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.

Safetensors

Model size

1.1B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ali77sina/tinyLlama-SEC-RAG-FT

Base model

Finetuned

(259)

this model