---
license: apache-2.0
base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
---

This model is fine-tuned for RAG for SEC filings, using synthetically created QA pairs with GPT-4-turbo. 

The format is as follows:

```
text = f"### Question: {question}, ### Context: {ctx}, ### Answer: {answer}"
```

**NOTE**: This model was fine-tuned using the full-model (bfloat16), and not adapters.