GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
utsubo12
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
utsubo12
Model Tree
Qwen/Qwen3-VL-8B-Instruct
Input Modalities
Output Modalities
Supported Functionality
The model translates a 256×256 semiconductor SEM image into a NetDSL-L2 program — a
Domain-Specific Language describing Manhattan-routed circuit layouts as a sequence of CANVAS,
WIRE2 and VIA commands. Rendering the generated DSL reproduces the input geometry as a binary
mask, enabling controlled augmentation, parameter editing and downstream metrology.
Qwen/Qwen3-VL-8B-Instructqwen3_vl_nothink (no reasoning tokens emitted)Feed a binarized SEM image; the model emits NetDSL-L2 code. The binarization is what closes the sim-to-real gap — the model only ever saw binary images during training.
python
from PIL import Imageimport numpy as np # 1. resize to the model's canvas, THEN threshold. Both steps matter.img = Image.open("test_normal_00169.jpg").convert("L").resize((256, 256), Image.LANCZOS)binary = Image.fromarray(np.where(np.array(img) > 96, 255, 0).astype(np.uint8), "L")The threshold is 96, applied to the resampled pixels. (§III-D of the paper prints "100" and omits the resize; the released data and code use 96 after a LANCZOS resize — that recipe reproduces the published ground-truth images pixel-for-pixel.)
Mean ± std over executable outputs. Binary input (proposed) vs raw input (baseline):
| Metric | Raw | Binary (ours) |
|---|---|---|
| IoU | 0.2865 ± 0.0802 | 0.3619 ± 0.0882 |
| Dice coefficient | 0.4393 ± 0.0980 | 0.5256 ± 0.0912 |
| BF1 @ 2 px | 0.4054 ± 0.1106 | 0.4412 ± 0.1098 |
| SkF1 @ 1 px | 0.1276 ± 0.0960 | 0.1746 ± 0.1145 |
| ASSD | 4.7768 ± 3.4596 | 4.1327 ± 1.2757 |
Executable outputs: 1019 of 1034 for raw input (98.5 %). For binary input the evaluation run was
interrupted and resumed, and its aggregate covers 986 attempted images, of which 957 were
executable (97.1 % = 957/986). Recomputing over all 1005 surviving binary renders gives IoU 0.3628 /
Dice 0.5265 and executability 1005/1034 = 97.2 % — the same conclusion. Details and per-sample data:
utsubo12/miic-netdsl-eval.
The prompt matters. The model was fine-tuned on one fixed instruction; a paraphrase will degrade output badly. Use it verbatim:
python
import numpy as np, torchfrom PIL import Imagefrom transformers import AutoProcessor, AutoModelForImageTextToText REPO = "utsubo12/qwen3-vl-8b-netdsl-l2" INSTRUCTION = """You are given a binary SEM-like image. Generate the NetDSL-L2 program that reproduces this image. NetDSL-L2 Syntax:- CANVAS W H: Set canvas size (256x256)- WIRE2 x0 y0 base_w cap_s_len cap_s_w cap_e_len cap_e_w segments: Manhattan wiring with optional dogbone caps - x0, y0: start position - base_w: line width - cap_s_len, cap_s_w: start cap length and width (0 for none) - cap_e_len, cap_e_w: end cap length and width (0 for none) - segments: H length or V length sequence- VIA x y r: Circle at (x,y) with radius r""" model = AutoModelForImageTextToText.from_pretrained( REPO, torch_dtype=torch.bfloat16, device_map="cuda")processor = AutoProcessor.from_pretrained(REPO) img = Image.open("test_normal_00169.jpg").convert("L").resize((256, 256), Image.LANCZOS)binary = Image.fromarray(np.where(np.array(img) > 96, 255, 0).astype(np.uint8), "L") messages = [{"role": "user", "content": [ {"type": "image", "image": binary.convert("RGB")}, {"type": "text", "text": INSTRUCTION},]}] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt", tokenize=True, return_dict=True,).to(model.device) out = model.generate(**inputs, max_new_tokens=1024, do_sample=False)dsl_code = processor.batch_decode( out[:, inputs["input_ids"].shape[1]:], skip_special_tokens=True)[0]print(dsl_code)Render the predicted DSL with the companion repository:
python
from src.dsl2_runtime import render_program_l2mask = render_program_l2(dsl_code) # -> PIL.Image, 256x256, mode "L"mask.save("reconstruction.png")The numbers in the paper were produced through LLaMA-Factory's
ChatModelwithtemplate="qwen3_vl_nothink"(seesrc/eval_dsl2_v3_miic_fulldata.py), not through thetransformerspath above. Use the repository scripts for exact reproduction.
bash
git clone https://github.com/YusukeO/eusipco2026-sem-dsl && cd eusipco2026-sem-dslpip install -r requirements.txt python -m src.reproduce_paper_figures --mode render-only # verify renderer, no GPUpython -m src.reproduce_paper_figures --mode full --model-dir utsubo12/qwen3-vl-8b-netdsl-l2text
CANVAS 256 256WIRE2 0 12 8 0 0 0 0 H 256WIRE2 12 0 10 0 0 30 14 V 60VIA 35 40 6WIRE2 x0 y0 base_w cap_s_len cap_s_w cap_e_len cap_e_w <segments> describes a wire with optional
dogbone end-caps; <segments> is a chain of H <length> / V <length> relative moves. See §III-A of
the paper — which writes the primitive as WIRE, while the concrete L2 token is WIRE2 (WIRE is
the NetDSL-L1 keyword).
bibtex
@inproceedings{ohtsubo2026bridging, author = {Ohtsubo, Yusuke and Dohi, Kota and Yawata, Koichiro and Takeshita, Koki and Sasaki, Tatsuya}, title = {Bridging the Sim-to-Real Gap in Semiconductor Visual Program Synthesis via Input Binarization}, booktitle = {Proceedings of the 34th European Signal Processing Conference (EUSIPCO)}, year = {2026}, publisher = {EURASIP}, note = {Accepted; final citation/DOI to be updated upon publication}}MIT for both the code and these weights. The base model Qwen3-VL-8B-Instruct is subject to its own license; please review it.
Yusuke Ohtsubo — yusuke.ohtsubo.nb@hitachi.com
CANVAS 256 256WIRE2 0 12 8 0 0 0 0 H 256WIRE2 12 0 10 0 0 30 14 V 60VIA 35 40 6from PIL import Imageimport numpy as np # 1. resize to the model's canvas, THEN threshold. Both steps matter.img = Image.open("test_normal_00169.jpg").convert("L").resize((256, 256), Image.LANCZOS)binary = Image.fromarray(np.where(np.array(img) > 96, 255, 0).astype(np.uint8), "L")import numpy as np, torchfrom PIL import Imagefrom transformers import AutoProcessor, AutoModelForImageTextToText REPO = "utsubo12/qwen3-vl-8b-netdsl-l2" INSTRUCTION = """You are given a binary SEM-like image. Generate the NetDSL-L2 program that reproduces this image. NetDSL-L2 Syntax:- CANVAS W H: Set canvas size (256x256)- WIRE2 x0 y0 base_w cap_s_len cap_s_w cap_e_len cap_e_w segments: Manhattan wiring with optional dogbone caps - x0, y0: start position - base_w: line width - cap_s_len, cap_s_w: start cap length and width (0 for none) - cap_e_len, cap_e_w: end cap length and width (0 for none) - segments: H length or V length sequence- VIA x y r: Circle at (x,y) with radius r""" model = AutoModelForImageTextToText.from_pretrained( REPO, torch_dtype=torch.bfloat16, device_map="cuda")processor = AutoProcessor.from_pretrained(REPO) img = Image.open("test_normal_00169.jpg").convert("L").resize((256, 256), Image.LANCZOS)binary = Image.fromarray(np.where(np.array(img) > 96, 255, 0).astype(np.uint8), "L") messages = [{"role": "user", "content": [ {"type": "image", "image": binary.convert("RGB")}, {"type": "text", "text": INSTRUCTION},]}] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, return_tensors="pt", tokenize=True, return_dict=True,).to(model.device) out = model.generate(**inputs, max_new_tokens=1024, do_sample=False)dsl_code = processor.batch_decode( out[:, inputs["input_ids"].shape[1]:], skip_special_tokens=True)[0]print(dsl_code)from src.dsl2_runtime import render_program_l2mask = render_program_l2(dsl_code) # -> PIL.Image, 256x256, mode "L"mask.save("reconstruction.png")git clone https://github.com/YusukeO/eusipco2026-sem-dsl && cd eusipco2026-sem-dslpip install -r requirements.txt python -m src.reproduce_paper_figures --mode render-only # verify renderer, no GPUpython -m src.reproduce_paper_figures --mode full --model-dir utsubo12/qwen3-vl-8b-netdsl-l2@inproceedings{ohtsubo2026bridging, author = {Ohtsubo, Yusuke and Dohi, Kota and Yawata, Koichiro and Takeshita, Koki and Sasaki, Tatsuya}, title = {Bridging the Sim-to-Real Gap in Semiconductor Visual Program Synthesis via Input Binarization}, booktitle = {Proceedings of the 34th European Signal Processing Conference (EUSIPCO)}, year = {2026}, publisher = {EURASIP}, note = {Accepted; final citation/DOI to be updated upon publication}}