Skip to content
Other

SmolLM2-SQL-SFT

a compact Text-to-SQL adapter

1 min read

The model turns natural language questions and database schemas into ready-to-use SQL queries. It is built on the lightweight SmolLM2-135M language model and fine-tuned using LoRA (a small add-on over the base model) on the NSText2SQL dataset. Thanks to its ultra-compact size, the model is ideal for local testing, simple query generation tasks, and learning how Text-to-SQL systems work on low-end hardware.

Key features

  • Specialization: translating natural language queries and database schemas into SQL code.
  • Base architecture: built on HuggingFaceTB/SmolLM2-135M using PEFT and LoRA.
  • Lightweight: only 135 million parameters for fast performance on minimal system requirements.

What you can do

  • Script integration: embed the adapter into a local pipeline for automated SQL query generation.
  • Testing: run experiments on text-to-code conversion on a regular computer without a powerful GPU.

Example

Example prompt from the card for query generation:
Schema: CREATE TABLE students (id INTEGER, name TEXT, age INTEGER)
Question: Find all students older than 20.
Expected SQL: SELECT * FROM students WHERE age > 20;

Read moreDetails
Training notes: training was completed in 2 epochs using Hugging Face Transformers and PEFT.
Metrics: Exact-Match Accuracy reached 37% (37/100) on the test set.
Limitations: the model is small, so the generated SQL may contain errors and requires verification before execution.
Discuss Telegram 0

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.

    # Rachitvig/SmolLM2-SQL-SFT
    # ===== Tokens: paste yours between the quotes =====
    export HF_TOKEN=""        # huggingface.co/settings/tokens, for gated models
    # ==========================================
    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 Rachitvig/SmolLM2-SQL-SFT --local-dir ~/models/SmolLM2-SQL-SFT
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to SmolLM2-SQL-SFT
  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 SmolLM2-SQL-SFT (quants, finetunes, LoRAs) will show up under the bell.

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

About the model

Rachitvig/SmolLM2-SQL-SFT
Author
Rachitvig
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

00

Ask AI about this model

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

Comments