Modelpublic

tussiiiii/Qwen3-4B-AgentBench-Merged-v2-13

sourceHugging Faceapache-2.0updated 7mo agoView on Hugging Face

0likes13downloads

Model Card

Qwen3-4B-AgentBench-Merged-v2-13

This repository provides a merged full model fine-tuned from Qwen/Qwen3-4B-Instruct-2507 using LoRA + Unsloth. The LoRA adapter has been merged into the base model weights.

The model can be loaded directly without requiring a separate adapter.

Training Objective

This model is trained for multi-turn agent-style reasoning tasks, including structured tool use and database-oriented reasoning.

Loss is applied to all assistant turns within each trajectory.

Training Configuration

—Base model: Qwen/Qwen3-4B-Instruct-2507
—Method: LoRA (merged)
—Max sequence length: 8192
—Epochs: 1
—Learning rate: 1e-06
—LoRA config: r=64, alpha=128

Training Data

The model was trained on a merged dataset created by concatenating and shuffling the following datasets:

—tussiiiii/openalexdbbenchsynth_v4
—tussiiiii/alfworldsynthv1

Dataset Details

—tussiiiii/openalexdbbenchsynth_v4
—tussiiiii/alfworldsynthv1

The datasets above were independently created by the author. They are fully synthetic and were generated from scratch. No benchmark evaluation data was used in their creation.

License & Compliance

Users must comply with:

—The license of each dataset listed above
—The license of the base model: Qwen/Qwen3-4B-Instruct-2507

This repository does not claim ownership of third-party datasets. Synthetic datasets were independently generated.

Usage

python

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "your_id/your-repo"

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