from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

# Load model and tokenizer
model_name = "OsamaBinLikhon/SheikhMiniMoE-Medical"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Medical query
prompt = "What are symptoms of fever?"
inputs = tokenizer(prompt, return_tensors="pt")

# Generate response
outputs = model.generate(**inputs, max_new_tokens=100, temperature=0.7)
response = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(response)

Safety Notice

Architecture: SheikhMiniMoE - Sparse Mixture of Experts with top-k routing
Parameters: N/A
Vocabulary Size: 5000
Embedding Dimension: 256
Hidden Dimension: 512
Number of Experts: 8
Top-K Routing: 2

⚠️ This model provides medical information for educational purposes only. It is not a substitute for professional medical advice, diagnosis, or treatment. Always consult qualified healthcare providers for medical concerns.

License

Apache 2.0 - See LICENSE file for details.

Citation

bibtex

@misc{SheikhMiniMoE,
  title={SheikhMiniMoE: Bilingual Medical Assistant},
  author={MiniMax Agent},
  year={2025},
  url={https://huggingface.co/OsamaBinLikhon/SheikhMiniMoE-Medical}
}