---
license: apache-2.0
base_model: openbmb/MiniCPM4-8B
tags:
  - question-generation
  - education
  - lora
  - paperprof
datasets:
  - squad
  - allenai/sciq
language:
  - en
---

# MiniCPM4-8B-PaperProf

Fine-tuned from [openbmb/MiniCPM4-8B](https://huggingface.co/openbmb/MiniCPM4-8B) for
**exam-question generation** in [PaperProf](https://huggingface.co/spaces/build-small-hackathon/PaperProf),
an AI study buddy that turns course PDFs into interactive quiz sessions.

## Training

- **Method:** QLoRA (4-bit NF4, r=16, alpha=32, all-linear targets), merged to bf16
- **Data:** ~3500 multi-task pairs in PaperProf's three production formats:
  open question generation (SQuAD), MCQ with distractors and per-option
  explanations (SciQ), and structured answer evaluation (SQuAD-derived),
  so the model is optimized for the exact tasks it serves.
- **Epochs:** 1, lr 2e-4 cosine, bf16 compute

## Usage

Drop-in replacement for the base model:

```python
from transformers import AutoTokenizer, AutoModelForCausalLM
tok = AutoTokenizer.from_pretrained("build-small-hackathon/MiniCPM4-8B-PaperProf", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("build-small-hackathon/MiniCPM4-8B-PaperProf", trust_remote_code=True, torch_dtype="bfloat16")
```

Built for the Build Small Hackathon, June 2026, by Team PaperProf (EPITA).