Instructions to use Umiharu/Qwen-4B-DB-AlfWorld-v13 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Umiharu/Qwen-4B-DB-AlfWorld-v13 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Umiharu/Qwen-4B-DB-AlfWorld-v13")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Umiharu/Qwen-4B-DB-AlfWorld-v13")
model = AutoModelForMultimodalLM.from_pretrained("Umiharu/Qwen-4B-DB-AlfWorld-v13")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Umiharu/Qwen-4B-DB-AlfWorld-v13 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Umiharu/Qwen-4B-DB-AlfWorld-v13"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Umiharu/Qwen-4B-DB-AlfWorld-v13",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Umiharu/Qwen-4B-DB-AlfWorld-v13

SGLang

How to use Umiharu/Qwen-4B-DB-AlfWorld-v13 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Umiharu/Qwen-4B-DB-AlfWorld-v13" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Umiharu/Qwen-4B-DB-AlfWorld-v13",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Umiharu/Qwen-4B-DB-AlfWorld-v13" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Umiharu/Qwen-4B-DB-AlfWorld-v13",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Umiharu/Qwen-4B-DB-AlfWorld-v13 with Docker Model Runner:
```
docker model run hf.co/Umiharu/Qwen-4B-DB-AlfWorld-v13
```

Qwen-4B-DB-AlfWorld-v13

This repository provides a merged model fine-tuned from Qwen/Qwen3-4B-Instruct-2507 on datasets u-10bei/sft_alfworld_trajectory_dataset_v5, dbbench_sft_dataset_react_v2 and dbbench_sft_dataset_react_v3.

All LoRA adapter weights have been merged into the base model, and the resulting merged model is saved here as a standalone model. No external adapter loading is required.

Dataset Notes (IMPORTANT)

ALFWorld datasets

For the datasets:

u-10bei/sft_alfworld_trajectory_dataset_v5
u-10bei/sft_alfworld_trajectory_dataset_v4

the following preprocessing steps were applied:

Only samples that include admissible actions for each dialogue turn were extracted. This ensures high-quality supervision aligned with the agent’s available action space.
Inserted the prefix below at the beginning of the first assistant message: Task Type: AGENT This explicitly marks the trajectory as an agent-based task.

Additionally, for sft_alfworld_trajectory_dataset_v5, only samples with input length ≤ 2048 tokens were used during training to ensure training stability and consistency with the maximum sequence length.

DBBench dataset

For u-10bei/dbbench_sft_dataset_react_v3, the following preprocessing was applied:

Inserted the prefix: Task Type: DATABASE at the start of the assistant’s initial turn. This makes the task type explicit and improves instruction consistency.

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 multi-turn trajectories, enabling the model to learn observation interpretation, step-by-step reasoning, action execution, tool use, and recovery from errors.

Training Configuration

Base model: Qwen/Qwen3-4B-Instruct-2507
Method: LoRA (merged into final weights)
Max sequence length: 2048
Learning rate: 5e-06
LoRA parameters used during training: r=32, alpha=64

Usage (Agent-style Inference Example)

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "Umiharu/Qwen-4B-DB-AlfWorld-v13"


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

prompt = "You are a household task-solving agent. Respond 'OK' if you are ready."
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
    **inputs,
    max_new_tokens=64,
    temperature=0.2,
    do_sample=False,
)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Sources & Terms (IMPORTANT)

Training data: u-10bei/sft_alfworld_trajectory_dataset_v5, dbbench_sft_dataset_react_v2 and dbbench_sft_dataset_react_v3

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.

Downloads last month: 13

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for Umiharu/Qwen-4B-DB-AlfWorld-v13

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

(1734)

this model

Umiharu
/

Qwen-4B-DB-AlfWorld-v13