tomasmcm / fin-llama-33b

Source: bavest/fin-llama-33b ✦ Quant: TheBloke/fin-llama-33B-AWQ ✦ Efficient Finetuning of Quantized LLMs for Finance

  • Public
  • 263 runs
  • GitHub
  • Paper
  • License



Run time and cost

This model runs on Nvidia A40 GPU hardware. Predictions typically complete within 2 seconds.



Efficient Finetuning of Quantized LLMs for Finance

Adapter Weights | Dataset


A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's question.

### Instruction:
What is the market cap of apple?

### Input:
(context if needed)

### Response: 


Act as an Accountant

I want you to act as an accountant and come up with creative ways to manage finances. You’ll need to consider budgeting, investment strategies and risk management when creating a financial plan for your client. In some cases, you may also need to provide advice on taxation laws and regulations in order to help them maximize their profits. My first suggestion request is “Create a financial plan for a small business that focuses on cost savings and long-term investments”.

Dataset for FIN-LLAMA

The dataset is released under bigscience-openrail-m. You can find the dataset used to train FIN-LLAMA models on HF at bavest/fin-llama-dataset.


We also thank Meta for releasing the LLaMA models without which this work would not have been possible.

This repo builds on the Stanford Alpaca , QLORA, Chinese-Guanaco and LMSYS FastChat repos.

License and Intended Use

We release the resources associated with QLoRA finetuning in this repository under GLP3 license. In addition, we release the FIN-LLAMA model family for base LLaMA model sizes of 7B, 13B, 33B, and 65B. These models are intended for purposes in line with the LLaMA license and require access to the LLaMA models.


  author = {William Todt, Ramtin Babaei, Pedram Babaei},
  title = {Fin-LLAMA: Efficient Finetuning of Quantized LLMs for Finance},
  year = {2023},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{}},