Skip to content
Other

Python Coding Assistant

LoRA-адаптер для генерации Python-кода

1 min read

Это LoRA-адаптер от mazennkarim, дообученный на базе SmolLM3-3B-Base (3B) для генерации Python-кода. Обучение выполнено через SFT и QLoRA на датасете iamtarun/python_code_instructions_18k_alpaca. В репозитории лежит не самостоятельная модель, а адаптер для PEFT.

Ключевые особенности

  • Дообучение через QLoRA + LoRA: 4-bit NF4, LoRA rank 16, alpha 32, dropout 0.05.
  • 350 шагов обучения, batch size 1, gradient accumulation 8, max sequence length 1024.
  • На 1 214 отложенных Python-промптах синтаксически валидный код получился в 97.12% случаев.
  • В сравнении на 100 промптах базовая модель дала 72% валидного Python, дообученная — 97%.
  • Адаптер загружается поверх SmolLM3-3B-Base через библиотеку PEFT.

Пример

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base_id = "HuggingFaceTB/SmolLM3-3B-Base"
adapter_id = "mazennkarim/python-coding-assistant"
tokenizer = AutoTokenizer.from_pretrained(adapter_id)
base = AutoModelForCausalLM.from_pretrained(base_id, device_map="auto")
model = PeftModel.from_pretrained(base, adapter_id)
ПодробнееСинтаксическая валидность: 97.12% на 1 214 промптах; у базовой модели — 72% против 97% на 100 промптах (+25 п.п.).
Метрика проверяет только парсинг кода как Python, а не функциональную корректность или исполнение.
Обучение: QLoRA, 4-bit NF4, LoRA r=16, alpha=32, 350 шагов.
Нужно загружать базовую SmolLM3-3B-Base и подключать adapter через PEFT.
Discuss Telegram 1

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.

    # mazennkarim/python-coding-assistant
    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 mazennkarim/python-coding-assistant --local-dir ~/models/python-coding-assistant
    # The model is in ~/models. How to run it is in the model card (link above).
  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 python-coding-assistant (quants, finetunes, LoRAs) will show up under the bell.

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

About the model

mazennkarim/python-coding-assistant
Author
mazennkarim
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

01

Ask AI about this model

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

Comments