Instructions to use Clinical-Reasoning-Hub/Diagnostic-Reasoning-Q3X1S with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Clinical-Reasoning-Hub/Diagnostic-Reasoning-Q3X1S with Transformers:

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

pipe = pipeline("text-generation", model="Clinical-Reasoning-Hub/Diagnostic-Reasoning-Q3X1S")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Clinical-Reasoning-Hub/Diagnostic-Reasoning-Q3X1S")
model = AutoModelForCausalLM.from_pretrained("Clinical-Reasoning-Hub/Diagnostic-Reasoning-Q3X1S", 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 Clinical-Reasoning-Hub/Diagnostic-Reasoning-Q3X1S with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Clinical-Reasoning-Hub/Diagnostic-Reasoning-Q3X1S"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Clinical-Reasoning-Hub/Diagnostic-Reasoning-Q3X1S",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Clinical-Reasoning-Hub/Diagnostic-Reasoning-Q3X1S

SGLang

How to use Clinical-Reasoning-Hub/Diagnostic-Reasoning-Q3X1S 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 "Clinical-Reasoning-Hub/Diagnostic-Reasoning-Q3X1S" \
    --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": "Clinical-Reasoning-Hub/Diagnostic-Reasoning-Q3X1S",
		"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 "Clinical-Reasoning-Hub/Diagnostic-Reasoning-Q3X1S" \
        --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": "Clinical-Reasoning-Hub/Diagnostic-Reasoning-Q3X1S",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Clinical-Reasoning-Hub/Diagnostic-Reasoning-Q3X1S with Docker Model Runner:
```
docker model run hf.co/Clinical-Reasoning-Hub/Diagnostic-Reasoning-Q3X1S
```

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.

Diagnostic-Reasoning-Q3 — bfloat16 serialisation

The same trained model as Diagnostic-Reasoning-Q3X1, stored in bfloat16 rather than float16.

The published results were produced from the Q3X1 float16 release, whose weights are cast to bfloat16 at load by the evaluation harness. Use Q3X1 to reproduce the published figures, and see its model card for evaluation results, overlap analysis and limitations.

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for Clinical-Reasoning-Hub/Diagnostic-Reasoning-Q3X1S

Base model

Qwen/Qwen3-8B-Base

Finetuned

Qwen/Qwen3-8B

Finetuned

(1989)

this model