fabriceyhc/Ministral-DrugDetector-14B-MFI

from transformers import Mistral3ForConditionalGeneration, MistralCommonBackend
from peft import PeftModel
import torch

# Load base model
base_model = "mistralai/Ministral-3-14B-Instruct-2512"
model = Mistral3ForConditionalGeneration.from_pretrained(
    base_model,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

# Load LoRA adapter
model = PeftModel.from_pretrained(model, "fabriceyhc/Ministral-DrugDetector-14B-MFI")

# Load tokenizer
tokenizer = MistralCommonBackend.from_pretrained("fabriceyhc/Ministral-DrugDetector-14B-MFI")

# Task instruction
task_instruction = """### Task Description:
Please carefully review the following medical note and identify illicit drug use.

**CRITICAL RULES:**
1. **Positive drug test -> ALWAYS ILLICIT** (unless in medication list)
2. **PMH/History of use -> ILLICIT** (even if historical)
3. **Substance use disorder -> ILLICIT**
4. **Patient self-reports (endorses, reports, admits) -> ILLICIT**
5. **Prescribed/medical use -> NOT ILLICIT**

**Drugs to identify:**
- **Methamphetamine**: Illicit amphetamine use (not prescribed Adderall)
- **Fentanyl**: Illicit fentanyl use (not prescribed patches/procedural)
- **Injection Drug Use**: IV drug use (IVDU, IVDA)

**Temporal Classification:**
- **Current**: Present tense, recent use, positive test
- **Historical**: Past tense, "history of", "former user"
- **Unknown**: Timeframe unclear

### Desired Format:
Methamphetamine Illicit Use: <True/False/Unknown>
Fentanyl Illicit Use: <True/False/Unknown>
Injection Drug Use: <True/False/Unknown>
Methamphetamine Temporal Status: <Current/Historical/Unknown/N/A>
Fentanyl Temporal Status: <Current/Historical/Unknown/N/A>
Injection Drug Use Temporal Status: <Current/Historical/Unknown/N/A>"""

# Example note
note_text = "Patient reports using meth daily for the past 2 weeks. Denies IV drug use."

# Format prompt
prompt = f"""<s>[INST] {task_instruction}

### The medical note to evaluate:
{note_text}

### Answer: [/INST]"""

# Generate
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
    **inputs,
    max_new_tokens=200,
    do_sample=False,
    pad_token_id=tokenizer.eos_token_id
)

# Decode
result = tokenizer.decode(outputs[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)
print(result)

Methamphetamine Illicit Use: True
Fentanyl Illicit Use: False
Injection Drug Use: False
Methamphetamine Temporal Status: Current
Fentanyl Temporal Status: N/A
Injection Drug Use Temporal Status: N/A

@misc{ministral-drugdetector-14b-mfi-2025,
  author = {Hanna-Chang, Fabrice},
  title = {Ministral-DrugDetector-14B-MFI},
  year = {2025},
  publisher = {HuggingFace},
  url = {https://huggingface.co/fabriceyhc/Ministral-DrugDetector-14B-MFI}
}