RichardErkhov/PipableAI_-_pip-SQL-1B-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

pip-SQL-1B - GGUF

• Model creator: https://huggingface.co/PipableAI/
• Original model: https://huggingface.co/PipableAI/pip-SQL-1B/

Name	Quant method	Size
pip-SQL-1B.Q2_K.gguf	Q2_K	0.52GB
pip-SQL-1B.IQ3_XS.gguf	IQ3_XS	0.57GB
pip-SQL-1B.IQ3_S.gguf	IQ3_S	0.6GB
pip-SQL-1B.Q3_K_S.gguf	Q3_K_S	0.6GB
pip-SQL-1B.IQ3_M.gguf	IQ3_M	0.63GB
pip-SQL-1B.Q3_K.gguf	Q3_K	0.66GB
pip-SQL-1B.Q3_K_M.gguf	Q3_K_M	0.66GB
pip-SQL-1B.Q3_K_L.gguf	Q3_K_L	0.69GB
pip-SQL-1B.IQ4_XS.gguf	IQ4_XS	0.7GB
pip-SQL-1B.Q4_0.gguf	Q4_0	0.72GB
pip-SQL-1B.IQ4_NL.gguf	IQ4_NL	0.73GB
pip-SQL-1B.Q4_K_S.gguf	Q4_K_S	0.76GB
pip-SQL-1B.Q4_K.gguf	Q4_K	0.81GB
pip-SQL-1B.Q4_K_M.gguf	Q4_K_M	0.81GB
pip-SQL-1B.Q4_1.gguf	Q4_1	0.8GB
pip-SQL-1B.Q5_0.gguf	Q5_0	0.87GB
pip-SQL-1B.Q5_K_S.gguf	Q5_K_S	0.89GB
pip-SQL-1B.Q5_K.gguf	Q5_K	0.93GB
pip-SQL-1B.Q5_K_M.gguf	Q5_K_M	0.93GB
pip-SQL-1B.Q5_1.gguf	Q5_1	0.95GB
pip-SQL-1B.Q6_K.gguf	Q6_K	1.09GB
pip-SQL-1B.Q8_0.gguf	Q8_0	1.33GB

Original model description:

license: mit language: - en metrics: - accuracy pipeline_tag: text-generation widget: - text: "CREATE TABLE radio(age VARCHAR, radio_id VARCHAR, frequency VARCHAR, wavelength VARCHAR); CREATE TABLE radio_faults(radio_id VARCHAR, fault_description VARCHAR)Get the radio id and defect descriptions of radios that have wavelength greater than 30 ?" example_title: "example1" - text: "CREATE TABLE system(JobID: String,GID: String, UID: String, Start:Time(yyyy/mm/dd), End: Time,ElapsedRaw: Time, CPUTimeRAW: Time,NCPUS: Number,NNodes: Number, NodeList: List, State:String, Timelimit: Time);Get UID and job id for Jobs that started on Jan 20 , 2023" example_title: "example2" - text: "CREATE TABLE department (Department_ID number, Name text, Creation text, Ranking number, Budget_in_Billions number, Num_Employees number) which has Department_ID as primary key abd CREATE TABLE head (head_ID number, name text, born_state text, age number) which has head_ID as primary key and CREATE TABLE management (department_ID number, head_ID number, temporary_acting text) which has department_ID as primary key" example_title: "example3" tags: - code - sql - text2sql - instruction_tuned - jax - pytorch - 1b - expert datasets: - PipableAI/spider-bird

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