drawais/circuitqa-adapters

CircuitQA LoRA adapters

LoRA adapters (r = 64, alpha = 128; weights stored in fp32, base model loaded in bf16) for Qwen/Qwen2.5-Coder-7B-Instruct, trained by the authors of CircuitQA: A Grounded Architecture for Question Answering over Digital RTL Designs with Multi-Backend Query Routing. Data, code and evaluation outputs: drawais/circuitqa. Only the adapter weights and configurations are provided; the base model and its tokenizer are loaded from their own repository.

Folder	Role
s4_seed42, s4_seed123, s4_seed456	Response Decoder reported in the paper (three seeds, selected checkpoints)
router_s4	Query Routing Module reported in the paper
mt_seed42, mt_seed123, mt_seed456	Compositional adapter used when the router emits several backend calls
router_mt	Multi-backend router (emits a list of backend calls)
s3_seed*, router_s3	Template-only training on the repository-disjoint split
s2_seed*	Training on the design-disjoint split

Requires peft>=0.21 (the configs were written by PEFT 0.21.2).

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel
base = "Qwen/Qwen2.5-Coder-7B-Instruct"
tok = AutoTokenizer.from_pretrained(base)
model = AutoModelForCausalLM.from_pretrained(base, torch_dtype="bfloat16", device_map="auto")
model = PeftModel.from_pretrained(model, "drawais/circuitqa-adapters", subfolder="s4_seed42")

Licence: Apache-2.0, as the base model.

Citation

If you use the CircuitQA dataset, code or adapters, please cite:

@misc{awais2026circuitqa,
  title        = {{CircuitQA}: A Grounded Architecture for Question Answering over Digital {RTL} Designs with Multi-Backend Query Routing},
  author       = {Awais, Muhammad and Postolache, Octavian Adrian and Oliveira, Sancho Moura},
  year         = {2026},
  howpublished = {\url{https://huggingface.co/datasets/drawais/circuitqa}},
  note         = {Dataset and code}
}

@misc{awais2026circuitqaadapters,
  title        = {{CircuitQA} Adapters: {LoRA} Adapters for {Qwen2.5-Coder-7B-Instruct}},
  author       = {Awais, Muhammad and Postolache, Octavian Adrian and Oliveira, Sancho Moura},
  year         = {2026},
  howpublished = {\url{https://huggingface.co/drawais/circuitqa-adapters}},
  note         = {Trained model adapters}
}