QuanLLM Field Branch

QuanLLM-v0.1-qm Quantum Mechanics Exam Prep Expert

QuanLLM-v0.1-qm is the first experimental field branch of the QuanLLM main product (an AI expert for quantum physics research and teaching), focused on university-level quantum mechanics final exam preparation. Built on the MiniMind architecture, it targets concept explanation, formula derivation, and exercise solving.

64M
Parameters
768
Hidden Dim
Local
Fully Deployable
Open Source
MiniMind Architecture
FIELD BRANCH

Quantum Mechanics · Final Exam Prep

This branch focuses on undergraduate quantum mechanics final exam scenarios. It is an early exploration of QuanLLM’s teaching application direction and validates our complete engineering pipeline from textbooks to model to interaction.

Mainline: QuanLLM Version: v0.1 Direction: Quantum Mechanics Teaching Status: Experimental

Built for Quantum Mechanics Final Exam Prep

General-purpose LLMs can answer some quantum mechanics questions, but they often fall short in formula rigor, textbook consistency, and exam focus. v0.1-qm attempts to deploy a more focused model using domain-specific data.

🎯

Exam-Oriented

Targets high-frequency final exam topics: concept explanation, formula derivation, calculation problems, and proof questions, with structured responses.

🔒

Fully Local

Can be fully deployed and run on a Windows PC with an NVIDIA RTX 5090. Data never leaves your machine.

📚

Textbook-Driven

Supports automatic extraction from PDF, Word, and TXT textbooks, as well as ready-made QA datasets such as StackExchange.

🚀

Open & Extensible

Built on MiniMind, with open deployment and data-processing scripts that can be extended to other quantum physics branches.

What v0.1-qm Can Do

Concept Explanation

Explains core concepts such as wave functions, the uncertainty principle, representation transformations, and identical particles in clear language to build intuition.

What is a Hermitian operator?
A Hermitian operator satisfies A† = A, has real eigenvalues, and corresponds to physical observables...

Formula Derivation

Step-by-step derivations of the Schrödinger equation, ladder operators, angular momentum commutation relations, and more.

Exercise Solving

Provides problem-solving strategies and step-by-step solutions for harmonic oscillators, hydrogen atoms, perturbation theory, and other typical exam topics.

WebUI Chat

A Streamlit-based chat interface with adjustable temperature, Top-p, and history length, supporting streaming output.

Local Deployment

One-click scripts for data generation, continued pre-training, SFT, and inference. Supports the RTX 5090 Blackwell architecture.

From Textbook to Your Own Model

01

Prepare Textbook

Put your quantum mechanics textbook (PDF / Word / TXT) into the raw_books/ directory.

02

Generate Data

Automatically extract pre-training corpus, heuristically generate QA pairs, or build SFT data from existing datasets.

03

Deploy Model

Continue pre-training + full-parameter SFT from MiniMind official weights, or run SFT-only.

04

Chat & Test

Interact with the model via command line or the Streamlit WebUI to verify response quality.

Experience QuanLLM-v0.1-qm

The current demo is static. Full conversational functionality requires deploying the model locally and accessing it through the WebUI.

QuanLLM-v0.1-qm Chat
👤
Explain the energy level formula for a 1D infinite potential well.
⚛️

For a 1D infinite potential well of width a, solving the time-independent Schrödinger equation gives:

En = (n²π²ℏ²)/(2ma²), n = 1, 2, 3, ...

Key points:

  • Energy is quantized, not continuous.
  • The ground-state energy is non-zero (zero-point energy).
  • Energy scales inversely with : the narrower the well, the higher the energy.

💡 Tip: Download the project and deploy the model locally to start real conversations. This page is for product demonstration only.

Start Building Your Quantum Mechanics AI Tutor

Download QuanLLM-v0.1-qm and deploy your own model using your textbooks or QA datasets.