Instructions to use cycloneboy/CscSQL-Merge-Qwen2.5-Coder-1.5B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cycloneboy/CscSQL-Merge-Qwen2.5-Coder-1.5B-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="cycloneboy/CscSQL-Merge-Qwen2.5-Coder-1.5B-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cycloneboy/CscSQL-Merge-Qwen2.5-Coder-1.5B-Instruct")
model = AutoModelForCausalLM.from_pretrained("cycloneboy/CscSQL-Merge-Qwen2.5-Coder-1.5B-Instruct")
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 cycloneboy/CscSQL-Merge-Qwen2.5-Coder-1.5B-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cycloneboy/CscSQL-Merge-Qwen2.5-Coder-1.5B-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cycloneboy/CscSQL-Merge-Qwen2.5-Coder-1.5B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cycloneboy/CscSQL-Merge-Qwen2.5-Coder-1.5B-Instruct

SGLang

How to use cycloneboy/CscSQL-Merge-Qwen2.5-Coder-1.5B-Instruct 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 "cycloneboy/CscSQL-Merge-Qwen2.5-Coder-1.5B-Instruct" \
    --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": "cycloneboy/CscSQL-Merge-Qwen2.5-Coder-1.5B-Instruct",
		"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 "cycloneboy/CscSQL-Merge-Qwen2.5-Coder-1.5B-Instruct" \
        --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": "cycloneboy/CscSQL-Merge-Qwen2.5-Coder-1.5B-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cycloneboy/CscSQL-Merge-Qwen2.5-Coder-1.5B-Instruct with Docker Model Runner:
```
docker model run hf.co/cycloneboy/CscSQL-Merge-Qwen2.5-Coder-1.5B-Instruct
```

nielsr HF Staff commited on Jul 31, 2025

Commit

b83e8e0

verified ·

1 Parent(s): 2633043

Improve model card: Add prominent GitHub link and sample usage

Browse files

This PR improves the model card for SLM-SQL by:
- Adding a prominent link to the GitHub repository (`https://github.com/CycloneBoy/slm_sql`) in the "Important Links" section, making it easier for users to find the code.
- Incorporating a clear sample usage example to demonstrate how to load and run the model using the `transformers` library, which significantly enhances user accessibility.

Files changed (1) hide show

README.md +30 -4

README.md CHANGED Viewed

@@ -1,19 +1,18 @@
 ---
-pipeline_tag: text-generation
 library_name: transformers
 license: cc-by-nc-4.0
 tags:
 - text-to-sql
 - reinforcement-learning
 ---
 # SLM-SQL: An Exploration of Small Language Models for Text-to-SQL
 ### Important Links
-📖[Arxiv Paper](https://arxiv.org/abs/2507.22478) |
-🤗[HuggingFace](https://huggingface.co/collections/cycloneboy/slm-sql-688b02f99f958d7a417658dc) |
 🤖[ModelScope](https://modelscope.cn/collections/SLM-SQL-624bb6a60e9643) |
 ## News
@@ -55,6 +54,33 @@ Performance Comparison of different Text-to-SQL methods on BIRD dev and test dat
 <img src="https://raw.githubusercontent.com/CycloneBoy/slm_sql/main/data/image/slmsql_ablation_study.png"  height="300" alt="slmsql_ablation_study">
 ## Model
 | **Model**                                | Base Model                   | Train Method | Modelscope                                                                                        | HuggingFace                                                                                  |

 ---
 library_name: transformers
 license: cc-by-nc-4.0
+pipeline_tag: text-generation
 tags:
 - text-to-sql
 - reinforcement-learning
 ---
 # SLM-SQL: An Exploration of Small Language Models for Text-to-SQL
 ### Important Links
+📖[Arxiv Paper](https://arxiv.org/abs/2507.22478) | 💾[GitHub](https://github.com/CycloneBoy/slm_sql) |
+🤗[HuggingFace Collection](https://huggingface.co/collections/cycloneboy/slm-sql-688b02f99f958d7a417658dc) |
 🤖[ModelScope](https://modelscope.cn/collections/SLM-SQL-624bb6a60e9643) |
 ## News
 <img src="https://raw.githubusercontent.com/CycloneBoy/slm_sql/main/data/image/slmsql_ablation_study.png"  height="300" alt="slmsql_ablation_study">
+## Sample Usage
+You can use the model with the `transformers` library. Here's an example:
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+# Load the tokenizer and model (e.g., SLM-SQL-1.5B)
+model_name = "cycloneboy/SLM-SQL-1.5B" # Adjust this to the specific model you want to use
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
+# Define the input prompt (natural language question for SQL)
+prompt = "what are the names of all employees?"
+# Prepare the input for the model
+input_ids = tokenizer.encode(prompt, return_tensors="pt").to(model.device)
+# Generate the SQL query
+output_ids = model.generate(input_ids, max_new_tokens=100, num_beams=1, do_sample=False)
+generated_sql = tokenizer.decode(output_ids[0], skip_special_tokens=True)
+print("Generated SQL Query:")
+print(generated_sql)
+```
 ## Model
 | **Model**                                | Base Model                   | Train Method | Modelscope                                                                                        | HuggingFace                                                                                  |