PipableAI/pip-SQL-1B

Pipable’s pipSQL

Please refer to https://huggingface.co/PipableAI/pipSQL-1.3b for our state of the art model, that gives better performance than chatgpt and claude on sql tasks on a lot of benchmarks.

Pipable’s pipSQL is a model distilled from llama 1b to generate sql queries given prompt and schema. We used a unique pipeline which involved the model working on two objectives alternatively ----

1. Maximizing the log prob of all tokens in the sequence (including the prompt tokens)
2. Minimizng the difference between the true value and the predicted maximum value of the output tokens i.e generated tokens for the sql query slice of the entire sequence.

License

The model's new weights along with all other assets involved with it are open sourced under mit license.

How to Use

text = """<schema>{schema}</schema>
<question>{question}</question>
<sql>"""

pytorch

from transformers import AutoModelForCasualLM, AutoTokenizer
device = "cuda"
model = AutoModelForCausalLM.from_pretrained("PipableAI/pipSQL1b")
tokenizer = AutoTokenizer.from_pretrained("PipableAI/pipSQL1b")

inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs, max_new_tokens=200)
print(tokenizer.decode(outputs[0], skip_special_tokens=True).split('<sql>')[1].split('</sql>')[0])

flax

from transformers import FlaxAutoModelForCasualLM, AutoTokenizer
model = FlaxAutoModelForCausalLM.from_pretrained("PipableAI/pipSQL1b" , from_pt=True)
tokenizer = AutoTokenizer.from_pretrained("PipableAI/pipSQL1b")

The PipableAI team

Avi Kothari, Pratham Gupta, Ritvik Aryan Kalra, Rohan Bhatial, Soham Acharya