Instructions to use Parssky/industrial-instruction-qwen4b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Parssky/industrial-instruction-qwen4b with Transformers:

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

pipe = pipeline("text-generation", model="Parssky/industrial-instruction-qwen4b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Parssky/industrial-instruction-qwen4b")
model = AutoModelForCausalLM.from_pretrained("Parssky/industrial-instruction-qwen4b", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Parssky/industrial-instruction-qwen4b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Parssky/industrial-instruction-qwen4b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Parssky/industrial-instruction-qwen4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Parssky/industrial-instruction-qwen4b

SGLang

How to use Parssky/industrial-instruction-qwen4b 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 "Parssky/industrial-instruction-qwen4b" \
    --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": "Parssky/industrial-instruction-qwen4b",
		"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 "Parssky/industrial-instruction-qwen4b" \
        --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": "Parssky/industrial-instruction-qwen4b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Parssky/industrial-instruction-qwen4b with Docker Model Runner:
```
docker model run hf.co/Parssky/industrial-instruction-qwen4b
```

Industrial-Instruction Qwen3-4B (Qwen-generated data)

Qwen3-4B-Instruct-2507 fully fine-tuned on the panasonic_qa_v1 config of Industrial-Instruction — the split generated with the open-weight Qwen3-30B-A3B-Instruct model.

A companion model trained on the Claude-Opus-4.6-generated split is available at Parssky/industrial-instruction-qwen4b-claude.

Paper

Industrial-Instruction: An End-to-End Framework for Building Instruction-Tuning and Benchmark Datasets from Industrial Technical Reports

Base Model

Qwen3-4B-Instruct-2507

Results

Panasonic benchmark (panasonic_qa_v1 test split, 1,000 items):

Configuration	F1	Jaccard	Set-Match Acc.
Base, with RAG	46.57%	41.57%	28.50%
Fine-tuned, with RAG	63.48%	57.95%	42.00%
Base, no RAG	46.63%	41.61%	28.50%
Fine-tuned, no RAG	63.14%	57.60%	41.70%

General knowledge (MMLU, 57 subjects, 14,042 questions): 72.13% base → 70.87% fine-tuned (−1.26).

FailureSensorIQ: AccOrgIBM 34% → 27%, F1-Macro 40% → 43%, F1-Micro 66% → 74%.

Limitations

Accuracy on perturbed (rephrased) FailureSensorIQ questions is 0%, both before and after fine-tuning. The training data contains no paraphrased question variants, so this model should not be relied on where question phrasing varies.
Fine-tuning costs 1.26 points of MMLU accuracy, concentrated in Humanities (moral-reasoning subjects drop ~10 points).
Source documentation comes from a single manufacturer; terminology may not transfer.