Instructions to use BrainHealthAI/BrainMed-8B-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BrainHealthAI/BrainMed-8B-SFT with Transformers:

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

pipe = pipeline("text-generation", model="BrainHealthAI/BrainMed-8B-SFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("BrainHealthAI/BrainMed-8B-SFT")
model = AutoModelForCausalLM.from_pretrained("BrainHealthAI/BrainMed-8B-SFT", 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 BrainHealthAI/BrainMed-8B-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BrainHealthAI/BrainMed-8B-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "BrainHealthAI/BrainMed-8B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/BrainHealthAI/BrainMed-8B-SFT

SGLang

How to use BrainHealthAI/BrainMed-8B-SFT 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 "BrainHealthAI/BrainMed-8B-SFT" \
    --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": "BrainHealthAI/BrainMed-8B-SFT",
		"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 "BrainHealthAI/BrainMed-8B-SFT" \
        --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": "BrainHealthAI/BrainMed-8B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use BrainHealthAI/BrainMed-8B-SFT with Docker Model Runner:
```
docker model run hf.co/BrainHealthAI/BrainMed-8B-SFT
```

BrainMed-8B-SFT

Full-parameter supervised fine-tune of FreedomIntelligence/HuatuoGPT-o1-8B on Williamsanderson/MedReason-MedO1-Reasoning-46K, a union of KG-grounded MedReason reasoning traces and verifier-checked medical-o1 traces.

Parameters: 8,030,261,248 (8.03B) - full weights, not an adapter
Precision: BF16
Recipe: MedReason (arXiv:2504.00993) - lr 5e-6, effective batch 128, 3 epochs, cosine schedule with 5% warmup, weight decay 0.1, DeepSpeed ZeRO-3, bf16
Weights obtained by: lowest held-out validation loss (val loss 0.7557 at optimizer step 1041)

Output format

The model is trained to reason inside <think>...</think> and answer inside <answer>...</answer>, under this system prompt:

You are a medical reasoning assistant. Work through the clinical problem step by step inside <think>...</think>, grounding every step in established medical knowledge, then give the final, complete answer inside <answer>...</answer>.

Evaluation

Benchmark	n	Accuracy
medbullets_op4	308	58.77
medbullets_op5	308	56.82
medmcqa_val	4183	61.2
medqa_4opt	1273	72.11
medxpertqa	1449	18.08
pubmedqa_test	1000	77.1

Scored with the MedReason evaluation harness (greedy decoding, strict answer prompt, max(head, tail) extraction) on the benchmark files shipped by the MedReason and HuatuoGPT-o1 repositories - no benchmark was rebuilt or resampled.

Data integrity

Training rows: 44,351.

Rows overlapping the evaluation benchmarks were kept, matching the upstream setting under which the published comparison tables were produced. The overlap was measured and is declared below rather than removed; the evaluation therefore reports a clean-subset score alongside the raw one, and the clean figure is the unbiased estimate.

Benchmark	items	overlapping training rows
hle_med	103	30 (29.13%)
medbullets_op4	308	35 (11.36%)
medbullets_op5	308	35 (11.36%)
medqa_4opt	1273	1 (0.08%)
medqa_5opt	1273	1 (0.08%)
medxpertqa	1449	15 (1.04%)
mmlu_pro_medical	1535	340 (22.15%)

This overlap originates upstream: the MedReason corpus derives reasoning traces from MMLU-medical, MedXpertQA and Humanity's Last Exam, three sets it also evaluates on.

Answer-format alignment was applied to 17,083 rows (38.52%): a canonical The answer is X. was appended where the letter was unambiguously recoverable from options already present in the question. Questions and reasoning traces are byte-identical to the source.

Intended use

Research and decision support. Not a medical device; not for autonomous clinical use.

Citation

@misc{wu2025medreason,
  title={MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs},
  author={Wu, Juncheng and others}, year={2025}, eprint={2504.00993}, archivePrefix={arXiv}
}