Instructions to use whoami02/defog-sqlcoder-2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use whoami02/defog-sqlcoder-2-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="whoami02/defog-sqlcoder-2-GGUF",
	filename="sqlcoder-7b-2.q8_0.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use whoami02/defog-sqlcoder-2-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf whoami02/defog-sqlcoder-2-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf whoami02/defog-sqlcoder-2-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf whoami02/defog-sqlcoder-2-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf whoami02/defog-sqlcoder-2-GGUF:Q8_0

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 whoami02/defog-sqlcoder-2-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf whoami02/defog-sqlcoder-2-GGUF:Q8_0

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 whoami02/defog-sqlcoder-2-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf whoami02/defog-sqlcoder-2-GGUF:Q8_0

Use Docker

docker model run hf.co/whoami02/defog-sqlcoder-2-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use whoami02/defog-sqlcoder-2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "whoami02/defog-sqlcoder-2-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "whoami02/defog-sqlcoder-2-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/whoami02/defog-sqlcoder-2-GGUF:Q8_0

Ollama
How to use whoami02/defog-sqlcoder-2-GGUF with Ollama:
```
ollama run hf.co/whoami02/defog-sqlcoder-2-GGUF:Q8_0
```

Unsloth Studio new

How to use whoami02/defog-sqlcoder-2-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 whoami02/defog-sqlcoder-2-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 whoami02/defog-sqlcoder-2-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for whoami02/defog-sqlcoder-2-GGUF to start chatting

Docker Model Runner
How to use whoami02/defog-sqlcoder-2-GGUF with Docker Model Runner:
```
docker model run hf.co/whoami02/defog-sqlcoder-2-GGUF:Q8_0
```

Lemonade

How to use whoami02/defog-sqlcoder-2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull whoami02/defog-sqlcoder-2-GGUF:Q8_0

Run and chat with the model

lemonade run user.defog-sqlcoder-2-GGUF-Q8_0

List all available models

lemonade list

Model Details

I do not claim ownership of this model.
It is converted into 8-bit GGUF format from original repository huggingface.co/defog/sqlcoder-7b-2

Model Description

Developed by: Defog AI

Model Sources

Repository: https://huggingface.co/defog/sqlcoder-7b-2

Example usage

With Llamacpp:

from langchain_community.llms. llamacpp import Llamacpp
from huggingface_hub import hf_hub_download

YOUR_MODEL_DIRECTORY = None
CONTEXT LENGHT = None
MAX TOKENS = None
BATCH SIZE = None
TEMPERATURE = None
GPU_OFFLOAD = None

def load_model (model_id, model_basename):
  model_path = hf_hub_download (
    repo_id=model_id,
    filename=model_basename,
    resume_download=True,
    cache_dir="YOUR_MODEL_DIRECTORY",
  )
  kwargs = {
    'model_path': model_path,
    'n_ctx': CONTEXT_LENGHT,
    'max_tokens': MAX_TOKENS,
    'n_batch': BATCH_SIZE,
    'n_gpu_layers': GPU_OFFLOAD,
    'temperature': TEMPERATURE,
    'verbose': True,
  }
  return LlamaCpp(**kwargs)

11m = load_model(
model_id="whoami02/defog-sqlcoder-2-GGUF",
model_basename="sqlcoder-7b-2.q8_0.gguf",

Downloads last month: 35

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

8-bit