Instructions to use CyberCastle/XiYanSQL-QwenCoder-7B-2504-W4A16-AWQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CyberCastle/XiYanSQL-QwenCoder-7B-2504-W4A16-AWQ with Transformers:

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

pipe = pipeline("text-generation", model="CyberCastle/XiYanSQL-QwenCoder-7B-2504-W4A16-AWQ")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CyberCastle/XiYanSQL-QwenCoder-7B-2504-W4A16-AWQ")
model = AutoModelForCausalLM.from_pretrained("CyberCastle/XiYanSQL-QwenCoder-7B-2504-W4A16-AWQ")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use CyberCastle/XiYanSQL-QwenCoder-7B-2504-W4A16-AWQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CyberCastle/XiYanSQL-QwenCoder-7B-2504-W4A16-AWQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CyberCastle/XiYanSQL-QwenCoder-7B-2504-W4A16-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CyberCastle/XiYanSQL-QwenCoder-7B-2504-W4A16-AWQ

SGLang

How to use CyberCastle/XiYanSQL-QwenCoder-7B-2504-W4A16-AWQ 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 "CyberCastle/XiYanSQL-QwenCoder-7B-2504-W4A16-AWQ" \
    --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": "CyberCastle/XiYanSQL-QwenCoder-7B-2504-W4A16-AWQ",
		"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 "CyberCastle/XiYanSQL-QwenCoder-7B-2504-W4A16-AWQ" \
        --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": "CyberCastle/XiYanSQL-QwenCoder-7B-2504-W4A16-AWQ",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CyberCastle/XiYanSQL-QwenCoder-7B-2504-W4A16-AWQ with Docker Model Runner:
```
docker model run hf.co/CyberCastle/XiYanSQL-QwenCoder-7B-2504-W4A16-AWQ
```

XiYanSQL-QwenCoder-7B-2504 W4A16 AWQ

Quantized model derived from XGenerationLab/XiYanSQL-QwenCoder-7B-2504.

This repository contains a locally generated quantized checkpoint ready to be uploaded to the Hugging Face Hub. The folder includes the quantized weights, tokenizer files, and the exact quantization settings used to produce this artifact.

Format

Quantization type: AWQ
Bits: 4-bit weights / 16-bit activations
Calibration dataset: birdsql/bird-critic-1.0-open
Tested backend: Transformers

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

model_id = "your-hf-username/XiYanSQL-QwenCoder-7B-2504-W4A16-AWQ"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    trust_remote_code=False,
)

About LLMToys

This quantizer is hosted in the LLMToys repository: https://github.com/CyberCastle/LLMToys. LLMToys is a collection of practical LLM tools and experiments maintained in a single codebase. It groups reusable components for local model execution, quantization workflows, runtime tuning, and structured generation pipelines such as natural-language-to-SQL.

Quantization Configuration

Setting	Value
Base model	XGenerationLab/XiYanSQL-QwenCoder-7B-2504
Output folder	XiYanSQL-QwenCoder-7B-2504-W4A16-AWQ
Quantization scheme	AWQ
Weight / activation format	W4A16
Model architecture	qwen2
Calibration dataset	birdsql/bird-critic-1.0-open
Calibration split	open
Dataset configuration	n/a
Calibration samples used	256
Max sequence length	2048
Max GPU memory budget	12.0 GiB
Sequential onloading	yes
Requested sequential targets	safe-auto
Effective sequential targets	Qwen2Attention, Qwen2MLP
Sequential targets per subgraph	1
trust_remote_code	no
Memory preflight mode	off
vLLM smoke test requested	no

Toolchain

Setting	Value
Generated at (UTC)	2026-05-03T21:28:14Z
Runner entrypoint	uv run quantizer/run.py
llmcompressor	0.10.1.dev127+g76b28ce7
transformers	5.6.2
torch	2.11.0+cu130
compressed-tensors	0.15.1a20260428

Notes

This README is generated automatically by the quantizer so the artifact keeps its execution context.
Review the original base model license and any upstream usage restrictions before publishing this checkpoint.
If you rerun the quantizer with different settings, regenerate and upload the full output directory again.

Downloads last month: 10

Safetensors

Model size

8B params

Tensor type

I64

I32

BF16

Model tree for CyberCastle/XiYanSQL-QwenCoder-7B-2504-W4A16-AWQ

Base model

XGenerationLab/XiYanSQL-QwenCoder-7B-2502

Finetuned

XGenerationLab/XiYanSQL-QwenCoder-7B-2504

Quantized

(3)

this model

CyberCastle
/

XiYanSQL-QwenCoder-7B-2504-W4A16-AWQ