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

Libraries

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

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

pipe = pipeline("text-generation", model="supritchaudhari/DeepSeek-R1-Medical-COT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("supritchaudhari/DeepSeek-R1-Medical-COT")
model = AutoModelForCausalLM.from_pretrained("supritchaudhari/DeepSeek-R1-Medical-COT")
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

vLLM

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

Use Docker

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

SGLang

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

Unsloth Studio

How to use supritchaudhari/DeepSeek-R1-Medical-COT with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for supritchaudhari/DeepSeek-R1-Medical-COT to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for supritchaudhari/DeepSeek-R1-Medical-COT to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for supritchaudhari/DeepSeek-R1-Medical-COT to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="supritchaudhari/DeepSeek-R1-Medical-COT",
    max_seq_length=2048,
)

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

supritchaudhari commited on Mar 12, 2025

Commit

c618322

verified ·

1 Parent(s): f008364

Trained with Unsloth

Browse files

Files changed (4) hide show

pytorch_model-00001-of-00004.bin +1 -1
pytorch_model-00002-of-00004.bin +1 -1
pytorch_model-00003-of-00004.bin +1 -1
pytorch_model-00004-of-00004.bin +1 -1

pytorch_model-00001-of-00004.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbf070f8947826046d9363bbbd947ea3becf528bd0d90e7d90e5ed96e0837c89
 size 4976718466

 version https://git-lfs.github.com/spec/v1
+oid sha256:ed8e502539362d50352220d7b92c9b0d08c8384ba62283fcfa6b87f91cc55f8f
 size 4976718466

pytorch_model-00002-of-00004.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3323032da30138253da0a50e95da89d076e9345dcee5b2fd72b2d19b2b38ca1a
 size 4999826886

 version https://git-lfs.github.com/spec/v1
+oid sha256:9ed6d22038ff10de2da1917e7837aad93f2bf4fef4ab92c54f317f236f0c3b19
 size 4999826886

pytorch_model-00003-of-00004.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96aabc45374b2b633fe21008a123ffee64ab68f57b29406ccb214a900db6fa8c
 size 4915939082

 version https://git-lfs.github.com/spec/v1
+oid sha256:f22bb237f155f2249ed7ccfc7210666d89649c28a47f7bc96ef0a53096f092f5
 size 4915939082

pytorch_model-00004-of-00004.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de54bd2d3dbd71b225aa6da126517261791d7d1fef2e5e415b73c9a4e40a6e5b
 size 1168140873

 version https://git-lfs.github.com/spec/v1
+oid sha256:f59a6756b706979b27ba5bd28922a871c12c97eae6cda4dcfbc1945aa7b6c76e
 size 1168140873