In practice, LACONIC is designed to reduce response length with minimal deployment overhead: the released model uses the usual decoding stack and does not require special inference-time control logic.

• —Base model: deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
• —Method: LACONIC
• —Target budget: 1500
• —Paper: LACONIC: Length-Aware Constrained Reinforcement Learning for LLMs
• —Code: Debugger001/LACONIC-LLM