Instructions to use EpistemeAI/Reason-Medical-20b-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EpistemeAI/Reason-Medical-20b-4bit with Transformers:

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

pipe = pipeline("text-generation", model="EpistemeAI/Reason-Medical-20b-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EpistemeAI/Reason-Medical-20b-4bit")
model = AutoModelForCausalLM.from_pretrained("EpistemeAI/Reason-Medical-20b-4bit", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EpistemeAI/Reason-Medical-20b-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EpistemeAI/Reason-Medical-20b-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EpistemeAI/Reason-Medical-20b-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EpistemeAI/Reason-Medical-20b-4bit

SGLang

How to use EpistemeAI/Reason-Medical-20b-4bit 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 "EpistemeAI/Reason-Medical-20b-4bit" \
    --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": "EpistemeAI/Reason-Medical-20b-4bit",
		"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 "EpistemeAI/Reason-Medical-20b-4bit" \
        --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": "EpistemeAI/Reason-Medical-20b-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use EpistemeAI/Reason-Medical-20b-4bit with Docker Model Runner:
```
docker model run hf.co/EpistemeAI/Reason-Medical-20b-4bit
```

legolasyiu commited on Jun 18

Commit

dee38cb

verified ·

1 Parent(s): c760f25

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -8

README.md CHANGED Viewed

@@ -71,17 +71,19 @@ Training may include one or more of the following stages:
 ## Training Data
-The model was trained on curated medical question-answer data intended to improve biomedical reasoning and medically relevant response quality.
-Dataset details:
-* Dataset name: `EpistemeAI/your-dataset-name`
-* Domain: medical reasoning, biomedical QA, clinical knowledge
 * Language: English
-* Format: instruction / question-answer / reasoning examples
-* Approximate size: replace with dataset size
-* Data filtering: replace with filtering method
-* Data licensing: replace with dataset license information
 ## Safety Alignment

 ## Training Data
+Training Dataset
+This model was fine-tuned using:
+* Dataset: lingshu-medical-mllm/ReasonMed
+* Dataset type: medical reasoning question-answer dataset
 * Language: English
+* License: Apache-2.0
+* Task categories: question answering and text generation
+* Domain: medical reasoning, biomedical knowledge, clinical-style QA
+* Format: question-answer examples with reasoning-oriented responses
+ReasonMed is a large-scale medical reasoning dataset containing high-quality medical question-answer examples with multi-step reasoning rationales and concise answer summaries. It was generated and curated through a multi-agent pipeline designed to improve correctness, logical coherence, and medical factuality.
 ## Safety Alignment