Arithmo-Mistral-7B / README.md
akjindal53244's picture
Update README.md
404abbd
|
raw
history blame
2.32 kB
metadata
license: apache-2.0
language:
  - en
tags:
  - Mathematical Reasoning

Model Card for Model ID

Code License Model Weight License Python 3.9+

This model is instruction-tuned Mistral-7B model using QLoRA on single RTX 4090 GPU. Model is tuned to reason and answer mathematical problems. Model is also capable of writing a Python program that upon compilation prints answer to the question. To generate python program, you can ask model to write a Python program (as part of prompt) along with question. Refer to Results section for examples.

Model Details

It is a Instruction-tuned Mistral-7B and performs mathematical reasoning and optionally write a Python program.

Model Description

How to query the model

Arithmo-Mistral-7B is trained with the following format:

CoT Format:

Question: <question>

Answer:

PoT Format:

Question: <question> <python_prompt>

Answer:

It will perform best if queried in this way.

How to Get Started with the Model

Model is compatibale with Huggingface. I will publish a generation/inference script soon. Model inference on CPU also works; I have tested it on Macbook M1 Pro. GPU inference is much faster than CPU inference.

Results

Here are sample screenshots of model output for few questions :)

image/png

image/png

image/png