Model Details

This model is trained on the MetRex dataset for estimating static power metrics for Verilog designs. Finetuned from model: Meta-Llama-3-8B-Instruct

Prompt

Set temperature to 0.4. Use the following prompt template:

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

Your task is to estimate static power for RTL designs in Skywater 130nm technology node.<|eot_id|><|start_header_id|>user<|end_header_id|>

Estimate static power for the given RTL design. Reason about the number and type of gates that would be present after synthesis. 
 # RTL: 
 module top_module(
        input a, 
        input b,
        output out
);

        assign out = ~(a | b);

endmodule<|eot_id|>

Citation

@INPROCEEDINGS{abdelatty2025metrex,
    author={M. {Abdelatty} and J. {Ma} and S. {Reda}},
     booktitle={2025 30th Asia and South Pacific Design Automation Conference (ASP-DAC)},
     title={MetRex: A Benchmark for Verilog Code Metric Reasoning Using LLMs},
     year={2025},
     volume={},
     number={},
}
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no pipeline_tag.

Model tree for scale-lab/Llama3-MetRex-Static-Power-8b

Finetuned
(563)
this model

Dataset used to train scale-lab/Llama3-MetRex-Static-Power-8b

Collection including scale-lab/Llama3-MetRex-Static-Power-8b