Instructions to use ALI-USER/qwen2.5-coder-spider-sql with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ALI-USER/qwen2.5-coder-spider-sql with Transformers:

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

pipe = pipeline("text-generation", model="ALI-USER/qwen2.5-coder-spider-sql")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ALI-USER/qwen2.5-coder-spider-sql")
model = AutoModelForCausalLM.from_pretrained("ALI-USER/qwen2.5-coder-spider-sql")
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 ALI-USER/qwen2.5-coder-spider-sql with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ALI-USER/qwen2.5-coder-spider-sql"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ALI-USER/qwen2.5-coder-spider-sql",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ALI-USER/qwen2.5-coder-spider-sql

SGLang

How to use ALI-USER/qwen2.5-coder-spider-sql 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 "ALI-USER/qwen2.5-coder-spider-sql" \
    --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": "ALI-USER/qwen2.5-coder-spider-sql",
		"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 "ALI-USER/qwen2.5-coder-spider-sql" \
        --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": "ALI-USER/qwen2.5-coder-spider-sql",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ALI-USER/qwen2.5-coder-spider-sql with Docker Model Runner:
```
docker model run hf.co/ALI-USER/qwen2.5-coder-spider-sql
```

Ali Assi commited on Aug 23, 2025

Commit

00bdb7b

verified ·

1 Parent(s): 30581aa

Update README.md

Browse files

Files changed (1) hide show

README.md +12 -0

README.md CHANGED Viewed

@@ -43,6 +43,18 @@ This model converts natural language questions into SQL queries by leveraging th
 ## Performance
 **Overall Performance Summary**
 The model achieved a **39.17% execution accuracy** on the Spider development set, correctly generating 405 out of 1,034 SQL queries. While this represents moderate performance, it demonstrates the model's capability to handle basic to intermediate SQL generation tasks across diverse database domains.

 ## Performance
+### Performance Comparison
+| Metric | Base Qwen Model | Fine-tuned Model |
+|--------|----------------|------------------|
+| **Total Queries** | 1,034 | 1,034 |
+| **Execution Success** | 570 | 577 |
+| **Execution Success Rate** | 55.1% | 55.8% |
+| **Correct Results** | 357 | 405 |
+| **Execution Accuracy** | 34.5% | 39.2% |
+| **Parse Errors** | 464 | 457 |
+| **Evaluation Time** | 84.9 min | 38.7 min |
 **Overall Performance Summary**
 The model achieved a **39.17% execution accuracy** on the Spider development set, correctly generating 405 out of 1,034 SQL queries. While this represents moderate performance, it demonstrates the model's capability to handle basic to intermediate SQL generation tasks across diverse database domains.