agent-distillation
/

agent_distilled_Qwen2.5-3B-Instruct

Model card Files Files and versions

Model Summary

This model is distilled Qwen2.5-3B-Instruct from agent trajectories in this dataset.

Repository: https://github.com/Nardien/agent-distillation
Paper: https://arxiv.org/abs/2505.17612

Framework versions

PEFT 0.15.1

Downloads last month: 8

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for agent-distillation/agent_distilled_Qwen2.5-3B-Instruct

Base model

Qwen/Qwen2.5-3B

Finetuned

Qwen/Qwen2.5-3B-Instruct

Adapter

(1283)

this model

Paper for agent-distillation/agent_distilled_Qwen2.5-3B-Instruct

Distilling LLM Agent into Small Models with Retrieval and Code Tools

Paper • 2505.17612 • Published May 23, 2025 • 81