Instructions to use shangyangwu2002/SCAD with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shangyangwu2002/SCAD with Transformers:

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

pipe = pipeline("text-generation", model="shangyangwu2002/SCAD")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("shangyangwu2002/SCAD")
model = AutoModelForCausalLM.from_pretrained("shangyangwu2002/SCAD", device_map="auto")
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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use shangyangwu2002/SCAD with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shangyangwu2002/SCAD"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shangyangwu2002/SCAD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/shangyangwu2002/SCAD

SGLang

How to use shangyangwu2002/SCAD 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 "shangyangwu2002/SCAD" \
    --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": "shangyangwu2002/SCAD",
		"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 "shangyangwu2002/SCAD" \
        --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": "shangyangwu2002/SCAD",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use shangyangwu2002/SCAD with Docker Model Runner:
```
docker model run hf.co/shangyangwu2002/SCAD
```

SCAD-4B

Text-only model for SCAD: Structured Credit Assignment and Distillation for Long-Horizon Agents, fine-tuned from Qwen3-4B.

Code · Retrieval corpus

This repository contains full model weights in BF16 Safetensors format, the tokenizer, and inference configuration.

Loading

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "shangyangwu2002/SCAD"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    torch_dtype=torch.bfloat16,
    device_map="auto",
)

Use the SCAD code repository for agent prompts, search tools, and evaluation. Retrieval uses the separately hosted SCAD corpus.

License

The model is released under Apache License 2.0; see LICENSE. The weights were fine-tuned from Qwen3-4B. Qwen's upstream attribution and license are retained.

Downloads last month: 245

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for shangyangwu2002/SCAD

Base model

Qwen/Qwen3-4B-Base

Finetuned

Qwen/Qwen3-4B

Finetuned

(1157)

this model