Instructions to use anand-subramanian/DeepSeek-R1-Medical-COT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anand-subramanian/DeepSeek-R1-Medical-COT with Transformers:

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

pipe = pipeline("text-generation", model="anand-subramanian/DeepSeek-R1-Medical-COT")
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("anand-subramanian/DeepSeek-R1-Medical-COT")
model = AutoModelForCausalLM.from_pretrained("anand-subramanian/DeepSeek-R1-Medical-COT", 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 anand-subramanian/DeepSeek-R1-Medical-COT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "anand-subramanian/DeepSeek-R1-Medical-COT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "anand-subramanian/DeepSeek-R1-Medical-COT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/anand-subramanian/DeepSeek-R1-Medical-COT

SGLang

How to use anand-subramanian/DeepSeek-R1-Medical-COT 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 "anand-subramanian/DeepSeek-R1-Medical-COT" \
    --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": "anand-subramanian/DeepSeek-R1-Medical-COT",
		"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 "anand-subramanian/DeepSeek-R1-Medical-COT" \
        --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": "anand-subramanian/DeepSeek-R1-Medical-COT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use anand-subramanian/DeepSeek-R1-Medical-COT with Docker Model Runner:
```
docker model run hf.co/anand-subramanian/DeepSeek-R1-Medical-COT
```

Uploaded model

Developed by: anand-subramanian
License: apache-2.0
Finetuned from model : unsloth/deepseek-r1-distill-llama-8b-unsloth-bnb-4bit
Supervised Fine Tuning based on first 500 responses in FreedomIntelligence/medical-o1-reasoning-SFT

Model Repos

anand-subramanian/DeepSeek-R1-Medical-COT contains the base model
anand-subramanian/DeepSeek-R1-Medical-COT-lora contains files resulting from the fune tuning on this base model.

Instructions for building this model based on this Datacamp article.

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 10