Instructions to use defog/sqlcoder-7b-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use defog/sqlcoder-7b-2 with Transformers:

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

pipe = pipeline("text-generation", model="defog/sqlcoder-7b-2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("defog/sqlcoder-7b-2")
model = AutoModelForCausalLM.from_pretrained("defog/sqlcoder-7b-2")

llama-cpp-python

How to use defog/sqlcoder-7b-2 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="defog/sqlcoder-7b-2",
	filename="sqlcoder-7b-q5_k_m.gguf",
)

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

Inference
Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use defog/sqlcoder-7b-2 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf defog/sqlcoder-7b-2:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf defog/sqlcoder-7b-2:Q5_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf defog/sqlcoder-7b-2:Q5_K_M
# Run inference directly in the terminal:
llama-cli -hf defog/sqlcoder-7b-2:Q5_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 defog/sqlcoder-7b-2:Q5_K_M
# Run inference directly in the terminal:
./llama-cli -hf defog/sqlcoder-7b-2:Q5_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 defog/sqlcoder-7b-2:Q5_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf defog/sqlcoder-7b-2:Q5_K_M

Use Docker

docker model run hf.co/defog/sqlcoder-7b-2:Q5_K_M

LM Studio
Jan

vLLM

How to use defog/sqlcoder-7b-2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "defog/sqlcoder-7b-2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "defog/sqlcoder-7b-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/defog/sqlcoder-7b-2:Q5_K_M

SGLang

How to use defog/sqlcoder-7b-2 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 "defog/sqlcoder-7b-2" \
    --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": "defog/sqlcoder-7b-2",
		"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 "defog/sqlcoder-7b-2" \
        --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": "defog/sqlcoder-7b-2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use defog/sqlcoder-7b-2 with Ollama:
```
ollama run hf.co/defog/sqlcoder-7b-2:Q5_K_M
```

Unsloth Studio new

How to use defog/sqlcoder-7b-2 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 defog/sqlcoder-7b-2 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 defog/sqlcoder-7b-2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for defog/sqlcoder-7b-2 to start chatting

Docker Model Runner
How to use defog/sqlcoder-7b-2 with Docker Model Runner:
```
docker model run hf.co/defog/sqlcoder-7b-2:Q5_K_M
```

Lemonade

How to use defog/sqlcoder-7b-2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull defog/sqlcoder-7b-2:Q5_K_M

Run and chat with the model

lemonade run user.sqlcoder-7b-2-Q5_K_M

List all available models

lemonade list

Running models on the Google Colab / Macbook pro m1

#11

by ajayyadav2055 - opened Feb 25, 2024

Discussion

ajayyadav2055

Feb 25, 2024

Hello Creators, i tried the demo in the defog web version with my custom table and it showed some great results . however, when i use it in the Google colab using the TPU, it gets crashed even with 12GB System ram.
I wanted to understand that how do i use these 7B models or even 34B models with low end configurations. Is there any way i can even use it or we have to use the high end configurations.

ajayyadav2055

Feb 25, 2024

@rishdotblog if you have any better approach to the above, please let the community know. Thanks

jp-defog

Feb 26, 2024

Hi @ajayyadav2055 , thanks for giving our model a run. Unfortunately we've not tried out hosting the model in TPU's, although our prior experience with GPU's would suggest that you would need at least 14GB of RAM to host the model in half precision (2 bytes per parameter), for which 12GB would be insufficient. You can try TPU architecture specific post-training quantization methods (https://cloud.google.com/blog/products/compute/accurate-quantized-training-aqt-for-tpu-v5e), but you might see the quality of the results to degrade slightly while doing so.

ajayyadav2055

Feb 28, 2024

hey @jp-defog , thanks for the info. Can we do the sharding of this model like HuggingFaceH4/zephyr-7b-alpha model, to make it run on the google colab in 1GB of chunks.

pratham-pi

Mar 11, 2024

@ajayyadav2055 You can try https://huggingface.co/PipableAI/pip-sql-1.3b this model for text-to-sql in 1.3B parameters. It surpasses GPT-3.5 in spider dataset.

jp-defog

Mar 11, 2024

Hi @ajayyadav2055 could you share more on how this chunking is done? I don't use collab much but am familiar with huggingface's default pipeline parallelism when running in a single node distributed GPU setting.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment