---
license: llama3.2
base_model: meta-llama/Llama-3.2-3B-Instruct
tags:
  - gguf
  - psychology
  - quiz-generation
  - education
---

# Llama-3.2-3B Psychology Quiz Generator (FP16 GGUF)

This is a GGUF (FP16) version of Llama-3.2-3B fine-tuned for generating psychology quiz questions.

## Model Details

- **Base Model**: meta-llama/Llama-3.2-3B-Instruct
- **LoRA Adapter**: Ghadafares2/llama3b-psych-mcqqa-lora
- **Format**: GGUF FP16
- **Size**: 5.99 GB
- **Use Case**: Psychology quiz question generation with RAG

## Usage with llama.cpp

```python
from llama_cpp import Llama

llm = Llama(
    model_path="Llama-3.2-3B-Psychology-FP16.gguf",
    n_ctx=2048,
    n_threads=8
)

# Retrieve context from psychology textbook first
context = "..." # Your RAG context here

prompt = f"""[INST] The following context is from a psychology textbook:

{context}

Based on the context above, generate 1 multiple-choice question about classical conditioning.
[/INST]"""

output = llm(prompt, max_tokens=250, temperature=0.2)
print(output['choices'][0]['text'])
```

## Important Notes

- This model was fine-tuned to work WITH RAG (textbook context)
- Best results require providing relevant psychology textbook excerpts
- For production use, consider the Q4_K_M quantized version for faster inference