astom-M/matsuo-llm-advanced-phase-e2a

The astom-M/matsuo-llm-advanced-phase-e2a is a 7.6 billion parameter language model fine-tuned from Qwen/Qwen2.5-7B-Instruct. This model is specifically optimized for agent tasks, demonstrating proficiency in database interaction (DBBench) and interactive environment navigation (ALFWorld). It leverages datasets like DBBench SFT, Spider, BIRD SQL, and the official ALFWorld v5 dataset to enhance its agentic capabilities. Its primary strength lies in executing complex, multi-step agent workflows.