Skip to content
Other

sva-qlora-verified

QLoRA adapter for generating SystemVerilog Assertions

1 min readupdated

This is a QLoRA adapter (a lightweight add-on for memory-efficient fine-tuning) built on Qwen2.5-Coder-7B-Instruct. Trained on verified data pairs (the Verified, Veri2 variant), it automatically generates SystemVerilog Assertions (verification properties) from RTL code. It is built for chip verification engineers, SystemVerilog developers, and anyone working in digital design with hardware description languages.

Key features

  • Built on the efficient Qwen2.5-Coder-7B-Instruct architecture.
  • Uses QLoRA for fine-tuning tailored to engineering workflows.
  • Trained on verified data pairs (Veri2) to ensure reliable output code.
  • Focused on generating SystemVerilog Assertions directly from RTL.

What you can do

  • Automate SystemVerilog Assertion creation from existing RTL code in your projects.
  • Plug the adapter into digital circuit testing and verification pipelines.
  • Speed up specification development and assertion writing for simulation.

Example

Load the Qwen/Qwen2.5-Coder-7B-Instruct base model alongside the veri2-anon/sva-qlora-verified adapter weights via the peft library to generate assertions from your RTL descriptions.

Read moreDetails
Library: peft
Base model: Qwen/Qwen2.5-Coder-7B-Instruct
Dataset and code: available in the repository on 4open.science
Discuss Telegram 0 2

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 15 GB · ready files17 GB
  • FP8 / INT8recommendedweights 7.7 GB9.0 GB
  • 4-bitweights 4.6 GB5.6 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 3080 · BF16 — from RTX 4090

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

This is a LoRA: counted together with its base model Qwen2.5-Coder-7B-Instruct.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

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.

    # veri2-anon/sva-qlora-verified
    # ===== 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 Qwen/Qwen2.5-Coder-7B-Instruct --local-dir ~/models/Qwen2.5-Coder-7B-Instruct
    hf download veri2-anon/sva-qlora-verified --local-dir ~/models/sva-qlora-verified
    # 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

Requires the base model

Qwen/Qwen2.5-Coder-7B-Instruct

This model is a LoRA / adapter. Download the base model first, then load this one on top.

  1. Qwen2.5-7Bfamily root
  2. Qwen2.5-Coder-7B
  3. Qwen2.5-Coder-7B-Instruct
  4. sva-qlora-verified

New posts about versions of Qwen2.5-7B (quants, finetunes, LoRAs) will show up under the bell.

Quantised versions 12All on Hugging Face
Fine-tunes 12All on Hugging Face
LoRAs and adapters 1All on Hugging Face
Merges 5All on Hugging Face

About the model

veri2-anon/sva-qlora-verified
Author
veri2-anon
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

20

Ask AI about this model

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

Comments