Qwen3-4B-ALFWorld-DBBench-Agent-SFT-01

This repository provides a merged model fine-tuned from Qwen/Qwen3-4B-Instruct-2507 using LoRA + Unsloth.

The LoRA adapter has been merged into the base model weights.

Training Objective

This adapter 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 model)
• Max sequence length: 2048
• Epochs: 1
• Learning rate: 1e-05
• LoRA: r=64, alpha=128

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

tokenizer = AutoTokenizer.from_pretrained("shotalab/Qwen3-4B-ALFWorld-DBBench-Agent-SFT-01")
model = AutoModelForCausalLM.from_pretrained(
    "shotalab/Qwen3-4B-ALFWorld-DBBench-Agent-SFT-01",
    torch_dtype=torch.float16,
    device_map="auto",
)

Sources & Terms (IMPORTANT)

Training data:

• u-10bei/sft_alfworld_trajectory_dataset_v5
• u-10bei/dbbench_sft_dataset_react_v4

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.