Qiskit Code Assistant

LLM Qiskit Code Assistant bertujuan untuk menjadikan pengkomputeran kuantum lebih mudah diakses oleh pengguna Qiskit baharu dan meningkatkan pengalaman pengekodan bagi pengguna semasa. Ia dilatih menggunakan jutaan token teks dari Qiskit SDK, bertahun-tahun contoh kod Qiskit, dan ciri IBM Quantum®. Qiskit Code Assistant boleh membantu aliran kerja pembangunan kuantum anda dengan menawarkan cadangan yang dijana oleh LLM berdasarkan model IBM Granite dan model sumber terbuka lain, yang menggabungkan ciri dan fungsi terkini dari IBM®.

Nota

Ingin terus ke arahan pemasangan? Pergi ke bahagian Pasang Qiskit Code Assistant.
Jika anda ada maklum balas atau ingin menghubungi pasukan pembangun, gunakan saluran Qiskit Slack Workspace atau repositori GitHub awam yang berkaitan.

Model Bahasa Besar (LLM) di sebalik Qiskit Code Assistant

Untuk memberikan cadangan kod, Qiskit Code Assistant menggunakan Model Bahasa Besar (LLM). Dalam kes ini, Qiskit Code Assistant kini bergantung pada model mistral-small-3.2-24b-qiskit, yang dibina atas model Mistral-Small-3.2-24B-Qiskit. Model mistral-small-3.2-24b-qiskit meningkatkan keupayaan penjanaan kod model Mistral-Small-3.2-24B-Instruct-2506 untuk Qiskit melalui pra-latihan lanjutan dan penalaan halus pada data Qiskit berkualiti tinggi, serta komit Python dan chat. Untuk maklumat lanjut tentang keluarga model Mistral AI, rujuk dokumentasi Mistral AI. Untuk maklumat lanjut tentang model .*-qiskit, lihat Qiskit Code Assistant: Training LLMs for generating Quantum Computing Code.

LLM khusus kami untuk Qiskit juga tersedia sebagai model sumber terbuka. Semak semua model yang tersedia di https://huggingface.co/Qiskit.

Penanda aras Qiskit HumanEval dan Qiskit HumanEval Hard

Untuk menguji mistral-small-3.2-24b-qiskit dan model-model lain, kami bekerjasama dengan Qiskit Advocates dan pakar untuk mencipta penanda aras berasaskan pelaksanaan yang dipanggil Qiskit HumanEval (QHE) dan Qiskit HumanEval Hard (QHE Hard), dan menjalankannya pada model-model tersebut. Penanda aras ini serupa dengan HumanEval, termasuk pelbagai masalah kod yang mencabar untuk diselesaikan, semuanya berdasarkan pustaka Qiskit rasmi.

Penanda aras ini terdiri daripada kira-kira 150 ujian, setiap satu dibuat dari definisi fungsi, diikuti oleh docstring yang memperincikan tugas yang diperlukan model untuk diselesaikan. Setiap contoh juga termasuk penyelesaian kanonik rujukan, serta ujian unit, untuk menilai ketepatan penyelesaian yang dihasilkan. Terdapat tiga tahap kesukaran untuk ujian: asas, pertengahan, dan sukar. Penanda aras Qiskit HumanEval Hard ialah variasi penanda aras Qiskit HumanEval, tetapi mengeluarkan maklumat berkaitan import kod, supaya LLM perlu mengetahui import kaedah atau kelas yang betul. Perubahan ini menjadikan set data jauh lebih mencabar bagi LLM, menurut ujian dan keputusan awal kami.

Set data untuk Qiskit HumanEval dan Qiskit HumanEval Hard tersedia di laman web ini: Qiskit HumanEval dan Qiskit HumanEval. Anda boleh menyumbang kepada pembangunan penanda aras ini di repositori GitHub.

Pasang Qiskit Code Assistant

Pelajari cara memasang, mengkonfigurasi, dan menggunakan mana-mana model Qiskit Code Assistant pada mesin tempatan anda.

Muat turun dari laman web Hugging Face

Ikuti langkah-langkah ini untuk memuat turun mana-mana model berkaitan Qiskit Code Assistant dari laman web Hugging Face:

Navigasi ke halaman model Qiskit yang dikehendaki di Hugging Face.
Pergi ke tab Files and Versions dan muat turun fail model safetensors atau GGUF.

Muat turun menggunakan Hugging Face CLI

Untuk memuat turun mana-mana model Qiskit Code Assistant yang tersedia menggunakan Hugging Face CLI, ikuti langkah-langkah ini:

Pasang Hugging Face CLI
Log masuk ke akaun Hugging Face anda
```
huggingface-cli login
```

Muat turun model yang anda suka dari senarai sebelumnya

huggingface-cli download <HF REPO NAME> <MODEL PATH> --local-dir <LOCAL PATH>

Gunakan model Qiskit Code Assistant secara tempatan melalui Ollama secara manual

Terdapat pelbagai cara untuk menggunakan dan berinteraksi dengan model Qiskit Code Assistant yang dimuat turun. Panduan ini menunjukkan penggunaan Ollama seperti berikut: sama ada dengan aplikasi Ollama menggunakan integrasi Hugging Face Hub atau model tempatan, atau dengan pakej llama-cpp-python.

Menggunakan aplikasi Ollama

Aplikasi Ollama menyediakan penyelesaian mudah untuk menjalankan LLM secara tempatan. Ia mudah digunakan, dengan CLI yang menjadikan keseluruhan proses persediaan, pengurusan model, dan interaksi agak mudah. Ia sesuai untuk eksperimen pantas dan untuk pengguna yang mahu mengendalikan butiran teknikal yang lebih sedikit.

Pasang Ollama

Muat turun aplikasi Ollama
Pasang fail yang dimuat turun
Lancarkan aplikasi Ollama yang dipasang

info
Aplikasi berjalan dengan jayanya apabila ikon Ollama muncul dalam bar menu desktop. Anda juga boleh mengesahkan perkhidmatan sedang berjalan dengan pergi ke http://localhost:11434/.
Cuba Ollama dalam terminal anda dan mula menjalankan model. Sebagai contoh:
```
ollama run hf.co/Qiskit/Qwen2.5-Coder-14B-Qiskit
```

Sediakan Ollama menggunakan integrasi Hugging Face Hub

Integrasi Ollama/Hugging Face Hub menyediakan cara untuk berinteraksi dengan model yang dihoskan di Hugging Face Hub tanpa perlu mencipta modelfile baharu atau memuat turun fail GGUF atau safetensors secara manual. Fail template dan params lalai sudah disertakan untuk model di Hugging Face Hub.

Pastikan aplikasi Ollama sedang berjalan.
Pergi ke halaman model yang dikehendaki, dan salin URL. Sebagai contoh, https://huggingface.co/Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF.

Dari terminal anda, jalankan arahan:

ollama run hf.co/Qiskit/Qwen2.5-Coder-14B-Qiskit

Anda boleh menggunakan model hf.co/Qiskit/Qwen2.5-Coder-14B-Qiskit atau mana-mana model GGUF rasmi yang disyorkan masa kini hf.co/Qiskit/mistral-small-3.2-24b-qiskit-GGUF atau hf.co/Qiskit/granite-3.3-8b-qiskit-GGUF.

Sediakan Ollama dengan model GGUF Qiskit Code Assistant yang dimuat turun secara manual

Jika anda telah memuat turun model GGUF secara manual seperti https://huggingface.co/Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF dan anda ingin bereksperimen dengan templat dan parameter yang berbeza, anda boleh ikuti langkah-langkah ini untuk memuatkannya ke dalam aplikasi Ollama tempatan anda.

Cipta Modelfile dengan memasukkan kandungan berikut dan pastikan anda mengemas kini <PATH-TO-GGUF-FILE> kepada laluan sebenar model yang anda muat turun.

FROM <PATH-TO-GGUF-FILE>
TEMPLATE """{{ if .System }}
System:
{{ .System }}

{{ end }}{{ if .Prompt }}Question:
{{ .Prompt }}

{{ end }}Answer:
```python{{ .Response }}
"""

PARAMETER stop "Question:"
PARAMETER stop "Answer:"
PARAMETER stop "System:"
PARAMETER stop "```"

PARAMETER temperature 0
PARAMETER top_k 1

Run the following command to create a custom model instance based on the Modelfile.
```
ollama create Qwen2.5-Coder-14B-Qiskit -f ./path-to-model-file
```
nota
This process may take some time for Ollama to read the model file, initialize the model instance, and configure it according to the specifications provided.

Run the Qiskit Code Assistant model manually downloaded in Ollama

After the Qwen2.5-Coder-14B-Qiskit model has been set up in Ollama, run the following command to launch the model and interact with it in the terminal (in chat mode).

ollama run Qwen2.5-Coder-14B-Qiskit

Some useful commands:

ollama list - List models on your computer
ollama rm Qwen2.5-Coder-14B-Qiskit - Delete the model
ollama show Qwen2.5-Coder-14B-Qiskit - Show model information
ollama stop Qwen2.5-Coder-14B-Qiskit - Stop a model that is currently running
ollama ps - List which models are currently loaded

Manually deploy the Qiskit Code Assistant models in local through the llama-cpp-python package

An alternative to the Ollama application is the llama-cpp-python package, which is a Python binding for llama.cpp. It gives you more control and flexibility to run the GGUF model locally, and is ideal for users who wish to integrate the local model in their workflows and Python applications.

Install llama-cpp-python
Interact with the model from within your application using llama_cpp. For example:

from llama_cpp import Llama

model_path = <PATH-TO-GGUF-FILE>

model = Llama(
        model_path,
        seed=17,
        n_ctx=10000,
        n_gpu_layers=37, # to offload in gpu, but put 0 if all in cpu
    )

input = 'Generate a quantum circuit with 2 qubits'
raw_pred = model(input)["choices"][0]["text"]

You can also add text generation parameters to the model to customize the inference:

generation_kwargs = {
        "max_tokens": 512,
        "echo": False, # Echo the prompt in the output
        "top_k": 1
    }

raw_pred = model(input, **generation_kwargs)["choices"][0]["text"]

Manually deploy the Qiskit Code Assistant models in local through llama.cpp

Use the `llama.cpp` library

Another alternative is to use llama.cpp, an open-source library for performing LLM inference on a CPU with minimal setup. It provides low-level control over the model execution and is typically run from the command line, pointing to a local GGUF model file.

There are several ways to install llama.cpp on your machine:

Install llama.cpp using brew, nix, or winget
Run with Docker: See out the Docker documentation by llama.cpp team
Download pre-built binaries from the releases page
Build from source by cloning this repository

Once installed, you can use llama.cpp to interact with GGUF models in conversation mode as follows:

# Use a local model file
llama-cli -m my_model.gguf -cnv

# Or download and run a model directly from Hugging Face
llama-cli -hf Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF -cnv

You can also launch an OpenAI-compatible API server for the model in the following way:

llama-server -hf Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF

Advanced parameters

With the llama-cli program, you can control the model generation using command-line options. For example, you can provide an initial “system” prompt using the -p/--prompt flag. In conversation mode (-cnv), this initial prompt acts as the system message. Otherwise, you can simply prepend any desired instruction to your prompt text. You can also adjust sampling parameters - for instance: temperature (--temp), top-k (--top-k), top-p (--top-p), repetition penalty (--repeat-penalty), and the seed to use (--seed). The following is an example invocation using these options:

llama-cli -hf Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF \
  -p "You are a friendly assistant." -cnv \
  --temp 0.7 \
  --top-k 50 \
  --top-p 0.95 \
  --repeat-penalty 1.1 \
  --seed 42

To ensure proper functionality of our Qiskit models, we recommend using the system prompt provided in our HF GGUF repositories: system prompt for mistral-small-3.2-24b-qiskit-GGUF, Qwen2.5-Coder-14B-Qiskit-GGUF, granite-3.3-8b-qiskit-GGUF, and granite-3.2-8b-qiskit-GGUF.

Manually connect Continue (VS Code)

Continue (VS Code)

1. Install the extension

Open VS Code, go to Extensions (Cmd+Shift+X), search Continue, install it.

2. Open the config

Click the Continue icon in the sidebar, then click the gear icon, or open the command palette (Cmd+Shift+P) and run Continue: Open Config File.

This opens ~/.continue/config.yaml (or config.json in older versions).

3. Configure the model

Add the following to config.yaml:

models:
  - name: Qiskit Code Assistant
    provider: ollama
    model: mistral-small-3.2-24b-qiskit
    apiBase: http://localhost:11434

This makes the Qiskit model available in the chat panel (sidebar conversations, inline Q&A) and for inline edit commands.

4. Test it

Chat: Open the Continue panel in the sidebar and ask a question (e.g., "How do I create a parameterized circuit in Qiskit?")
Inline edit: Select a block of code, press Cmd+I (Mac) or Ctrl+I (Linux/Windows)

Manually connect Jupyter AI (JupyterLab)

Jupyter AI (JupyterLab)

Note: These instructions cover Jupyter AI v2.x.

1. Install Jupyter AI and the Ollama provider

pip install "jupyter-ai<3" langchain-ollama

The "jupyter-ai<3" pin ensures you get v2.x. The langchain-ollama package is required for Jupyter AI to detect Ollama as a provider. Without it, Ollama will not appear in the settings panel.

Then restart JupyterLab.

2. Configure the chat model

Open JupyterLab and click the chat icon in the left sidebar. In the settings panel:

Under Language model, select Ollama as the provider.
Enter mistral-small-3.2-24b-qiskit as the model name.
No API key is needed for Ollama (leave the field empty).
Click the back arrow to start chatting.

3. Use the `%%ai` magic command

The %%ai magic lets you query the model directly in notebook cells.

%load_ext jupyter_ai_magics

Then in a cell:

%%ai ollama:mistral-small-3.2-24b-qiskit
Write a function that implements Grover's algorithm using Qiskit

4. Custom Ollama host (optional)

By default, Jupyter AI connects to http://127.0.0.1:11434. If your Ollama server runs on a different address or port:

In the chat UI: Set the "Base API URL" field in the AI settings panel.

Manually connect OpenCode (Terminal)

OpenCode (Terminal)

1. Install OpenCode

curl -fsSL https://opencode.ai/install | bash

2. Configure the Qiskit model

Create an opencode.json file in your project root (or ~/.config/opencode/opencode.json for a global config):

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "ollama": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Ollama (local)",
      "options": {
        "baseURL": "http://localhost:11434/v1"
      },
      "models": {
        "mistral-small-3.2-24b-qiskit": {
          "name": "Qiskit Code Assistant"
        }
      }
    }
  }
}

3. Select the model

Launch OpenCode in your project directory:

opencode

Inside the TUI, run the /models command and select Qiskit Code Assistant from the list.

4. Test it

Ask a question directly in the chat, for example: "Define a Bell circuit and run it using QiskitRuntimeService"

Available models

Current models

These are the latest recommended models for use with Qiskit Code Assistant:

Qiskit/mistral-small-3.2-24b-qiskit - Released October 2025
Qiskit/Qwen2.5-Coder-14B-Qiskit - Released June 2025
qiskit/granite-3.3-8b-qiskit - Released June 2025
qiskit/granite-3.2-8b-qiskit - Released June 2025

GGUF models (recommended for personal environments/laptops)

GGUF format models are optimized for local use and require fewer computational resources:

mistral-small-3.2-24b-qiskit-GGUF – Released October 2025
Trained with Qiskit data up to version 2.1
Qiskit/Qwen2.5-Coder-14B-Qiskit-GGUF – Released June 2025
Trained with Qiskit data up to version 2.0
qiskit/granite-3.3-8b-qiskit-GGUF – Released June 2025
Trained with Qiskit data up to version 2.0
qiskit/granite-3.2-8b-qiskit-GGUF – Released June 2025
Trained with Qiskit data up to version 2.0

The Open Source Qiskit Code Assistant models are available in safetensors or GGUF file format and can be downloaded from the Hugging Face as explained below.

Qiskit versions used for training

Model						Benchmark Metrics					Release date	Trained on Qiskit version
	QiskitHumanEval-Hard	QiskitHumanEval	HumanEval	ASDiv	MathQA	SciQ	MBPP	IFEval	CrowsPairs (English)	TruthfulQA (MC1 acc)
mistral-small-3.2-24b-qiskit	32.45	47.02	77.49	3.77	49.68	97.50	64.00	48.44	67.08	39.41	January 2026	2.2
Qwen2.5-Coder-14B-Qiskit	25.17	49.01	91.46	4.21	53.90	97.00	77.60	49.64	65.18	37.82	June 2025	2.0
granite-3.3-8b-qiskit	14.57	27.15	62.80	0.48	38.66	93.30	52.40	59.71	59.75	39.05	June 2025	2.0
granite-3.2-8b-qiskit	9.93	24.50	57.32	0.09	41.41	96.30	51.80	60.79	66.79	40.51	June 2025	2.0
granite-8b-qiskit-rc-0.10	15.89	38.41	59.76	—	—	—	—	—	—	—	February 2025	1.3
granite-8b-qiskit	17.88	44.37	53.66	—	—	—	—	—	—	—	November 2024	1.2

Note: All models listed in the benchmark table were evaluated using their respective system prompt, defined in their Hugging Face model.

Deprecated models

These models are no longer actively maintained but remain available:

qiskit/granite-8b-qiskit-rc-0.10 - Released February 2025 (deprecated)
qiskit/granite-8b-qiskit - Released November 2024 (deprecated)

More information and citations

To learn more about Qiskit Code Assistant, the Qiskit HumanEval, or Qiskit HumanEval Hard benchmarks, and cite them in your scientific publications, review these recommended citations:

@misc{2405.19495,
Author = {Nicolas Dupuis and Luca Buratti and Sanjay Vishwakarma and Aitana Viudes Forrat and David Kremer and Ismael Faro and Ruchir Puri and Juan Cruz-Benito},
Title = {Qiskit Code Assistant: Training LLMs for generating Quantum Computing Code},
Year = {2024},
Eprint = {arXiv:2405.19495},
}

@misc{2406.14712,
Author = {Sanjay Vishwakarma and Francis Harkins and Siddharth Golecha and Vishal Sharathchandra Bajpe and Nicolas Dupuis and Luca Buratti and David Kremer and Ismael Faro and Ruchir Puri and Juan Cruz-Benito},
Title = {Qiskit HumanEval: An Evaluation Benchmark For Quantum Code Generative Models},
Year = {2024},
Eprint = {arXiv:2406.14712},
}

@misc{2508.20907,
Author = {Nicolas Dupuis and Adarsh Tiwari and Youssef Mroueh and David Kremer and Ismael Faro and Juan Cruz-Benito},
Title = {Quantum Verifiable Rewards for Post-Training Qiskit Code Assistant},
Year = {2025},
Eprint = {arXiv:2508.20907},
}

Model Bahasa Besar (LLM) di sebalik Qiskit Code Assistant​

Penanda aras Qiskit HumanEval dan Qiskit HumanEval Hard​

Pasang Qiskit Code Assistant​

Menggunakan aplikasi Ollama​

Pasang Ollama​

Sediakan Ollama menggunakan integrasi Hugging Face Hub​

Sediakan Ollama dengan model GGUF Qiskit Code Assistant yang dimuat turun secara manual​

Run the Qiskit Code Assistant model manually downloaded in Ollama​

Use the llama.cpp library​

Advanced parameters​

Continue (VS Code)​

1. Install the extension​

2. Open the config​

3. Configure the model​

4. Test it​

Jupyter AI (JupyterLab)​

1. Install Jupyter AI and the Ollama provider​

2. Configure the chat model​

3. Use the %%ai magic command​

4. Custom Ollama host (optional)​

OpenCode (Terminal)​

1. Install OpenCode​

2. Configure the Qiskit model​

3. Select the model​

4. Test it​

Available models​

Current models​

GGUF models (recommended for personal environments/laptops)​

Qiskit versions used for training​

Deprecated models​

More information and citations​

Model Bahasa Besar (LLM) di sebalik Qiskit Code Assistant

Penanda aras Qiskit HumanEval dan Qiskit HumanEval Hard

Pasang Qiskit Code Assistant

Menggunakan aplikasi Ollama

Pasang Ollama

Sediakan Ollama menggunakan integrasi Hugging Face Hub

Sediakan Ollama dengan model GGUF Qiskit Code Assistant yang dimuat turun secara manual

Run the Qiskit Code Assistant model manually downloaded in Ollama

Use the `llama.cpp` library

Advanced parameters

Continue (VS Code)

1. Install the extension

2. Open the config

3. Configure the model

4. Test it

Jupyter AI (JupyterLab)

1. Install Jupyter AI and the Ollama provider

2. Configure the chat model

3. Use the `%%ai` magic command

4. Custom Ollama host (optional)

OpenCode (Terminal)

1. Install OpenCode

2. Configure the Qiskit model

3. Select the model

4. Test it

Available models

Current models

GGUF models (recommended for personal environments/laptops)

Qiskit versions used for training

Deprecated models

More information and citations