Instructions to use Hugo991/SQLBuilder with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Hugo991/SQLBuilder with Transformers:

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

pipe = pipeline("text-generation", model="Hugo991/SQLBuilder")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Hugo991/SQLBuilder")
model = AutoModelForCausalLM.from_pretrained("Hugo991/SQLBuilder")
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 Settings

vLLM

How to use Hugo991/SQLBuilder with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hugo991/SQLBuilder"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hugo991/SQLBuilder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Hugo991/SQLBuilder

SGLang

How to use Hugo991/SQLBuilder 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 "Hugo991/SQLBuilder" \
    --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": "Hugo991/SQLBuilder",
		"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 "Hugo991/SQLBuilder" \
        --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": "Hugo991/SQLBuilder",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Hugo991/SQLBuilder with Docker Model Runner:
```
docker model run hf.co/Hugo991/SQLBuilder
```

SQLBuilder / generation_config.json

Hugo991

Upload folder using huggingface_hub

4321963 verified 6 months ago

raw

history blame contribute delete

777 Bytes

	{
	"bos_token_id": 151644,
	"do_sample": true,
	"eos_token_id": 151645,
	"pad_token_id": 151645,
	"temperature": 0.7,
	"top_k": 20,
	"top_p": 0.8,
	"transformers_version": "4.56.1",

	"prompt_template": "<\|im_start\|>system\nYou are a strict SQL generation engine.\nYour only task is to convert natural language instructions into valid SQL queries.\nRules:\n1. Output ONLY SQL. No explanations, no comments.\n2. Always generate syntactically correct SQL.\n3. Never invent tables or columns. If context is missing, propose a safe generic structure.\n4. Use explicit column lists, never SELECT *.\n5. Use clear table aliases when joins are present.\n6. Keep formatting clean and standardized.\n<\|im_end\|>\n<\|im_start\|>user\n{input}\n<\|im_end\|>\n<\|im_start\|>assistant\n"
	}