math-llm-demo_v2 / README.md
Joash2024's picture
feat: configure for ZeroGPU with A100
628f881

A newer version of the Gradio SDK is available: 5.9.1

Upgrade
metadata
title: Mathematics Derivative Solver V2
emoji: 🧮
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 4.44.1
app_file: app.py
pinned: false
hardware:
  zerogpu: true
  memory: 16
python_packages:
  - torch>=2.0.0
  - transformers>=4.30.0
  - accelerate>=0.20.0
  - peft==0.5.0
  - numpy>=1.21.0
  - spaces>=0.1.0

Mathematics Derivative Solver V2

This Space demonstrates our fine-tuned math model for solving derivatives. We use:

  1. Base Model: HuggingFaceTB/SmolLM2-1.7B-Instruct
  2. Our Fine-tuned Model: Joash2024/Math-SmolLM2-1.7B

Features

  • Step-by-step derivative solutions
  • LaTeX notation support
  • A100 GPU acceleration via ZeroGPU
  • Float16 precision for efficient inference

Supported Functions

  • Polynomials (x^2, x^3 + 2x)
  • Trigonometric (sin(x), cos(x))
  • Exponential (e^x)
  • Logarithmic (log(x))
  • Combinations (x e^{-x})