---
base_model: Qwen/Qwen3-4B-Instruct-2507
datasets:
- u-10bei/sft_alfworld_trajectory_dataset
- u-10bei/sft_alfworld_trajectory_dataset_v2
- u-10bei/sft_alfworld_trajectory_dataset_v3
- u-10bei/sft_alfworld_trajectory_dataset_v4
- u-10bei/sft_alfworld_trajectory_dataset_v5
- u-10bei/dbbench_sft_dataset_react
- u-10bei/dbbench_sft_dataset_react_v2
- u-10bei/dbbench_sft_dataset_react_v3
- u-10bei/dbbench_sft_dataset_react_v4
language:
- en
license: apache-2.0
library_name: mergekit
pipeline_tag: text-generation
tags:
- merge
- ties
- agent
- tool-use
- alfworld
- dbbench
---

## Performance
The model shows balanced performance across agentic tasks:
- **ALFWorld**: 0.60 (Pass@1)
- **DBBench**: 0.5353

# Qwen3-4B Agent TIES Merge v1.2
This repository provides a merged model optimized for agentic tasks, created by merging specialized LoRA adapters into the base model **Qwen/Qwen3-4B-Instruct-2507**.

The merge was performed using the **TIES-Merging** method via **Mergekit**, combining expertise in ALFWorld trajectories and DBBench (SQL) tasks.

This repository contains **full model weights**, ready for inference without needing to load separate adapters.

## Merge Details
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) method.

### Merge Method
- **Method**: `ties`
- **Base Model**: `Qwen/Qwen3-4B-Instruct-2507`
- **Dtype**: `bfloat16`

### Configuration
The following mergekit-yaml configuration was used to produce this model:

```config.yaml
merge_method: ties
base_model: Qwen/Qwen3-4B-Instruct-2507
dtype: bfloat16
models:
  - model: moushi21/agent-bench-alfworld-merged3
    parameters:
      weight: 1.0    # ALF Main
      density: 0.3   # 70% Noise Cut
  - model: moushi21/agent-bench-dbbench-merged4
    parameters:
      weight: 0.3    # DB
      density: 0.3   # 70% Noise Cut
```

## Usage

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

model_id = "moushi21/agent-bench-merged12"

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

## Sources & Terms (IMPORTANT)

### Training Data (Source Model Lineage)
The source models utilized the following datasets for fine-tuning:
* **ALFWorld**: `u-10bei/sft_alfworld_trajectory_dataset` (v1 to v5)
* **DBBench**: `u-10bei/dbbench_sft_dataset_react` (v1 to v4)

### License & Compliance
* **Dataset License**: MIT License. These datasets are 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 (**Qwen3-4B-Instruct-2507**).