Text Generation
GGUF
English
large-language-model
quantization
cpu-inference
local-inference
conversational
Instructions to use maroofiums/Edge4-SQL-Q4_K_M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use maroofiums/Edge4-SQL-Q4_K_M with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf maroofiums/Edge4-SQL-Q4_K_M:Q4_K_M # Run inference directly in the terminal: llama cli -hf maroofiums/Edge4-SQL-Q4_K_M:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf maroofiums/Edge4-SQL-Q4_K_M:Q4_K_M # Run inference directly in the terminal: llama cli -hf maroofiums/Edge4-SQL-Q4_K_M:Q4_K_M
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf maroofiums/Edge4-SQL-Q4_K_M:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama cli -hf maroofiums/Edge4-SQL-Q4_K_M:Q4_K_M
Use Docker
docker model run hf.co/maroofiums/Edge4-SQL-Q4_K_M:Q4_K_M
- Llama new
- LM Studio
- Jan
- vLLM
How to use maroofiums/Edge4-SQL-Q4_K_M with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "maroofiums/Edge4-SQL-Q4_K_M" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "maroofiums/Edge4-SQL-Q4_K_M", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/maroofiums/Edge4-SQL-Q4_K_M:Q4_K_M
- Ollama
How to use maroofiums/Edge4-SQL-Q4_K_M with Ollama:
ollama run hf.co/maroofiums/Edge4-SQL-Q4_K_M:Q4_K_M
- Unsloth Desktop
- Pi
How to use maroofiums/Edge4-SQL-Q4_K_M with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf maroofiums/Edge4-SQL-Q4_K_M:Q4_K_M
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:9931/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "maroofiums/Edge4-SQL-Q4_K_M:Q4_K_M" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Docker Model Runner
How to use maroofiums/Edge4-SQL-Q4_K_M with Docker Model Runner:
docker model run hf.co/maroofiums/Edge4-SQL-Q4_K_M:Q4_K_M
- Lemonade
How to use maroofiums/Edge4-SQL-Q4_K_M with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull maroofiums/Edge4-SQL-Q4_K_M:Q4_K_M
Run and chat with the model
lemonade run user.Edge4-SQL-Q4_K_M-Q4_K_M
List all available models
lemonade list
- Hermes Agent
How to use maroofiums/Edge4-SQL-Q4_K_M with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf maroofiums/Edge4-SQL-Q4_K_M:Q4_K_M
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:9931/v1 hermes config set model.default maroofiums/Edge4-SQL-Q4_K_M:Q4_K_M
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use maroofiums/Edge4-SQL-Q4_K_M with OpenClaw:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama serve -hf maroofiums/Edge4-SQL-Q4_K_M:Q4_K_M
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:9931/v1 \ --custom-model-id "maroofiums/Edge4-SQL-Q4_K_M:Q4_K_M" \ --custom-provider-id llama-cpp \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,88 @@
|
|
| 1 |
---
|
| 2 |
license: mit
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: mit
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
tags:
|
| 6 |
+
- gguf
|
| 7 |
+
- large-language-model
|
| 8 |
+
- text-generation
|
| 9 |
+
- quantization
|
| 10 |
+
- cpu-inference
|
| 11 |
+
- local-inference
|
| 12 |
+
pipeline_tag: text-generation
|
| 13 |
+
base_model:
|
| 14 |
+
- microsoft/Phi-4-mini-instruct
|
| 15 |
---
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
# Edge4-SQL-Q4_K_M
|
| 19 |
+
|
| 20 |
+
A quantized GGUF language model for local inference and experimentation with efficient language-model deployment.
|
| 21 |
+
|
| 22 |
+
## Overview
|
| 23 |
+
|
| 24 |
+
This repository contains GGUF-format model files designed for use with compatible local inference engines. The project focuses on exploring quantized model deployment in resource-constrained environments, including systems without dedicated GPUs.
|
| 25 |
+
|
| 26 |
+
## Model Files
|
| 27 |
+
|
| 28 |
+
| File | Description |
|
| 29 |
+
|---|---|
|
| 30 |
+
| `Edge4-SQL-Q4_K_M.gguf` | GGUF model file |
|
| 31 |
+
|
| 32 |
+
Both files are approximately 2.49 GB.
|
| 33 |
+
|
| 34 |
+
## Key Features
|
| 35 |
+
|
| 36 |
+
- **GGUF format:** Compatible with supported GGUF inference runtimes.
|
| 37 |
+
- **Quantized weights:** Uses the Q4_K_M naming convention, commonly associated with 4-bit K-quantization.
|
| 38 |
+
- **Local inference:** Intended for experimentation with locally hosted language models.
|
| 39 |
+
- **CPU-oriented workflows:** Suitable for evaluating inference on systems with limited computational resources.
|
| 40 |
+
- **Flexible integration:** Can be incorporated into Python applications and other compatible software.
|
| 41 |
+
|
| 42 |
+
## Getting Started
|
| 43 |
+
|
| 44 |
+
Install a compatible inference runtime, such as [`llama.cpp`](https://github.com/ggml-org/llama.cpp).
|
| 45 |
+
|
| 46 |
+
Example command:
|
| 47 |
+
|
| 48 |
+
```bash
|
| 49 |
+
llama-cli \
|
| 50 |
+
-m ./Edge4-SQL-CPU-Q4_K_M.gguf \
|
| 51 |
+
-p "Explain the concept of relational databases." \
|
| 52 |
+
-n 256
|
| 53 |
+
```
|
| 54 |
+
|
| 55 |
+
Adjust the model path, prompt, and generation parameters according to your environment.
|
| 56 |
+
|
| 57 |
+
## Use Cases
|
| 58 |
+
|
| 59 |
+
Potential applications include:
|
| 60 |
+
|
| 61 |
+
- Local language-model experimentation.
|
| 62 |
+
- Natural-language processing applications.
|
| 63 |
+
- Structured-data and SQL-generation experiments.
|
| 64 |
+
- Prototyping AI-powered applications.
|
| 65 |
+
- Research into model quantization and efficient inference.
|
| 66 |
+
|
| 67 |
+
Actual suitability depends on the underlying model, its training, and the intended task.
|
| 68 |
+
|
| 69 |
+
## Performance and Compatibility
|
| 70 |
+
|
| 71 |
+
Performance depends on the inference runtime, CPU architecture, available RAM, context length, and runtime configuration.
|
| 72 |
+
|
| 73 |
+
The Q4_K_M designation describes a quantization format; it does not guarantee a specific inference speed, accuracy level, or memory requirement.
|
| 74 |
+
|
| 75 |
+
## Limitations
|
| 76 |
+
|
| 77 |
+
- Generated outputs may contain errors or inaccurate information.
|
| 78 |
+
- Performance and output quality should be evaluated for the intended application.
|
| 79 |
+
- Compatibility depends on the underlying architecture and supported inference runtime.
|
| 80 |
+
- No benchmark results or accuracy claims are provided here.
|
| 81 |
+
|
| 82 |
+
## License
|
| 83 |
+
|
| 84 |
+
The applicable license depends on the original base model and its redistribution terms. Verify the original model's license before redistributing or using this model commercially.
|
| 85 |
+
|
| 86 |
+
## Disclaimer
|
| 87 |
+
|
| 88 |
+
This repository is intended for experimentation, development, and evaluation. Test the model thoroughly before using it in production applications.
|