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 / eval_results.json

kyLELEng

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

a750b19 verified 25 days ago

raw

history blame contribute delete

6.59 kB

	{
	"training_log_history": [
	{
	"loss": 1.7147529602050782,
	"grad_norm": 0.5557429194450378,
	"learning_rate": 5e-05,
	"entropy": 1.3842266023159027,
	"num_tokens": 79716.0,
	"mean_token_accuracy": 0.6636141866445542,
	"epoch": 0.0010526315789473684,
	"step": 10
	},
	{
	"loss": 1.057517147064209,
	"grad_norm": 0.4807300567626953,
	"learning_rate": 9.982817869415808e-05,
	"entropy": 1.194282191991806,
	"num_tokens": 161880.0,
	"mean_token_accuracy": 0.7640660256147385,
	"epoch": 0.002105263157894737,
	"step": 20
	},
	{
	"loss": 0.8556486129760742,
	"grad_norm": 0.32483115792274475,
	"learning_rate": 9.810996563573883e-05,
	"entropy": 0.8799786627292633,
	"num_tokens": 242837.0,
	"mean_token_accuracy": 0.8109526604413986,
	"epoch": 0.003157894736842105,
	"step": 30
	},
	{
	"loss": 0.7565423011779785,
	"grad_norm": 0.28475627303123474,
	"learning_rate": 9.639175257731959e-05,
	"entropy": 0.7401942551136017,
	"num_tokens": 319859.0,
	"mean_token_accuracy": 0.8288935780525207,
	"epoch": 0.004210526315789474,
	"step": 40
	},
	{
	"loss": 0.7918671607971192,
	"grad_norm": 0.2301568239927292,
	"learning_rate": 9.467353951890035e-05,
	"entropy": 0.7903933167457581,
	"num_tokens": 397501.0,
	"mean_token_accuracy": 0.825095483660698,
	"epoch": 0.005263157894736842,
	"step": 50
	},
	{
	"loss": 0.8224129676818848,
	"grad_norm": 0.3627431392669678,
	"learning_rate": 9.29553264604811e-05,
	"entropy": 0.7655193030834198,
	"num_tokens": 473920.0,
	"mean_token_accuracy": 0.8176214396953583,
	"epoch": 0.00631578947368421,
	"step": 60
	},
	{
	"loss": 0.8464207649230957,
	"grad_norm": 0.2397315502166748,
	"learning_rate": 9.123711340206186e-05,
	"entropy": 0.8343378663063049,
	"num_tokens": 559247.0,
	"mean_token_accuracy": 0.8138128280639648,
	"epoch": 0.007368421052631579,
	"step": 70
	},
	{
	"loss": 0.7613609313964844,
	"grad_norm": 0.24598781764507294,
	"learning_rate": 8.951890034364262e-05,
	"entropy": 0.7148342356085777,
	"num_tokens": 647916.0,
	"mean_token_accuracy": 0.8272515207529068,
	"epoch": 0.008421052631578947,
	"step": 80
	},
	{
	"loss": 0.7937052249908447,
	"grad_norm": 0.3052941560745239,
	"learning_rate": 8.780068728522337e-05,
	"entropy": 0.7415616571903229,
	"num_tokens": 731904.0,
	"mean_token_accuracy": 0.818175607919693,
	"epoch": 0.009473684210526316,
	"step": 90
	},
	{
	"loss": 0.8092642784118652,
	"grad_norm": 0.21103884279727936,
	"learning_rate": 8.608247422680413e-05,
	"entropy": 0.7637654632329941,
	"num_tokens": 813854.0,
	"mean_token_accuracy": 0.8194937348365784,
	"epoch": 0.010526315789473684,
	"step": 100
	},
	{
	"eval_loss": 0.7767549753189087,
	"eval_runtime": 347.5891,
	"eval_samples_per_second": 11.508,
	"eval_steps_per_second": 2.877,
	"eval_entropy": 0.7429669258594513,
	"eval_num_tokens": 813854.0,
	"eval_mean_token_accuracy": 0.8241108784079552,
	"epoch": 0.010526315789473684,
	"step": 100
	},
	{
	"loss": 0.7675327777862548,
	"grad_norm": 0.2367396205663681,
	"learning_rate": 8.436426116838489e-05,
	"entropy": 0.7208087205886841,
	"num_tokens": 888287.0,
	"mean_token_accuracy": 0.8270161330699921,
	"epoch": 0.011578947368421053,
	"step": 110
	},
	{
	"loss": 0.8215232849121094,
	"grad_norm": 0.24846169352531433,
	"learning_rate": 8.264604810996563e-05,
	"entropy": 0.778062978386879,
	"num_tokens": 968928.0,
	"mean_token_accuracy": 0.8151075035333634,
	"epoch": 0.01263157894736842,
	"step": 120
	},
	{
	"loss": 0.8481046676635742,
	"grad_norm": 0.2661391496658325,
	"learning_rate": 8.092783505154639e-05,
	"entropy": 0.7925655305385589,
	"num_tokens": 1056013.0,
	"mean_token_accuracy": 0.8117670178413391,
	"epoch": 0.01368421052631579,
	"step": 130
	},
	{
	"loss": 0.8251470565795899,
	"grad_norm": 0.2490185648202896,
	"learning_rate": 7.920962199312715e-05,
	"entropy": 0.7860086858272552,
	"num_tokens": 1139592.0,
	"mean_token_accuracy": 0.8182792365550995,
	"epoch": 0.014736842105263158,
	"step": 140
	},
	{
	"loss": 0.8617103576660157,
	"grad_norm": 0.19872666895389557,
	"learning_rate": 7.749140893470791e-05,
	"entropy": 0.7972662836313248,
	"num_tokens": 1236037.0,
	"mean_token_accuracy": 0.8090041935443878,
	"epoch": 0.015789473684210527,
	"step": 150
	},
	{
	"loss": 0.7977757453918457,
	"grad_norm": 0.19242972135543823,
	"learning_rate": 7.577319587628867e-05,
	"entropy": 0.7521506130695343,
	"num_tokens": 1324602.0,
	"mean_token_accuracy": 0.8219349443912506,
	"epoch": 0.016842105263157894,
	"step": 160
	},
	{
	"loss": 0.8367820739746094,
	"grad_norm": 0.2736385762691498,
	"learning_rate": 7.405498281786943e-05,
	"entropy": 0.7833776384592056,
	"num_tokens": 1412212.0,
	"mean_token_accuracy": 0.8115390419960022,
	"epoch": 0.017894736842105262,
	"step": 170
	},
	{
	"loss": 0.7536766052246093,
	"grad_norm": 0.20205377042293549,
	"learning_rate": 7.233676975945017e-05,
	"entropy": 0.7218452334403992,
	"num_tokens": 1506219.0,
	"mean_token_accuracy": 0.8291705161333084,
	"epoch": 0.018947368421052633,
	"step": 180
	},
	{
	"loss": 0.7809348106384277,
	"grad_norm": 0.22076274454593658,
	"learning_rate": 7.061855670103093e-05,
	"entropy": 0.7482779085636139,
	"num_tokens": 1587426.0,
	"mean_token_accuracy": 0.8284277468919754,
	"epoch": 0.02,
	"step": 190
	}
	],
	"generation_eval": {
	"json_validity_rate": 0.5,
	"avg_required_field_completion": 0.171875,
	"num_generation_eval_samples": 8
	},
	"generation_eval_no_think": {
	"inference_mode": "tokenizer.apply_chat_template(..., enable_thinking=False) when supported",
	"num_generation_eval_samples": 24,
	"json_validity_rate": 1.0,
	"listing_num_samples": 13,
	"listing_json_validity_rate": 1.0,
	"listing_avg_required_field_completion": 0.7980769230769231
	}
	}