Instructions to use Melody923/DeepSeek-R1-Medicalai-923 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Melody923/DeepSeek-R1-Medicalai-923 with Transformers:

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

pipe = pipeline("text-generation", model="Melody923/DeepSeek-R1-Medicalai-923")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Melody923/DeepSeek-R1-Medicalai-923")
model = AutoModelForCausalLM.from_pretrained("Melody923/DeepSeek-R1-Medicalai-923")
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 Melody923/DeepSeek-R1-Medicalai-923 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Melody923/DeepSeek-R1-Medicalai-923"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Melody923/DeepSeek-R1-Medicalai-923",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Melody923/DeepSeek-R1-Medicalai-923

SGLang

How to use Melody923/DeepSeek-R1-Medicalai-923 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 "Melody923/DeepSeek-R1-Medicalai-923" \
    --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": "Melody923/DeepSeek-R1-Medicalai-923",
		"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 "Melody923/DeepSeek-R1-Medicalai-923" \
        --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": "Melody923/DeepSeek-R1-Medicalai-923",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use Melody923/DeepSeek-R1-Medicalai-923 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 Melody923/DeepSeek-R1-Medicalai-923 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 Melody923/DeepSeek-R1-Medicalai-923 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Melody923/DeepSeek-R1-Medicalai-923 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Melody923/DeepSeek-R1-Medicalai-923",
    max_seq_length=2048,
)

Docker Model Runner
How to use Melody923/DeepSeek-R1-Medicalai-923 with Docker Model Runner:
```
docker model run hf.co/Melody923/DeepSeek-R1-Medicalai-923
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Model ID

Medical reasoning llm

Model Details

Model Description

Developed by: Melody Zhao
Model type: LLM
Language(s) (NLP): English
License: Mit
Finetuned from model [optional]: unsloth/DeepSeek-R1-Distill-Llama-8B

How to Get Started with the Model

question = """A patient with acute appendicitis has been
ill for 5 days, with slightly relieved abdominal pain
but still feverish.
A tender mass was found in the lower right abdomen
during a physical examination. How should this be handled at this point?
"""

FastLanguageModel.for_inference(model)  # Unsloth has 2x faster inference!
inputs = tokenizer([prompt_style.format(question, "")],
                   return_tensors="pt").to("cuda")

from transformers import TextStreamer

text_streamer = TextStreamer(tokenizer)
_ = model.generate(**inputs, streamer=text_streamer, max_new_tokens=2048)
```python

[More Information Needed]

## Training Details

### Training Data

[FreedomIntelligence/medical-o1-reasoning-SFT](https://huggingface.co/datasets/FreedomIntelligence/medical-o1-reasoning-SFT)

#### Preprocessing [optional]

train_prompt_style = """Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request. Before answering, think carefully about the question and create a step-by-step chain of thoughts to ensure a logical and accurate response.

Instruction:

You are a medical expert with advanced knowledge in clinical reasoning, diagnostics, and treatment planning. Please answer the following medical question.

Question:

{}

Response:

{} {}"""




#### Training Hyperparameters

- **Training regime:**
    - fp16
    - optim="adamw_8bit",
    - weight_decay=0.01,
    - lr_scheduler_type="linear",
    - per_device_train_batch_size=2,
    - gradient_accumulation_steps=4, 
    - warmup_steps=5,
    - max_steps=60,
    - learning_rate=1e-4,
        
[More Information Needed]




#### Summary
This is fine tuned model on Medical dataset with Deepseek llama 3-8b distill

#### Hardware

nvidia L4

## Model Card Authors [optional]

Melody Zhao

## Model Card Contact

[Github](https://github.com/Melody-coder923)

Downloads last month: 5

Safetensors

Model size

8B params

Tensor type

BF16

Model tree for Melody923/DeepSeek-R1-Medicalai-923

Base model

deepseek-ai/DeepSeek-R1-Distill-Llama-8B

Finetuned

unsloth/DeepSeek-R1-Distill-Llama-8B

Finetuned

(175)

this model

Quantizations

2 models

Melody923
/

DeepSeek-R1-Medicalai-923