Instructions to use adiitya0929/TinySQL-125M-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adiitya0929/TinySQL-125M-base with Transformers:

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

pipe = pipeline("text-generation", model="adiitya0929/TinySQL-125M-base")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("adiitya0929/TinySQL-125M-base")
model = AutoModelForCausalLM.from_pretrained("adiitya0929/TinySQL-125M-base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use adiitya0929/TinySQL-125M-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "adiitya0929/TinySQL-125M-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adiitya0929/TinySQL-125M-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/adiitya0929/TinySQL-125M-base

SGLang

How to use adiitya0929/TinySQL-125M-base 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 "adiitya0929/TinySQL-125M-base" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adiitya0929/TinySQL-125M-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "adiitya0929/TinySQL-125M-base" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adiitya0929/TinySQL-125M-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use adiitya0929/TinySQL-125M-base with Docker Model Runner:
```
docker model run hf.co/adiitya0929/TinySQL-125M-base
```

adiitya0929 commited on 5 days ago

Commit

66503a8

verified ·

1 Parent(s): 6a2d676

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -0

README.md CHANGED Viewed

@@ -21,6 +21,7 @@ The pretrained base model of TinySQL: a 125M-parameter decoder trained from rand
 - **Paper:** [TinySQL: A 125M-Parameter Text-to-SQL Model Built and Pretrained From Scratch on 4.5B Tokens](https://doi.org/10.5281/zenodo.23396770) (Zenodo, 2026)
 - **Code:** [github.com/aditya0929/tinysql](https://github.com/aditya0929/tinysql)
 ## Quick start

 - **Paper:** [TinySQL: A 125M-Parameter Text-to-SQL Model Built and Pretrained From Scratch on 4.5B Tokens](https://doi.org/10.5281/zenodo.23396770) (Zenodo, 2026)
 - **Code:** [github.com/aditya0929/tinysql](https://github.com/aditya0929/tinysql)
+- **feel free to contact me at** - https://www.linkedin.com/in/aditya-narayan-jha-36193a251/
 ## Quick start