Instructions to use QuantFactory/sqlcoder-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QuantFactory/sqlcoder-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="QuantFactory/sqlcoder-GGUF")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("QuantFactory/sqlcoder-GGUF", dtype="auto")

llama-cpp-python

How to use QuantFactory/sqlcoder-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QuantFactory/sqlcoder-GGUF",
	filename="sqlcoder.Q2_K.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use QuantFactory/sqlcoder-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/sqlcoder-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/sqlcoder-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QuantFactory/sqlcoder-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QuantFactory/sqlcoder-GGUF:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf QuantFactory/sqlcoder-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QuantFactory/sqlcoder-GGUF:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf QuantFactory/sqlcoder-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QuantFactory/sqlcoder-GGUF:Q4_K_M

Use Docker

docker model run hf.co/QuantFactory/sqlcoder-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use QuantFactory/sqlcoder-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "QuantFactory/sqlcoder-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantFactory/sqlcoder-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/QuantFactory/sqlcoder-GGUF:Q4_K_M

SGLang

How to use QuantFactory/sqlcoder-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "QuantFactory/sqlcoder-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantFactory/sqlcoder-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "QuantFactory/sqlcoder-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "QuantFactory/sqlcoder-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use QuantFactory/sqlcoder-GGUF with Ollama:
```
ollama run hf.co/QuantFactory/sqlcoder-GGUF:Q4_K_M
```

Unsloth Studio

How to use QuantFactory/sqlcoder-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for QuantFactory/sqlcoder-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for QuantFactory/sqlcoder-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QuantFactory/sqlcoder-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use QuantFactory/sqlcoder-GGUF with Docker Model Runner:
```
docker model run hf.co/QuantFactory/sqlcoder-GGUF:Q4_K_M
```

Lemonade

How to use QuantFactory/sqlcoder-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QuantFactory/sqlcoder-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.sqlcoder-GGUF-Q4_K_M

List all available models

lemonade list

sqlcoder-GGUF / README.md

aashish1904

Upload README.md with huggingface_hub

5d87399 verified almost 2 years ago

preview code

raw

history blame contribute delete

4.43 kB


	---

	license: other
	language:
	- en
	metrics:
	- code_eval
	library_name: transformers
	pipeline_tag: text-generation
	tags:
	- code
	inference: false

	---

	[![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory)


	# QuantFactory/sqlcoder-GGUF
	This is quantized version of [defog/sqlcoder](https://huggingface.co/defog/sqlcoder) created using llama.cpp

	# Original Model Card

	# ARCHIVE NOTICE
	This repository is now significantly outdated. You should use the repository at [sqlcoder-7b-2](https://huggingface.co/defog/sqlcoder-7b-2) instead. It is significantly better and consumes fewer GPU resources.

	# Defog SQLCoder
	Defog's SQLCoder is a state-of-the-art LLM for converting natural language questions to SQL queries.

	[Interactive Demo](https://defog.ai/sqlcoder-demo) \| [♾️ Colab](https://colab.research.google.com/drive/1z4rmOEiFkxkMiecAWeTUlPl0OmKgfEu7) \| [🐦 Twitter](https://twitter.com/defogdata)

	## 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](https://github.com/defog-ai/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](./inference.py). You can also use a demo on our website [here](https://defog.ai/sqlcoder-demo), or run SQLCoder in Colab [here](https://colab.research.google.com/drive/13BIKsqHnPOBcQ-ba2p77L5saiepTIwu0#scrollTo=ZpbVgVHMkJvC)

	## 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

	- [x] 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