Sakai0920/LLM-Advanced-Competition-2025-merged

Qwen3-4B Agent Trajectory LoRA - LLM Advanced Competition 2025

This repository provides a merged model fine-tuned from Qwen/Qwen3-4B-Instruct-2507 using LoRA + Unsloth, then merged back into the base model.

This is a standalone model ready for inference (no adapter loading required).

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 (full precision base) → merged
• Max sequence length: 4096
• Epochs: 2
• Learning rate: 2e-06
• LoRA: r=64, alpha=128

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "Sakai0920/LLM-Advanced-Competition-2025-merged"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    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.