Instructions to use kyLELEng/retailops-instruct-qwen3.5-9b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kyLELEng/retailops-instruct-qwen3.5-9b with Transformers:

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

pipe = pipeline("text-generation", model="kyLELEng/retailops-instruct-qwen3.5-9b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kyLELEng/retailops-instruct-qwen3.5-9b")
model = AutoModelForCausalLM.from_pretrained("kyLELEng/retailops-instruct-qwen3.5-9b")
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

vLLM

How to use kyLELEng/retailops-instruct-qwen3.5-9b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kyLELEng/retailops-instruct-qwen3.5-9b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kyLELEng/retailops-instruct-qwen3.5-9b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/kyLELEng/retailops-instruct-qwen3.5-9b

SGLang

How to use kyLELEng/retailops-instruct-qwen3.5-9b 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 "kyLELEng/retailops-instruct-qwen3.5-9b" \
    --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": "kyLELEng/retailops-instruct-qwen3.5-9b",
		"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 "kyLELEng/retailops-instruct-qwen3.5-9b" \
        --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": "kyLELEng/retailops-instruct-qwen3.5-9b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use kyLELEng/retailops-instruct-qwen3.5-9b with Docker Model Runner:
```
docker model run hf.co/kyLELEng/retailops-instruct-qwen3.5-9b
```

retailops-instruct-qwen3.5-9b / inference_retailops.py

kyLELEng

Upload merged RetailOps-Instruct Qwen3.5-9B full model

a750b19 verified 25 days ago

raw

history blame contribute delete

1.91 kB

	import json
	import torch
	from transformers import AutoModelForCausalLM, AutoTokenizer

	MODEL_ID = "kyLELEng/retailops-instruct-qwen3.5-9b"
	SYSTEM_PROMPT = 'You are RetailOps-Instruct, an e-commerce catalog optimization assistant. Return exactly one valid JSON object. Do not invent unsupported product features. Use product metadata and reviews as the source of truth.'

	tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
	model = AutoModelForCausalLM.from_pretrained(
	MODEL_ID,
	torch_dtype=torch.bfloat16,
	device_map="auto",
	trust_remote_code=True,
	)
	model.eval()

	sample_input = {
	"category": "Home & Kitchen > Kitchen & Dining > Small Appliances",
	"brand": "ExampleBrand",
	"raw_title": "Portable Electric Kettle",
	"raw_description": "Small kettle for boiling water.",
	"product_specs": {"capacity": "1.0L", "material": "stainless steel", "safety": "auto shut-off"},
	"positive_reviews": ["Heats water quickly.", "Good size for small apartments."],
	"negative_reviews": ["The instructions were unclear.", "The outside gets warm after use."],
	"brand_voice": "clear, practical, trustworthy",
	}

	messages = [
	{"role": "system", "content": SYSTEM_PROMPT},
	{
	"role": "user",
	"content": (
	"Given the product metadata, category, and customer reviews, "
	"generate an optimized product listing package.\n\nINPUT:\n"
	+ json.dumps(sample_input, ensure_ascii=False, indent=2)
	),
	},
	]

	prompt = tokenizer.apply_chat_template(
	messages,
	tokenize=False,
	add_generation_prompt=True,
	enable_thinking=False,
	)
	inputs = tokenizer(prompt, return_tensors="pt").to(model.device)

	with torch.no_grad():
	output = model.generate(**inputs, max_new_tokens=900, do_sample=False)

	print(tokenizer.decode(output[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))