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

Libraries

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

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

pipe = pipeline("text-generation", model="sripathim/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("sripathim/DeepSeek-R1-Medical-COT")
model = AutoModelForCausalLM.from_pretrained("sripathim/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 Settings

vLLM

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

Use Docker

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

SGLang

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

Unsloth Studio

How to use sripathim/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 sripathim/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 sripathim/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 sripathim/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="sripathim/DeepSeek-R1-Medical-COT",
    max_seq_length=2048,
)

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

sripathim commited on Feb 23, 2025

Commit

a2776f4

verified ·

1 Parent(s): 09be34a

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 sha256:32910bd592b403db3bfed9cf300e46df1abd434e83cfe2b0bcdb83e06c546cd9
 size 4976718466

 version https://git-lfs.github.com/spec/v1
+oid sha256:695070dd06a863462190aa246eba9cb2381d09c991e1ff8d133b2b8d7db71b2e
 size 4976718466

pytorch_model-00002-of-00004.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03c8bec4d0ed40e43dab05ffd12fdcc33f3542f97240af48642ddfe14b0d4ec5
 size 4999826886

 version https://git-lfs.github.com/spec/v1
+oid sha256:d85d5d57f37292c9d27526287d808080eeeec127b3933ad25da6ee5ac389f2d3
 size 4999826886

pytorch_model-00003-of-00004.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:839db9ab3779524f290f3192f7cb574f1b1660afa212e66f15fcd86f45d0f535
 size 4915939082

 version https://git-lfs.github.com/spec/v1
+oid sha256:2e40346ff15ae87b672aaae35664b79786468207dcafa3f1b2d5a2eb8ae6b5d8
 size 4915939082

pytorch_model-00004-of-00004.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ded6e28e50cbf83c165aac872395fcb168a30ae185c084aae5a0f7a45f84df3b
 size 1168140873

 version https://git-lfs.github.com/spec/v1
+oid sha256:1cd9410aa30a3e2c8733a4a08e6a398233ec4e82980df70854c560a122a8403d
 size 1168140873