Quantization made by Richard Erkhov.

Github

Discord

Request more models

sqlcoder-7b-2 - GGUF

• Model creator: https://huggingface.co/defog/
• Original model: https://huggingface.co/defog/sqlcoder-7b-2/

Name	Quant method	Size
sqlcoder-7b-2.Q2K.gguf	Q2K	2.36GB
sqlcoder-7b-2.IQ3XS.gguf	IQ3XS	2.6GB
sqlcoder-7b-2.IQ3S.gguf	IQ3S	2.75GB
sqlcoder-7b-2.Q3KS.gguf	Q3K_S	2.75GB
sqlcoder-7b-2.IQ3M.gguf	IQ3M	2.9GB
sqlcoder-7b-2.Q3K.gguf	Q3K	3.07GB
sqlcoder-7b-2.Q3KM.gguf	Q3K_M	3.07GB
sqlcoder-7b-2.Q3KL.gguf	Q3K_L	3.35GB
sqlcoder-7b-2.IQ4XS.gguf	IQ4XS	3.4GB
sqlcoder-7b-2.Q40.gguf	Q40	3.56GB
sqlcoder-7b-2.IQ4NL.gguf	IQ4NL	3.58GB
sqlcoder-7b-2.Q4KS.gguf	Q4K_S	3.59GB
sqlcoder-7b-2.Q4K.gguf	Q4K	3.8GB
sqlcoder-7b-2.Q4KM.gguf	Q4K_M	3.8GB
sqlcoder-7b-2.Q41.gguf	Q41	3.95GB
sqlcoder-7b-2.Q50.gguf	Q50	4.33GB
sqlcoder-7b-2.Q5KS.gguf	Q5K_S	4.33GB
sqlcoder-7b-2.Q5K.gguf	Q5K	4.45GB
sqlcoder-7b-2.Q5KM.gguf	Q5K_M	4.45GB
sqlcoder-7b-2.Q51.gguf	Q51	4.72GB
sqlcoder-7b-2.Q6K.gguf	Q6K	5.15GB

Original model description:

---

license: cc-by-sa-4.0
library_name: transformers
pipeline_tag: text-generation

---

Update notice

The model weights were updated at 7 AM UTC on Feb 7, 2024. The new model weights lead to a much more performant model – particularly for joins.

If you downloaded the model before that, please redownload the weights for best performance.

Model Card for SQLCoder-7B-2

A capable large language model for natural language to SQL generation.

!image/png

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

• Developed by: Defog, Inc
• Model type: [Text to SQL]
• License: [CC-by-SA-4.0]
• Finetuned from model: [CodeLlama-7B]

Model Sources [optional]

• HuggingFace:
• GitHub:
• Demo:

Uses

This model is intended to be used by non-technical users to understand data inside their SQL databases. It is meant as an analytics tool, and not as a database admin tool.

This model has not been trained to reject malicious requests from users with write access to databases, and should only be used by users with read-only access.

How to Get Started with the Model

Use the code here to get started with the model.

Prompt

Please use the following prompt for optimal results. Please remember to use dosample=False and numbeams=4 for optimal results.

### Task
Generate a SQL query to answer [QUESTION]{user_question}[/QUESTION]

Database Schema
The query will run on a database with the following schema:
{tablemetadatastringDDLstatements}

Answer
Given the database schema, here is the SQL query that [QUESTION]{user_question}[/QUESTION]
[SQL]

Evaluation

This model was evaluated on SQL-Eval, a PostgreSQL based evaluation framework developed by Defog for testing and alignment of model capabilities.

You can read more about the methodology behind SQLEval here.

Results

We classified each generated question into one of 6 categories. The table displays the percentage of questions answered correctly by each model, broken down by category.

	date	groupby	orderby	ratio	join	where
sqlcoder-70b	96	91.4	97.1	85.7	97.1	91.4
sqlcoder-7b-2	96	91.4	94.3	91.4	94.3	77.1
sqlcoder-34b	80	94.3	85.7	77.1	85.7	80
gpt-4	72	94.3	97.1	80	91.4	80
gpt-4-turbo	76	91.4	91.4	62.8	88.6	77.1
natural-sql-7b	56	88.6	85.7	60	88.6	80
sqlcoder-7b	64	82.9	74.3	54.3	74.3	74.3
gpt-3.5	72	77.1	82.8	34.3	65.7	71.4
claude-2	52	71.4	74.3	57.1	65.7	62.9

Model Card Contact

Contact us on X at @defogdata, or on email at [email protected]