Skip to content
Other

leona-qasm-1.0

LoRA, которая переводит текст в OpenQASM 3

1 min readupdated

Это LoRA-адаптер от LeonaQuantum для генерации кода OpenQASM 3 по описанию на естественном языке. Базовая модель — Qwen/Qwen3.8-27B; адаптер обучен на 24 593 строках и представляет собой clean-v13 step-600. Оценка ещё идёт, заявленных результатов пока нет.

Ключевые особенности

  • LoRA rank 16 / alpha 32 для Qwen3.8-27B.
  • Обучение: 600 шагов от clean-v12 step-1000, lr 2e-5, gradient accumulation 16.
  • Данные: 22 260 строк clean-v12 + 2 333 проверенные строки; всего 24 593.
  • Добавлены ��роверенная арифметика, QFT и схемы из MQT Bench и библиотеки Qiskit.
  • В репозитории только адаптер; веса базовой модели загружаются отдельно.
  • В карточке указаны enable_thinking=False и greedy decoding.

Пример

from transformers import Qwen3_5ForConditionalGeneration
from peft import PeftModel
import torch
base = Qwen3_5ForConditionalGeneration.from_pretrained(
    'Qwen/Qwen3.8-27B',
    revision='1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0',
    torch_dtype=torch.bfloat16)
model = PeftModel.from_pretrained(base, 'LeonaQuantum/leona-qasm-1.0')
ПодробнееОценка адаптера ещё не завершена — цифр бенчмарков нет.
База: Qwen3.8-27B в BF16; окружение: Transformers 5.22.1, PEFT 0.21.2, PyTorch 2.8.0.
Максимальная длина 4 096, greedy decoding, max_new_tokens=4096.
Сгенерированные схемы нужно проверять; данные обучения здесь не распространяются.
Discuss Telegram 1 22

Will it run?

Working out the memory needs

The bot is still collecting this model's weight sizes; the estimate will appear here in a few minutes. Meanwhile you can rent a GPU with headroom.

Massed ComputeOpen Massed Compute

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # LeonaQuantum/leona-qasm-1.0
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download LeonaQuantum/leona-qasm-1.0 --local-dir ~/models/leona-qasm-1.0
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to leona-qasm-1.0
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of leona-qasm-1.0 (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

LeonaQuantum/leona-qasm-1.0
Author
LeonaQuantum
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

221

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments

Computer vision

UAV-PUR-8B

UAV-PUR-8B