qwen2.5-7b-sft226

qwen2.5-7b-agent-sft-lora

This repository provides a fully merged model fine-tuned from unsloth/Qwen2.5-7B-Instruct using LoRA + Unsloth.

Unlike standard LoRA deployments, this repository contains the complete model weights with the LoRA adapter already merged into the base model. You can use this model directly for inference without needing to load the base model separately.

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: unsloth/Qwen2.5-7B-Instruct
• Method: LoRA (full precision base)
• Max sequence length: 2048
• Epochs: 2
• Learning rate: 2e-06
• LoRA: r=64, alpha=128

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
import torch

base = "unsloth/Qwen2.5-7B-Instruct"
adapter = "your_id/your-repo"

tokenizer = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(
    base,
    torch_dtype=torch.float16,
    device_map="auto",
)
model = PeftModel.from_pretrained(model, adapter)

Sources & Terms (IMPORTANT)

Training data: 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.