You can deploy this model and start earning money today!

OUSSNDOU77/
SamaDoctor-R1

Name: SamaDoctor-R1
Availability: InStock

mit

Views

No views yet

SamaDoctor-R1 🩺🤖

SamaDoctor‑R1 is a fine-tuned version of deepseek-ai/deepseek-llm-7b-instruct, specialized in medical reasoning using chain-of-thought (CoT) prompting.

🧠 Powered by DeepSeek-R1 architecture
🏥 Fine-tuned on medical CoT dataset
🌍 "Sama" means "my" in Wolof, symbolizing care, trust, and proximity

💡 Use Cases

Diagnostic explanation
Medical student tutoring
Clinical decision support (research context)

🚀 Model Specs

Base: deepseek-ai/deepseek-llm-7b-instruct
Format: LoRA / PEFT
Finetuned using: Unsloth + Hugging Face Trainer
Dataset: med-cot

📥 How to Use

python

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("OUSSNDOU77/SamaDoctor-R1")
tokenizer = AutoTokenizer.from_pretrained("OUSSNDOU77/SamaDoctor-R1")

prompt = "<s> You are a medical reasoning assistant. <think> What are the signs of appendicitis? </think>"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))