astom-M/matsuo-llm-advanced-phase-e3ab

The astom-M/matsuo-llm-advanced-phase-e3ab is a 7.6 billion parameter language model fine-tuned from Qwen/Qwen2.5-7B-Instruct with a 32K context length. This model is specifically optimized for agent tasks, demonstrating proficiency in environments like DBBench and ALFWorld. Its training incorporates diverse datasets including synthetic SFT for DBBench, xlangai/spider, and birdsql/bird_mini_dev, making it suitable for complex database interaction and interactive environment reasoning.