Instructions to use Dbmaxwell/Qwen3-4B-Instruct-2507-Fintool-TR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Dbmaxwell/Qwen3-4B-Instruct-2507-Fintool-TR with Transformers:

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

pipe = pipeline("text-generation", model="Dbmaxwell/Qwen3-4B-Instruct-2507-Fintool-TR")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Dbmaxwell/Qwen3-4B-Instruct-2507-Fintool-TR")
model = AutoModelForCausalLM.from_pretrained("Dbmaxwell/Qwen3-4B-Instruct-2507-Fintool-TR", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Dbmaxwell/Qwen3-4B-Instruct-2507-Fintool-TR with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Dbmaxwell/Qwen3-4B-Instruct-2507-Fintool-TR"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Dbmaxwell/Qwen3-4B-Instruct-2507-Fintool-TR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Dbmaxwell/Qwen3-4B-Instruct-2507-Fintool-TR

SGLang

How to use Dbmaxwell/Qwen3-4B-Instruct-2507-Fintool-TR 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 "Dbmaxwell/Qwen3-4B-Instruct-2507-Fintool-TR" \
    --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": "Dbmaxwell/Qwen3-4B-Instruct-2507-Fintool-TR",
		"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 "Dbmaxwell/Qwen3-4B-Instruct-2507-Fintool-TR" \
        --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": "Dbmaxwell/Qwen3-4B-Instruct-2507-Fintool-TR",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use Dbmaxwell/Qwen3-4B-Instruct-2507-Fintool-TR with Docker Model Runner:
```
docker model run hf.co/Dbmaxwell/Qwen3-4B-Instruct-2507-Fintool-TR
```

Qwen3-4B Fintool TR

unsloth/Qwen3-4B-Instruct-2507 modelinin Dbmaxwell/FintoolDataset-tr üzerinde 4-bit QLoRA ile üç epoch tool-calling SFT uygulanmış, Hub'a birleşik 16-bit ağırlıklarla yüklenmiş sürümüdür.

Sequence length: 8192
LoRA: r=16, alpha=16
Learning rate: 2e-5
Effective batch size: 8
Final eval loss: 0.404270738363266
Seed: 3407

Model çıktıları finansal tavsiye değildir; gerçek işlemlerden önce araç argümanlarını ve sonuçlarını doğrulayın.

Downloads last month: 368

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for Dbmaxwell/Qwen3-4B-Instruct-2507-Fintool-TR

Base model

Qwen/Qwen3-4B-Instruct-2507

Finetuned

unsloth/Qwen3-4B-Instruct-2507

Finetuned

(465)

this model

Dbmaxwell
/

Qwen3-4B-Instruct-2507-Fintool-TR

Qwen3-4B Fintool TR

Model tree for Dbmaxwell/Qwen3-4B-Instruct-2507-Fintool-TR

Dataset used to train Dbmaxwell/Qwen3-4B-Instruct-2507-Fintool-TR