Modelpublic

melon1891/agentbench-qwen3-4b-lr5e6-20260224v2

sourceHugging Faceapache-2.0updated 7mo agoView on Hugging Face

0likes19downloads

Model Card

agentbench-qwen3-4b-lr5e6-20260224v2

A full model fine-tuned from Qwen/Qwen3-4B-Instruct-2507 using LoRA + Unsloth, with the adapter merged into the base model.

Training Objective

This model is trained to improve multi-turn agent task performance on ALFWorld (household tasks) and DBBench (database operations).

Loss is applied to all assistant turns in the multi-turn trajectory, enabling the model to learn environment observation, action selection, tool use, and recovery from errors.

Training Configuration

—Base model: Qwen/Qwen3-4B-Instruct-2507
—Method: LoRA (merged into base)
—Max sequence length: 8192
—Epochs: 2
—Learning rate: 5e-06
—LoRA: r=16, alpha=32

Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("melon1891/agentbench-qwen3-4b-lr5e6-20260224v2")
tokenizer = AutoTokenizer.from_pretrained("melon1891/agentbench-qwen3-4b-lr5e6-20260224v2")

Sources & Terms (IMPORTANT)

Training data: melon1891/merged-agent-sft-dataset-20260224

Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License. Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.