Instructions to use AlioLeuchtmann/ALIO-SQL-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AlioLeuchtmann/ALIO-SQL-7B with Transformers:

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

pipe = pipeline("text-generation", model="AlioLeuchtmann/ALIO-SQL-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AlioLeuchtmann/ALIO-SQL-7B")
model = AutoModelForCausalLM.from_pretrained("AlioLeuchtmann/ALIO-SQL-7B")
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 AlioLeuchtmann/ALIO-SQL-7B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/AlioLeuchtmann/ALIO-SQL-7B

SGLang

How to use AlioLeuchtmann/ALIO-SQL-7B 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 "AlioLeuchtmann/ALIO-SQL-7B" \
    --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": "AlioLeuchtmann/ALIO-SQL-7B",
		"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 "AlioLeuchtmann/ALIO-SQL-7B" \
        --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": "AlioLeuchtmann/ALIO-SQL-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AlioLeuchtmann/ALIO-SQL-7B with Docker Model Runner:
```
docker model run hf.co/AlioLeuchtmann/ALIO-SQL-7B
```

AlioLeuchtmann commited on May 29, 2025

Commit

9973311

verified ·

1 Parent(s): 39e24d1

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -1

README.md CHANGED Viewed

@@ -45,12 +45,15 @@ After training, this checkpoint even exceeds the performance of its teacher mode
 ## Prompt:
 ```sql
 CREATE TABLE geographic\n(\n    city   TEXT not null\n        primary key,\n    county TEXT null,\n    region TEXT null\n) \n /* \n 2 example rows: \n SELECT * FROM geographic LIMIT 2; \n    city              county   region \nalameda      alameda county bay area \n  alamo contra costa county bay area  \n */\n\n <br>
 CREATE TABLE generalinfo\n(\n    id_restaurant INTEGER         not null\n        primary key,\n    label         TEXT  null,\n    food_type     TEXT  null,\n    city          TEXT  null,\n    review        REAL null,\n    foreign key (city) references geographic(city)\n            on update cascade on delete cascade\n) \n /* \n 2 example rows: \n SELECT * FROM generalinfo LIMIT 2; \n id_restaurant                label     food_type          city review \n            1       sparky's diner 24 hour diner san francisco    2.3 \n            2 kabul afghan cuisine       afghani    san carlos    3.8  \n */\n\nCREATE TABLE location\n(\n    id_restaurant INTEGER        not null\n        primary key,\n    street_num    INTEGER          null,\n    street_name   TEXT null,\n    city          TEXT null,\n    foreign key (city) references geographic (city)\n            on update cascade on delete cascade,\n    foreign key (id_restaurant) references generalinfo (id_restaurant)\n            on update cascade on delete cascade\n) \n /* \n 2 example rows: \n SELECT * FROM location LIMIT 2; \n id_restaurant street_num    street_name          city \n            1        242      church st san francisco \n            2        135 el camino real    san carlos  \n */\n\n  <br>
 -- External Knowledge: Atlantic Ave refers to street_name = 'atlantic ave'; rating refers to review\n  <br>
 -- Using valid SQLite and understanding External Knowledge, answer the following question for the tables provided above.\n  <br>
--- What is the rating of each restaurant reviews on Atlantic Ave?\nGenerate the SQL after thinking step by step:\n  <br>
 ```
@@ -68,4 +71,7 @@ You are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>
 '''
 ```

 ## Prompt:
+Single Prompt used throughout the Dataset so best used as follows:
 ```sql
 CREATE TABLE geographic\n(\n    city   TEXT not null\n        primary key,\n    county TEXT null,\n    region TEXT null\n) \n /* \n 2 example rows: \n SELECT * FROM geographic LIMIT 2; \n    city              county   region \nalameda      alameda county bay area \n  alamo contra costa county bay area  \n */\n\n <br>
 CREATE TABLE generalinfo\n(\n    id_restaurant INTEGER         not null\n        primary key,\n    label         TEXT  null,\n    food_type     TEXT  null,\n    city          TEXT  null,\n    review        REAL null,\n    foreign key (city) references geographic(city)\n            on update cascade on delete cascade\n) \n /* \n 2 example rows: \n SELECT * FROM generalinfo LIMIT 2; \n id_restaurant                label     food_type          city review \n            1       sparky's diner 24 hour diner san francisco    2.3 \n            2 kabul afghan cuisine       afghani    san carlos    3.8  \n */\n\nCREATE TABLE location\n(\n    id_restaurant INTEGER        not null\n        primary key,\n    street_num    INTEGER          null,\n    street_name   TEXT null,\n    city          TEXT null,\n    foreign key (city) references geographic (city)\n            on update cascade on delete cascade,\n    foreign key (id_restaurant) references generalinfo (id_restaurant)\n            on update cascade on delete cascade\n) \n /* \n 2 example rows: \n SELECT * FROM location LIMIT 2; \n id_restaurant street_num    street_name          city \n            1        242      church st san francisco \n            2        135 el camino real    san carlos  \n */\n\n  <br>
 -- External Knowledge: Atlantic Ave refers to street_name = 'atlantic ave'; rating refers to review\n  <br>
 -- Using valid SQLite and understanding External Knowledge, answer the following question for the tables provided above.\n  <br>
+-- What is the rating of each restaurant reviews on Atlantic Ave?\n <br>
+Generate the SQL after thinking step by step:\n  <br>
 ```
 '''
 ```
+### Generation Config:
+- No Sampling for best Performance