---
base_model: centmount/advanced-step1-alfworld-0222
datasets:
- u-10bei/dbbench_sft_dataset_react_v4
language:
- en
license: apache-2.0
library_name: peft
pipeline_tag: text-generation
tags:
- lora
- agent
- tool-use
- alfworld
- dbbench
---

# qwen3-4b-step1-alfworld-lora0222

This repository provides a **LoRA adapter** fine-tuned from
**centmount/advanced-step1-alfworld-0222** using **LoRA + Unsloth**.

This repository contains **LoRA adapter weights only**.
The base model must be loaded separately.

## 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: centmount/advanced-step1-alfworld-0222
- Method: LoRA (full precision base)
- Max sequence length: 3072
- Epochs: 1
- Learning rate: 5e-07
- LoRA: r=16, alpha=32

## Usage

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

base = "centmount/advanced-step1-alfworld-0222"
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.