language:
- en
license: other
library_name: transformers
tags:
- code
metrics:
- code_eval
model_name: Sqlcoder
base_model: defog/sqlcoder
inference: false
model_creator: Defog.ai
model_type: starcoder
pipeline_tag: text-generation
prompt_template: |
{prompt}
quantized_by: TheBloke
TheBloke's LLM work is generously supported by a grant from andreessen horowitz (a16z)
Sqlcoder - GPTQ
Description
This repo contains GPTQ model files for Defog.ai's Sqlcoder.
Multiple GPTQ parameter permutations are provided; see Provided Files below for details of the options provided, their parameters, and the software used to create them.
Repositories available
- GPTQ models for GPU inference, with multiple quantisation parameter options.
- 2, 3, 4, 5, 6 and 8-bit GGUF models for CPU+GPU inference
- Defog.ai's original unquantised fp16 model in pytorch format, for GPU inference and for further conversions
Prompt template: Unknown
{prompt}
Provided files, and GPTQ parameters
Multiple quantisation parameters are provided, to allow you to choose the best one for your hardware and requirements.
Each separate quant is in a different branch. See below for instructions on fetching from different branches.
All recent GPTQ files are made with AutoGPTQ, and all files in non-main branches are made with AutoGPTQ. Files in the main branch which were uploaded before August 2023 were made with GPTQ-for-LLaMa.
Explanation of GPTQ parameters
- Bits: The bit size of the quantised model.
- GS: GPTQ group size. Higher numbers use less VRAM, but have lower quantisation accuracy. "None" is the lowest possible value.
- Act Order: True or False. Also known as
desc_act. True results in better quantisation accuracy. Some GPTQ clients have had issues with models that use Act Order plus Group Size, but this is generally resolved now. - Damp %: A GPTQ parameter that affects how samples are processed for quantisation. 0.01 is default, but 0.1 results in slightly better accuracy.
- GPTQ dataset: The calibration dataset used during quantisation. Using a dataset more appropriate to the model's training can improve quantisation accuracy. Note that the GPTQ calibration dataset is not the same as the dataset used to train the model - please refer to the original model repo for details of the training dataset(s).
- Sequence Length: The length of the dataset sequences used for quantisation. Ideally this is the same as the model sequence length. For some very long sequence models (16+K), a lower sequence length may have to be used. Note that a lower sequence length does not limit the sequence length of the quantised model. It only impacts the quantisation accuracy on longer inference sequences.
- ExLlama Compatibility: Whether this file can be loaded with ExLlama, which currently only supports Llama models in 4-bit.
| Branch | Bits | GS | Act Order | Damp % | GPTQ Dataset | Seq Len | Size | ExLlama | Desc |
|---|---|---|---|---|---|---|---|---|---|
| main | 4 | 128 | Yes | 0.1 | Evol Instruct Code | 4096 | 9.20 GB | No | 4-bit, with Act Order and group size 128g. Uses even less VRAM than 64g, but with slightly lower accuracy. |
| gptq-4-32g-actorder_True | 4 | 32 | Yes | 0.1 | Evol Instruct Code | 4096 | 10.09 GB | No | 4-bit, with Act Order and group size 32g. Gives highest possible inference quality, with maximum VRAM usage. |
| gptq-8--1g-actorder_True | 8 | None | Yes | 0.1 | Evol Instruct Code | 4096 | 16.49 GB | No | 8-bit, with Act Order. No group size, to lower VRAM requirements. |
| gptq-8-128g-actorder_True | 8 | 128 | Yes | 0.1 | Evol Instruct Code | 4096 | 16.84 GB | No | 8-bit, with group size 128g for higher inference quality and with Act Order for even higher accuracy. |
| gptq-8-32g-actorder_True | 8 | 32 | Yes | 0.1 | Evol Instruct Code | 4096 | 17.90 GB | No | 8-bit, with group size 32g and Act Order for maximum inference quality. |
| gptq-4-64g-actorder_True | 4 | 64 | Yes | 0.1 | Evol Instruct Code | 4096 | 9.49 GB | No | 4-bit, with Act Order and group size 64g. Uses less VRAM than 32g, but with slightly lower accuracy. |
How to download, including from branches
In text-generation-webui
To download from the main branch, enter TheBloke/sqlcoder-GPTQ in the "Download model" box.
To download from another branch, add :branchname to the end of the download name, eg TheBloke/sqlcoder-GPTQ:gptq-4-32g-actorder_True
From the command line
I recommend using the huggingface-hub Python library:
pip3 install huggingface-hub
To download the main branch to a folder called sqlcoder-GPTQ:
mkdir sqlcoder-GPTQ
huggingface-cli download TheBloke/sqlcoder-GPTQ --local-dir sqlcoder-GPTQ --local-dir-use-symlinks False
To download from a different branch, add the --revision parameter:
mkdir sqlcoder-GPTQ
huggingface-cli download TheBloke/sqlcoder-GPTQ --revision gptq-4-32g-actorder_True --local-dir sqlcoder-GPTQ --local-dir-use-symlinks False
More advanced huggingface-cli download usage
If you remove the --local-dir-use-symlinks False parameter, the files will instead be stored in the central Huggingface cache directory (default location on Linux is: ~/.cache/huggingface), and symlinks will be added to the specified --local-dir, pointing to their real location in the cache. This allows for interrupted downloads to be resumed, and allows you to quickly clone the repo to multiple places on disk without triggering a download again. The downside, and the reason why I don't list that as the default option, is that the files are then hidden away in a cache folder and it's harder to know where your disk space is being used, and to clear it up if/when you want to remove a download model.
The cache location can be changed with the HF_HOME environment variable, and/or the --cache-dir parameter to huggingface-cli.
For more documentation on downloading with huggingface-cli, please see: HF -> Hub Python Library -> Download files -> Download from the CLI.
To accelerate downloads on fast connections (1Gbit/s or higher), install hf_transfer:
pip3 install hf_transfer
And set environment variable HF_HUB_ENABLE_HF_TRANSFER to 1:
mkdir sqlcoder-GPTQ
HF_HUB_ENABLE_HF_TRANSFER=1 huggingface-cli download TheBloke/sqlcoder-GPTQ --local-dir sqlcoder-GPTQ --local-dir-use-symlinks False
Windows Command Line users: You can set the environment variable by running set HF_HUB_ENABLE_HF_TRANSFER=1 before the download command.
With git (not recommended)
To clone a specific branch with git, use a command like this:
git clone --single-branch --branch gptq-4-32g-actorder_True https://huggingface.co/TheBloke/sqlcoder-GPTQ
Note that using Git with HF repos is strongly discouraged. It will be much slower than using huggingface-hub, and will use twice as much disk space as it has to store the model files twice (it stores every byte both in the intended target folder, and again in the .git folder as a blob.)
How to easily download and use this model in text-generation-webui.
Please make sure you're using the latest version of text-generation-webui.
It is strongly recommended to use the text-generation-webui one-click-installers unless you're sure you know how to make a manual install.
- Click the Model tab.
- Under Download custom model or LoRA, enter
TheBloke/sqlcoder-GPTQ.
- To download from a specific branch, enter for example
TheBloke/sqlcoder-GPTQ:gptq-4-32g-actorder_True - see Provided Files above for the list of branches for each option.
- Click Download.
- The model will start downloading. Once it's finished it will say "Done".
- In the top left, click the refresh icon next to Model.
- In the Model dropdown, choose the model you just downloaded:
sqlcoder-GPTQ - The model will automatically load, and is now ready for use!
- If you want any custom settings, set them and then click Save settings for this model followed by Reload the Model in the top right.
- Note that you do not need to and should not set manual GPTQ parameters any more. These are set automatically from the file
quantize_config.json.
- Once you're ready, click the Text Generation tab and enter a prompt to get started!
How to use this GPTQ model from Python code
Install the necessary packages
Requires: Transformers 4.33.0 or later, Optimum 1.12.0 or later, and AutoGPTQ 0.4.2 or later.
pip3 install transformers optimum
pip3 install auto-gptq --extra-index-url https://huggingface.github.io/autogptq-index/whl/cu118/ # Use cu117 if on CUDA 11.7
If you have problems installing AutoGPTQ using the pre-built wheels, install it from source instead:
pip3 uninstall -y auto-gptq
git clone https://github.com/PanQiWei/AutoGPTQ
cd AutoGPTQ
git checkout v0.4.2
pip3 install .
You can then use the following code
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
model_name_or_path = "TheBloke/sqlcoder-GPTQ"
# To use a different branch, change revision
# For example: revision="gptq-4-32g-actorder_True"
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
device_map="auto",
trust_remote_code=False,
revision="main")
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
prompt = "Tell me about AI"
prompt_template=f'''{prompt}
'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, do_sample=True, top_p=0.95, top_k=40, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
do_sample=True,
temperature=0.7,
top_p=0.95,
top_k=40,
repetition_penalty=1.1
)
print(pipe(prompt_template)[0]['generated_text'])
Compatibility
The files provided are tested to work with AutoGPTQ, both via Transformers and using AutoGPTQ directly. They should also work with Occ4m's GPTQ-for-LLaMa fork.
ExLlama is compatible with Llama models in 4-bit. Please see the Provided Files table above for per-file compatibility.
Huggingface Text Generation Inference (TGI) is compatible with all GPTQ models.
Discord
For further support, and discussions on these models and AI in general, join us at:
Thanks, and how to contribute
Thanks to the chirper.ai team!
Thanks to Clay from gpus.llm-utils.org!
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: https://patreon.com/TheBlokeAI
- Ko-Fi: https://ko-fi.com/TheBlokeAI
Special thanks to: Aemon Algiz.
Patreon special mentions: Alicia Loh, Stephen Murray, K, Ajan Kanaga, RoA, Magnesian, Deo Leter, Olakabola, Eugene Pentland, zynix, Deep Realms, Raymond Fosdick, Elijah Stavena, Iucharbius, Erik Bjäreholt, Luis Javier Navarrete Lozano, Nicholas, theTransient, John Detwiler, alfie_i, knownsqashed, Mano Prime, Willem Michiel, Enrico Ros, LangChain4j, OG, Michael Dempsey, Pierre Kircher, Pedro Madruga, James Bentley, Thomas Belote, Luke @flexchar, Leonard Tan, Johann-Peter Hartmann, Illia Dulskyi, Fen Risland, Chadd, S_X, Jeff Scroggin, Ken Nordquist, Sean Connelly, Artur Olbinski, Swaroop Kallakuri, Jack West, Ai Maven, David Ziegler, Russ Johnson, transmissions 11, John Villwock, Alps Aficionado, Clay Pascal, Viktor Bowallius, Subspace Studios, Rainer Wilmers, Trenton Dambrowitz, vamX, Michael Levine, 준교 김, Brandon Frisco, Kalila, Trailburnt, Randy H, Talal Aujan, Nathan Dryer, Vadim, 阿明, ReadyPlayerEmma, Tiffany J. Kim, George Stoitzev, Spencer Kim, Jerry Meng, Gabriel Tamborski, Cory Kujawski, Jeffrey Morgan, Spiking Neurons AB, Edmond Seymore, Alexandros Triantafyllidis, Lone Striker, Cap'n Zoog, Nikolai Manek, danny, ya boyyy, Derek Yates, usrbinkat, Mandus, TL, Nathan LeClaire, subjectnull, Imad Khwaja, webtim, Raven Klaugh, Asp the Wyvern, Gabriel Puliatti, Caitlyn Gatomon, Joseph William Delisle, Jonathan Leane, Luke Pendergrass, SuperWojo, Sebastain Graf, Will Dee, Fred von Graf, Andrey, Dan Guido, Daniel P. Andersen, Nitin Borwankar, Elle, Vitor Caleffi, biorpg, jjj, NimbleBox.ai, Pieter, Matthew Berman, terasurfer, Michael Davis, Alex, Stanislav Ovsiannikov
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 Sqlcoder
Defog SQLCoder
Defog's SQLCoder is a state-of-the-art LLM for converting natural language questions to SQL queries.
Interactive Demo | ♾️ Colab | 🐦 Twitter
TL;DR
SQLCoder is a 15B parameter model that slightly 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. It also significantly outperforms text-davinci-003, a model that's more than 10 times its size.
SQLCoder is fine-tuned on a base StarCoder model.
Results on novel datasets not seen in training
| model | perc_correct |
|---|---|
| gpt-4 | 74.3 |
| defog-sqlcoder | 64.6 |
| gpt-3.5-turbo | 60.6 |
| defog-easysql | 57.1 |
| text-davinci-003 | 54.3 |
| wizardcoder | 52.0 |
| starcoder | 45.1 |
License
The model weights have a CC BY-SA 4.0 license, with OpenRAIL-M clauses for responsible use attached. 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 CC BY-SA 4.0 license terms.
Training
Defog was trained on 10,537 human-curated questions across 2 epochs. These questions were based on 10 different schemas. None of the schemas in the training data were included in our evaluation framework.
Training happened in 2 phases. The first phase was on questions that were classified as "easy" or "medium" difficulty, and the second phase was on questions that were classified as "hard" or "extra hard" difficulty.
The results of training on our easy+medium data were stored in a model called defog-easy. We found that the additional training on hard+extra-hard data led to a 7 percentage point increase in performance.
Results by question category
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 | defog-sqlcoder | gpt-3.5-turbo | defog-easy | text-davinci-003 | wizard-coder | star-coder |
|---|---|---|---|---|---|---|---|
| group_by | 82.9 | 77.1 | 71.4 | 62.9 | 62.9 | 68.6 | 54.3 |
| order_by | 71.4 | 65.7 | 60.0 | 68.6 | 60.0 | 54.3 | 57.1 |
| ratio | 62.9 | 57.1 | 48.6 | 40.0 | 37.1 | 22.9 | 17.1 |
| table_join | 74.3 | 57.1 | 60.0 | 54.3 | 51.4 | 54.3 | 51.4 |
| where | 80.0 | 65.7 | 62.9 | 60.0 | 60.0 | 60.0 | 45.7 |
Using SQLCoder
You can use SQLCoder via the transformers library by downloading our model weights from the HuggingFace repo. We have added sample code for inference here. 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 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