---
base_model: mistralai/Mistral-7B-v0.3
library_name: peft
pipeline_tag: text-generation
tags:
- lora
- transformers
- hc up
- clinical-writing
- humanization
---

# Model Card for HCUP LLM Humanizer Adapter

## Model Details
- **Base Model:** mistralai/Mistral-7B-v0.3
- **Adapter Type:** LoRA (QLoRA 4-bit)
- **Training:** DPO on clinical writing humanization pairs

## Purpose
Trained to produce humanized, non-AI-sounding clinical manuscripts using HCUP administrative data patterns.

## Usage
```python
from peft import PeftModel, AutoModelForCausalLM, AutoTokenizer
import torch

base = AutoModelForCausalLM.from_pretrained(
    "mistralai/Mistral-7B-v0.3",
    torch_dtype=torch.float16,
    device_map="auto"
)
model = PeftModel.from_pretrained(base, "Sharpener9290/hcup-llm-humanizer-v1")
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-v0.3")
```

## Training Data
- **400 instruction pairs** from HCUP corpus (nis, neds, trinetx, hcup_general)
- **50 preference pairs** for DPO humanization style transfer

## LoRA Config
- rank=16, alpha=32
- target_modules: q_proj, v_proj
- dropout=0.05