Instructions to use AbijahKaj/qwen3-4b-skidl with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AbijahKaj/qwen3-4b-skidl with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="AbijahKaj/qwen3-4b-skidl")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AbijahKaj/qwen3-4b-skidl")
model = AutoModelForCausalLM.from_pretrained("AbijahKaj/qwen3-4b-skidl")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

PEFT
How to use AbijahKaj/qwen3-4b-skidl with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AbijahKaj/qwen3-4b-skidl with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AbijahKaj/qwen3-4b-skidl"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AbijahKaj/qwen3-4b-skidl",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AbijahKaj/qwen3-4b-skidl

SGLang

How to use AbijahKaj/qwen3-4b-skidl with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "AbijahKaj/qwen3-4b-skidl" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AbijahKaj/qwen3-4b-skidl",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "AbijahKaj/qwen3-4b-skidl" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AbijahKaj/qwen3-4b-skidl",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AbijahKaj/qwen3-4b-skidl with Docker Model Runner:
```
docker model run hf.co/AbijahKaj/qwen3-4b-skidl
```

qwen3-4b-skidl

A fine-tune of Qwen/Qwen3-4B for generating executable SKiDL Python netlists from natural-language circuit descriptions. Given a description like "ESP32 board with BME280 on I2C and USB-C", the model outputs valid Python using Part(), Net(), and generate_netlist() — producing a .net file KiCad can open directly.

This repo has two branches:

Branch	Contents	Size	Use
`main` (this)	Merged weights — LoRA baked into base	7.5 GB	Load directly, no base model needed
`lora`	Adapter only	504 MB	Lightweight; load on top of Qwen3-4B

Quick start

Merged (main branch — recommended)

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained(
    "AbijahKaj/qwen3-4b-skidl",
    dtype="auto",
    device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("AbijahKaj/qwen3-4b-skidl")

LoRA adapter (lora branch)

from transformers import AutoModelForCausalLM, AutoTokenizer
from peft import PeftModel

base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-4B", dtype="auto", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("AbijahKaj/qwen3-4b-skidl", revision="lora")
model = PeftModel.from_pretrained(base, "AbijahKaj/qwen3-4b-skidl", revision="lora")

Generating a circuit

SYSTEM = (
    "You are an expert electronics engineer and KiCad schematic designer. "
    "When given a description of an electronic circuit, generate executable "
    "SKiDL Python code that defines the circuit using the SKiDL library."
)

messages = [
    {"role": "system", "content": SYSTEM},
    {"role": "user", "content": "Design a CAN bus interface using MCP2515 controller and TJA1050 transceiver on SPI, with 120 ohm termination resistor."},
]
text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(text, return_tensors="pt").to(model.device)
out = model.generate(**inputs, max_new_tokens=1024, do_sample=False)
print(tokenizer.decode(out[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))

Training


Base model	Qwen/Qwen3-4B
Method	SFT + LoRA
Dataset	AbijahKaj/kicad-netlist-sft-dataset — 100,179 SKiDL Python circuit examples
LoRA rank / alpha	r=64, α=32, dropout=0.05
Target modules	q/k/v/o_proj, gate/up/down_proj
Epochs	2
Peak LR	2e-4 (cosine decay)
Effective batch	8
Max length	8192 tokens
Trainable params	~132M (5.65% of 4B)

Loss curve

Phase	Train loss	Token accuracy
Start	0.86	75%
Epoch 1 end	0.17	95%
Epoch 2 end	0.15	95–96%
Eval loss (final)	0.1581	95.3%

SKiDL validation (final checkpoint)

Functional scoring across 5 held-out circuits: Python syntax + SKiDL import + net count + part count + connectivity + GND checks.

Circuit	Score
LED blink — ATtiny85	0.85
USB power meter — ATmega328P + INA219	0.85
CAN bus — MCP2515 + TJA1050	0.95
Average	0.883

Why SKiDL?

KiCad's native s-expression netlist is deeply nested and pathological for LLMs. PCBSchemaGen (arXiv:2602.00510) shows SKiDL Python achieves 87% Pass@1 with GPT-4o on circuit generation — because Python-based HDLs align with LLM pretraining data and are 3× more compact than s-expressions.

Dataset

AbijahKaj/kicad-netlist-sft-dataset — 100,179 ChatML examples:

Source	Count
Si7li/ltspice-spice-circuits (LTspice → SKiDL)	~54,000
bshada/open-schematics (GitHub `.kicad_sch` files)	~45,000
Ashed00/SPICE-Circuits	~800
Synthetic + tool-augmented	~308