astom-M/matsuo-llm-advanced-household-agent
TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:Feb 9, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The astom-M/matsuo-llm-advanced-household-agent is a 7.6 billion parameter language model, fine-tuned from Qwen/Qwen2.5-7B-Instruct, specifically designed for household navigation and manipulation tasks. It was trained using Supervised Fine-Tuning (SFT) with LoRA on 50,000 synthetic samples generated by a rule-based Python simulator. This model excels at interpreting and executing household tasks, generating responses in a THOUGHT/ACTION dialogue format.

Loading preview...