You can deploy this model and start earning money today!

Abiral7/
FinAssistant

transformers

safetensors

text-generation-inference

unsloth

llama

trl

unsloth/llama-3-8b-bnb-4bit

finetune

apache-2.0

endpoints_compatible

Views

No views yet

FinAssistant

Introduction

FinAssistant is an AI-powered financial assistant model designed to answer financial questions and assist in improving financial literacy. It is based on the unsloth/llama-3-8b-bnb-4bit model and fine-tuned on the AdaptLLM/ConvFinQA dataset.

Model Details

Model Name: FinAssistant
Developer: Abiral7 (Individual)
Base Model: unsloth/llama-3-8b-bnb-4bit
Model Type: Language Model
Language(s): English
License: apache-2.0

Intended Use

FinAssistant is designed to:

Answer financial questions
Provide general financial advice
Assist in improving financial literacy

Primary use cases include:

Answering Financial Questions: Providing information and guidance on various finance-related issues.
Financial Advice: Giving general advice on maintaining financial stability.

Training Data

This model was fine-tuned on the AdaptLLM/ConvFinQA dataset.

Performance and Limitations

Currently, no specific performance metrics are available for this model.

Limitations and Biases

Users should be aware of the following limitations:

Accuracy and Reliability:
- Not a Substitute for Professional Advice: The model provides general financial information but is not a licensed professional. Users should consult financial advisors for serious concerns.
- Potential for Incorrect Information: AI-generated responses may occasionally be incorrect or outdated.
Biases:
- Training Data Bias: The model may reflect biases present in the training data, potentially leading to skewed or inappropriate responses.
- Cultural Sensitivity: Responses may not account for cultural differences and may inadvertently provide advice that is culturally insensitive or inappropriate.
Scope of Knowledge:
- Limited to Training Data: The model's knowledge is limited to the data it was trained on and may not include the latest financial data and information.

Ethical Considerations:

Users are strongly advised to:

Use this model as a supplementary tool, not a replacement for professional advice.
Protect their privacy by avoiding sharing sensitive personal information.
Verify any critical information or advice with licensed professionals.

Installation

To use FinAssistant, you need to install the following dependencies:

bash

pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"
pip install --no-deps "xformers<0.0.27" "trl<0.9.0" peft accelerate bitsandbytes

Usage

Here's a basic example of how to use the MedAssistant model:

python

from unsloth import FastLanguageModel
from transformers import AutoModel, TextStreamer
from peft import PeftModel, PeftConfig

# Load base model
model_name = "unsloth/llama-3-8b-bnb-4bit"
base_model, tokenizer = FastLanguageModel.from_pretrained(
    model_name=model_name,
    max_seq_length=2048,
    load_in_4bit=True
)

# Load adapter configuration
adapter_name = "Abiral7/FinAssistant"
peft_config = PeftConfig.from_pretrained(adapter_name)

# Apply adapter to base model
model = PeftModel.from_pretrained(base_model, adapter_name)

FastLanguageModel.for_inference(model) # Enable native 2x faster inference

# Example usage
inputs = tokenizer(
[

"""     #System:

        You are a Financial LLM, that has knowledge in the Financial Industry and can do Financial Analysis. 
        Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. 
        Please ensure that your responses are socially unbiased and positive in nature.\n\nIf a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. 
        If you don't know the answer to a question, please don't share false information.



        #User:

        Investor performance chart: The subsequent chart and accompanying data are not considered "soliciting material" or "filed" with the SEC. This information should not be incorporated by reference into future filings under the Securities Act of 1933 or Securities Exchange Act of 1934, as amended, unless explicitly incorporated by the company. The chart depicts a 5-year comparison of cumulative total investor returns for our Class B common stock, S&P 500 index, and Dow Jones Transportation Average. It compares total cumulative return on investment (quarterly stock price changes plus reinvested dividends) assuming $100 invested on 12/31/2001 in each.
        Cumulative 5-year return comparison:
        [Chart values from $40 to $200, years 2001-2006]
        S&P 500, UPS, DJ Transport lines
        Data table:
        Date | UPS | S&P 500 | DJ Transport
        12/31/01 | $100.00 | $100.00 | $100.00
        12/31/02 | $117.19 | $77.90 | $88.52
        12/31/03 | $140.49 | $100.24 | $116.70
        12/31/04 | $163.54 | $111.15 | $149.06
        12/31/05 | $146.35 | $116.61 | $166.42
        12/31/06 | $148.92 | $135.02 | $182.76
        Equity compensation plan information: As of 12/31/2006, the following data pertains to plans authorizing our Class A common stock issuance. Class B common stock is not authorized under these plans. What was UPS Inc.'s return in 2006? 148.92 and what was the change in UPS Inc.'s return from 2001 to 2006?


        #Assistant


        """
], return_tensors = "pt").to("cuda")

from transformers import TextStreamer
text_streamer = TextStreamer(tokenizer)
_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 5000)

Hardware Requirements

To run this model efficiently, the following hardware is recommended:

GPU: A modern GPU with at least 8GB of VRAM, preferably an NVIDIA GPU with CUDA support.
CPU: A multi-core CPU for preprocessing and managing data.
Memory (RAM): At least 16GB of RAM.
Storage: Sufficient SSD storage for model weights and datasets.

Feedback and Issues

Users can provide feedback or report issues related to the model: Use the "Discussions" tab on this Hugging Face model page to ask questions, provide feedback, or report issues directly to the model developer or community.