OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Models

Qizhengpt

QiZhenGPT is an open-source Chinese medical language-model project that instruction-tunes existing models with medical question-and-answer data and releases model checkpoints and evaluation data, initially focused on drug knowledge questions.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Qizhengpt — OpenViST project profile in AI Models.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use QiZhenGPT when you need a repository for examining or configuring an instruction-tuned Chinese medical model, especially for drug-knowledge question answering.

Who it is for

  • Researchers examining Chinese medical language-model tuning and drug-question evaluation.
  • Developers who want to configure a documented demo using a QiZhenGPT checkpoint and its matching base model.

Documented uses

  • Explore released instruction-tuned checkpoints based on Chinese-LLaMA-Plus, CaMA or ChatGLM.
  • Review medical instruction data and drug-question evaluation material.
  • Set up a model-specific demo using the repository’s documented steps.
Before you choose

Requirements & limits

The repository is public and identified as open source under GPL-3.0.

  • The released checkpoints are LoRA weights tied to specific base-model families; choose the matching base model and demo instructions.
  • The project’s initial evaluation focus is drug knowledge, while broader medical Q&A and record generation are described as planned application directions.
  • The repository presents MedCopilot as a distinct clinical assistant built with the model, knowledge base and clinical data.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up a QiZhenGPT model demo

Prepare and launch one of the repository’s documented model-specific demos.

Before you start

  • Python package installation through the repository’s requirements.txt.
  • The matching base model: Chinese-LLaMA-Plus-7B, ChatGLM-6B or CaMA-13B.
  • The corresponding QiZhenGPT LoRA weights placed in the lora directory.
  • Access to the QiZhenGPT repository and its referenced base-model resources.

Steps

  1. Install the project dependencies with pip install -r requirements.txt.

  2. Obtain the base model and download the matching QiZhenGPT LoRA weights into the lora directory.

  3. For Chinese-LLaMA-Plus, run sh scripts/merge_llama_plus.sh; for ChatGLM or CaMA, follow the README’s model-specific demo instructions instead.

  4. Set the model location in the relevant demo script, then run the corresponding Python demo script.

Expected outcome

The README describes launching a model-specific demo for the selected checkpoint family.

Guide limitations

  • The setup instructions differ by base model; the merge step is documented for Chinese-LLaMA-Plus, not for ChatGLM or CaMA.
  • The guide does not establish hardware requirements or guarantee successful execution.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
7 November 2026
Original website title
CMKRG/QiZhenGPT · Official homepage title · retained in its source language
How we review sourcesSuggest a correction