Yano/exp-0223-027-realobs-llmagent-qwen2.5-7b
TEXT GENERATIONConcurrency Cost:1Model Size:7.6BQuant:FP8Ctx Length:32kPublished:Feb 23, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

Yano/exp-0223-027-realobs-llmagent-qwen2.5-7b is a 7.6 billion parameter language model fine-tuned from Qwen/Qwen2.5-7B-Instruct using QLoRA. This model is specifically designed for agentic tasks within the ALFWorld environment, integrating real environment observations with LLM-renarrated strategic thoughts and actions. It specializes in generating agent responses that include strategic thinking and action-dominant formats, particularly for handling failure patterns inherited from real-world trajectories.

Loading preview...