Instructions to use zero9tech/Qwen3-4B-Data-Science-Insight-TR-16.2K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use zero9tech/Qwen3-4B-Data-Science-Insight-TR-16.2K with Transformers:

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

pipe = pipeline("text-generation", model="zero9tech/Qwen3-4B-Data-Science-Insight-TR-16.2K")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("zero9tech/Qwen3-4B-Data-Science-Insight-TR-16.2K")
model = AutoModelForCausalLM.from_pretrained("zero9tech/Qwen3-4B-Data-Science-Insight-TR-16.2K")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use zero9tech/Qwen3-4B-Data-Science-Insight-TR-16.2K with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "zero9tech/Qwen3-4B-Data-Science-Insight-TR-16.2K"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "zero9tech/Qwen3-4B-Data-Science-Insight-TR-16.2K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/zero9tech/Qwen3-4B-Data-Science-Insight-TR-16.2K

SGLang

How to use zero9tech/Qwen3-4B-Data-Science-Insight-TR-16.2K 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 "zero9tech/Qwen3-4B-Data-Science-Insight-TR-16.2K" \
    --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": "zero9tech/Qwen3-4B-Data-Science-Insight-TR-16.2K",
		"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 "zero9tech/Qwen3-4B-Data-Science-Insight-TR-16.2K" \
        --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": "zero9tech/Qwen3-4B-Data-Science-Insight-TR-16.2K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use zero9tech/Qwen3-4B-Data-Science-Insight-TR-16.2K with Docker Model Runner:
```
docker model run hf.co/zero9tech/Qwen3-4B-Data-Science-Insight-TR-16.2K
```

murataksit34 commited on Apr 13

Commit

0e78352

verified ·

1 Parent(s): 39c2a67

Fix README with correct datasets/splits and curriculum notes

Browse files

Files changed (1) hide show

README.md +11 -11

README.md CHANGED Viewed

@@ -15,19 +15,19 @@ datasets:
 - zero9tech/veri-bilimci-insight-diyalog-tr-16.2k
 ---
-# QWEN3-4B-Data-Science-V2-TR — Türkçe Insight Ustası
-## Eğitim Kurgusu
-1. Türkçe düşünme adaptasyonu:  ile yaklaşık  ön eğitim/adaptasyon ( kayıt).
-2. Alan uzmanlığı SFT: .
-## Kullanılan Dataset Özeti
-- Toplam kayıt:
-- Split:  ·  ·
-- Hard gate:
-- Soft gate:
-- Self-BLEU (final):
-- Distinct-2 (final):
 ## Copyright
 Copyright (c) Zero9 Tech

 - zero9tech/veri-bilimci-insight-diyalog-tr-16.2k
 ---
+# QWEN3-4B-Data-Science-V2-TR - Turkce Insight Ustasi
+## Egitim Kurgusu
+1. Turkce dusunme adaptasyonu: wikimedia/wikipedia ile yaklasik %80 on egitim/adaptasyon (427,990 kayit).
+2. Alan uzmanligi SFT: zero9tech/veri-bilimci-insight-diyalog-tr-16.2k.
+## Kullanilan Dataset Ozeti
+- Toplam kayit: 16,180
+- Split: train 13,763 ; validation 814 ; test 1,603
+- Hard gate: PASS
+- Soft gate: PASS
+- Self-BLEU (final): 0.5988
+- Distinct-2 (final): 0.0806
 ## Copyright
 Copyright (c) Zero9 Tech