## Task
Generate a SQL query to answer the following question:
`{prompt}`
### Database Schema
This query will run on a database whose schema is represented in this string:
CREATE TABLE products (
product_id INTEGER PRIMARY KEY, -- Unique ID for each product
name VARCHAR(50), -- Name of the product
price DECIMAL(10,2), -- Price of each unit of the product
quantity INTEGER -- Current quantity in stock
);
CREATE TABLE sales (
sale_id INTEGER PRIMARY KEY, -- Unique ID for each sale
product_id INTEGER, -- ID of product sold
customer_id INTEGER, -- ID of customer who made purchase
salesperson_id INTEGER, -- ID of salesperson who made the sale
sale_date DATE, -- Date the sale occurred
quantity INTEGER -- Quantity of product sold
);
-- sales.product_id can be joined with products.product_id
### SQL
Given the database schema, here is the SQL query that answers `{prompt}`:
```sql
Compatibility
These quantised GGUFv2 files are compatible with llama.cpp from August 27th onwards, as of commit d0cee0d
They are also compatible with many third party UIs and libraries - please see the list at the top of this README.
Explanation of quantisation methods
Click to see details
The new methods available are:
GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
Refer to the Provided Files table below to see what files use which methods, and how.
very large, extremely low quality loss - not recommended
Note: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
How to download GGUF files
Note for manual downloaders: You almost never want to clone the entire repo! Multiple different quantisation formats are provided, and most users only want to pick and download a single file.
The following clients/libraries will automatically download models for you, providing a list of available models to choose from:
LM Studio
LoLLMS Web UI
Faraday.dev
In text-generation-webui
Under Download Model, you can enter the model repo: TheBloke/sqlcoder2-GGUF and below it, a specific filename to download, such as: sqlcoder2.Q4_K_M.gguf.
Then click Download.
On the command line, including multiple files at once
I recommend using the huggingface-hub Python library:
pip3 install huggingface-hub
Then you can download any individual model file to the current directory, at high speed, with a command like this:
Windows Command Line users: You can set the environment variable by running set HF_HUB_ENABLE_HF_TRANSFER=1 before the download command.
Example llama.cpp command
Make sure you are using llama.cpp from commit d0cee0d or later.
./main -ngl 32 -m sqlcoder2.Q4_K_M.gguf --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "## Task\nGenerate a SQL query to answer the following question:\n`{prompt}`\n\n### Database Schema\nThis query will run on a database whose schema is represented in this string:\nCREATE TABLE products (\n product_id INTEGER PRIMARY KEY, -- Unique ID for each product\n name VARCHAR(50), -- Name of the product\n price DECIMAL(10,2), -- Price of each unit of the product\n quantity INTEGER -- Current quantity in stock\n);\n\nCREATE TABLE sales (\n sale_id INTEGER PRIMARY KEY, -- Unique ID for each sale\n product_id INTEGER, -- ID of product sold\n customer_id INTEGER, -- ID of customer who made purchase\n salesperson_id INTEGER, -- ID of salesperson who made the sale\n sale_date DATE, -- Date the sale occurred\n quantity INTEGER -- Quantity of product sold\n);\n\n-- sales.product_id can be joined with products.product_id\n\n### SQL\nGiven the database schema, here is the SQL query that answers `{prompt}`:\n```sql"
Change -ngl 32 to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
Change -c 2048 to the desired sequence length. For extended sequence models - eg 8K, 16K, 32K - the necessary RoPE scaling parameters are read from the GGUF file and set by llama.cpp automatically.
If you want to have a chat-style conversation, replace the -p <PROMPT> argument with -i -ins
How to load this model in Python code, using ctransformers
First install the package
Run one of the following commands, according to your system:
shell
1# Base ctransformers with no GPU acceleration2pip install ctransformers
3# Or with CUDA GPU acceleration4pip install ctransformers[cuda]5# Or with AMD ROCm GPU acceleration (Linux only)6CT_HIPBLAS=1 pip install ctransformers --no-binary ctransformers
7# Or with Metal GPU acceleration for macOS systems only8CT_METAL=1 pip install ctransformers --no-binary ctransformers
Simple ctransformers example code
python
1from ctransformers import AutoModelForCausalLM
23# Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.4llm = AutoModelForCausalLM.from_pretrained("TheBloke/sqlcoder2-GGUF", model_file="sqlcoder2.Q4_K_M.gguf", model_type="starcoder", gpu_layers=50)56print(llm("AI is going to"))
How to use with LangChain
Here are guides on using llama-cpp-python and ctransformers with LangChain:
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
Patreon special mentions: Pierre Kircher, Stanislav Ovsiannikov, Michael Levine, Eugene Pentland, Andrey, 준교 김, Randy H, Fred von Graf, Artur Olbinski, Caitlyn Gatomon, terasurfer, Jeff Scroggin, James Bentley, Vadim, Gabriel Puliatti, Harry Royden McLaughlin, Sean Connelly, Dan Guido, Edmond Seymore, Alicia Loh, subjectnull, AzureBlack, Manuel Alberto Morcote, Thomas Belote, Lone Striker, Chris Smitley, Vitor Caleffi, Johann-Peter Hartmann, Clay Pascal, biorpg, Brandon Frisco, sidney chen, transmissions 11, Pedro Madruga, jinyuan sun, Ajan Kanaga, Emad Mostaque, Trenton Dambrowitz, Jonathan Leane, Iucharbius, usrbinkat, vamX, George Stoitzev, Luke Pendergrass, theTransient, Olakabola, Swaroop Kallakuri, Cap'n Zoog, Brandon Phillips, Michael Dempsey, Nikolai Manek, danny, Matthew Berman, Gabriel Tamborski, alfie_i, Raymond Fosdick, Tom X Nguyen, Raven Klaugh, LangChain4j, Magnesian, Illia Dulskyi, David Ziegler, Mano Prime, Luis Javier Navarrete Lozano, Erik Bjäreholt, 阿明, Nathan Dryer, Alex, Rainer Wilmers, zynix, TL, Joseph William Delisle, John Villwock, Nathan LeClaire, Willem Michiel, Joguhyik, GodLy, OG, Alps Aficionado, Jeffrey Morgan, ReadyPlayerEmma, Tiffany J. Kim, Sebastain Graf, Spencer Kim, Michael Davis, webtim, Talal Aujan, knownsqashed, John Detwiler, Imad Khwaja, Deo Leter, Jerry Meng, Elijah Stavena, Rooh Singh, Pieter, SuperWojo, Alexandros Triantafyllidis, Stephen Murray, Ai Maven, ya boyyy, Enrico Ros, Ken Nordquist, Deep Realms, Nicholas, Spiking Neurons AB, Elle, Will Dee, Jack West, RoA, Luke @flexchar, Viktor Bowallius, Derek Yates, Subspace Studios, jjj, Toran Billups, Asp the Wyvern, Fen Risland, Ilya, NimbleBox.ai, Chadd, Nitin Borwankar, Emre, Mandus, Leonard Tan, Kalila, K, Trailburnt, S_X, Cory Kujawski
Thank you to all my generous patrons and donaters!
And thank you again to a16z for their generous grant.
Original model card: Defog.ai's Sqlcoder2
Defog SQLCoder
Defog's SQLCoder is a state-of-the-art LLM for converting natural language questions to SQL queries.
SQLCoder is a 15B parameter model that outperforms gpt-3.5-turbo for natural language to SQL generation tasks on our sql-eval framework, and significantly outperforms all popular open-source models. When fine-tuned on a given schema, it also outperforms gpt-4
SQLCoder is fine-tuned on a base StarCoder model.
Results on novel datasets not seen in training
model
perc_correct
gpt4-2023-10-04
82.0
defog-sqlcoder2
74.5
gpt4-2023-08-28
74.0
defog-sqlcoder-7b
71.0
gpt-3.5-2023-10-04
66.0
claude-2
64.5
gpt-3.5-2023-08-28
61.0
claude_instant_1
61.0
text-davinci-003
52.5
License
The code in this repo (what little there is of it) is Apache-2 licensed. The model weights have a CC BY-SA 4.0 license, with additional responsible use restrictions added. The TL;DR is that you can use and modify the model for any purpose – including commercial use. However, if you modify the weights (for example, by fine-tuning), you must open-source your modified weights under the same license terms.
Training
Defog was trained on more than 20,000 human-curated questions. These questions were based on 10 different schemas. None of the schemas in the training data were included in our evaluation framework.
We classified each generated question into one of 5 categories. The table displays the percentage of questions answered correctly by each model, broken down by category.
query_category
gpt-4
sqlcoder2-15b
sqlcoder-7b
gpt-3.5
claude-2
claude-instant
gpt-3
date
72
76
64
68
52
48
32
group_by
91.4
80
82.9
77.1
71.4
71.4
71.4
order_by
82.9
77.1
74.3
68.6
74.3
74.3
68.6
ratio
80
60
54.3
37.1
57.1
45.7
25.7
join
82.9
77.1
74.3
71.4
65.7
62.9
57.1
where
80
77.1
74.3
74.3
62.9
60
54.3
Using SQLCoder
You can use SQLCoder via the transformers library by downloading our model weights from the Hugging Face repo. We have added sample code for inference on a sample database schema.
bash
1python inference.py -q "Question about the sample database goes here"23# Sample question:4# Do we get more revenue from customers in New York compared to customers in San Francisco? Give me the total revenue for each city, and the difference between the two.
You can also use a demo on our website here, or run SQLCoder in Colab here
Hardware Requirements
SQLCoder has been tested on an A100 40GB GPU with bfloat16 weights. You can also load an 8-bit and 4-bit quantized version of the model on consumer GPUs with 20GB or more of memory – like RTX 4090, RTX 3090, and Apple M2 Pro, M2 Max, or M2 Ultra Chips with 20GB or more of memory.
Todo
Open-source the v1 model weights
Train the model on more data, with higher data variance
Tune the model further with Reward Modelling and RLHF
Pretrain a model from scratch that specializes in SQL analysis
