Instructions to use SII-JasperLi77/CHEESE-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SII-JasperLi77/CHEESE-14B with Transformers:

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

pipe = pipeline("text-generation", model="SII-JasperLi77/CHEESE-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SII-JasperLi77/CHEESE-14B")
model = AutoModelForCausalLM.from_pretrained("SII-JasperLi77/CHEESE-14B", 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 SII-JasperLi77/CHEESE-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SII-JasperLi77/CHEESE-14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SII-JasperLi77/CHEESE-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SII-JasperLi77/CHEESE-14B

SGLang

How to use SII-JasperLi77/CHEESE-14B 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 "SII-JasperLi77/CHEESE-14B" \
    --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": "SII-JasperLi77/CHEESE-14B",
		"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 "SII-JasperLi77/CHEESE-14B" \
        --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": "SII-JasperLi77/CHEESE-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SII-JasperLi77/CHEESE-14B with Docker Model Runner:
```
docker model run hf.co/SII-JasperLi77/CHEESE-14B
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

CHEESE-14B

CHEESE-14B is a research model fine-tuned from Qwen3-14B. It is released to support research on musculoskeletal care, clinical reasoning, and domain-adapted medical language models.

For public research use, we release CHEESE-14B as a smaller checkpoint fine-tuned from Qwen3-14B. The larger internal CHEESE model used in the full research system is not part of this release, and no private clinical data are included.

Model Details

Model name: CHEESE-14B
Base model: Qwen/Qwen3-14B
Architecture: Qwen3ForCausalLM
Parameter scale: 14B
Precision: bfloat16
Format: Safetensors
Context length: 40,960 tokens
License: Apache 2.0, following the base model license

Intended Use

CHEESE-14B is intended for research and development in medical language modeling, with an emphasis on musculoskeletal care. It can be used for experiments in clinical text understanding, medical reasoning, and domain-specific instruction following.

The model is not a medical device. It should not be used for autonomous diagnosis, treatment decisions, triage, or clinical deployment without independent validation, regulatory review, and clinician oversight.

Usage

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "SII-JasperLi77/CHEESE-14B"

tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype="auto",
    device_map="auto",
    trust_remote_code=True,
)

messages = [
    {"role": "user", "content": "Summarize the key considerations for postoperative rehabilitation after musculoskeletal surgery."}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True,
)
inputs = tokenizer([text], return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Limitations

CHEESE-14B may produce incorrect, incomplete, or unsupported medical statements. It may also reflect biases and limitations from the base model and fine-tuning process. Outputs should be treated as research artifacts and reviewed by qualified professionals before any clinical interpretation.

Citation

If you use this model, please cite the Qwen3 technical report and the CHEESE/OrthoPilot work when available.

Downloads last month: -

Safetensors

Model size

15B params

Tensor type

BF16

Model tree for SII-JasperLi77/CHEESE-14B

Base model

Qwen/Qwen3-14B-Base

Finetuned

Qwen/Qwen3-14B

Finetuned

(306)

this model