Yano/exp-0223-027-realobs-llmagent-qwen2.5-7b

TEXT GENERATIONPricing:Input $0.4 / Cached $0.08 / Output $0.8Concurrent Unit Cost:1Model Size:7.6BQuant:FP8Context Size:32kTool Calling:SupportedPublished:Feb 23, 2026License:apache-2.0Architecture:Transformer Open Weights Featherless Exclusive 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...

Overview

Yano/exp-0223-027-realobs-llmagent-qwen2.5-7b is a 7.6 billion parameter model fine-tuned from Qwen/Qwen2.5-7B-Instruct using QLoRA (4-bit, Unsloth). Its primary purpose is to enhance agentic behavior within the ALFWorld environment by combining real observational data with sophisticated LLM-generated strategic responses.

Key Design Principles

  • Real Environment Observations: Utilizes byte-exact preservation of real data from experiment 016 for environment responses.
  • LLM-Renarrated Agent Responses: Agent responses are generated by the LLM, focusing on strategic THOUGHT processes and an ACTION-dominant format, rather than templated replies.
  • Structured Response Format: Employs a specific format where the first turn includes THOUGHT+ACTION, subsequent turns are ACTION-only, and a recovery THOUGHT is introduced after failures.
  • Failure Pattern Integration: Naturally incorporates failure patterns observed in 72% of trajectories from the source experiment 016, allowing for more robust agent behavior.

Training Configuration

  • Base Model: Qwen/Qwen2.5-7B-Instruct
  • Method: QLoRA (4-bit), merged to 16-bit
  • Max Sequence Length: 2048 tokens
  • Epochs: 3
  • Learning Rate: 2e-05
  • LoRA Parameters: r=64, alpha=128
  • Collator: AllAssistantTurnsCollator, ensuring all agent turns are supervised during training.

Good For

  • Developing and testing LLM agents in simulated environments like ALFWorld.
  • Research into integrating real-world observations with strategic LLM planning.
  • Creating agents that can articulate their thought processes and recover from failures.

Finetunes
1 models