Instructions to use grendo55/qwen2.5-0.5b-diary255-sql with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grendo55/qwen2.5-0.5b-diary255-sql with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="grendo55/qwen2.5-0.5b-diary255-sql",
	filename="qwen2.5-0.5b-diary255-sql.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use grendo55/qwen2.5-0.5b-diary255-sql with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf grendo55/qwen2.5-0.5b-diary255-sql
# Run inference directly in the terminal:
llama-cli -hf grendo55/qwen2.5-0.5b-diary255-sql

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf grendo55/qwen2.5-0.5b-diary255-sql
# Run inference directly in the terminal:
llama-cli -hf grendo55/qwen2.5-0.5b-diary255-sql

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 grendo55/qwen2.5-0.5b-diary255-sql
# Run inference directly in the terminal:
./llama-cli -hf grendo55/qwen2.5-0.5b-diary255-sql

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 grendo55/qwen2.5-0.5b-diary255-sql
# Run inference directly in the terminal:
./build/bin/llama-cli -hf grendo55/qwen2.5-0.5b-diary255-sql

Use Docker

docker model run hf.co/grendo55/qwen2.5-0.5b-diary255-sql

LM Studio
Jan
Ollama
How to use grendo55/qwen2.5-0.5b-diary255-sql with Ollama:
```
ollama run hf.co/grendo55/qwen2.5-0.5b-diary255-sql
```

Unsloth Studio

How to use grendo55/qwen2.5-0.5b-diary255-sql 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 grendo55/qwen2.5-0.5b-diary255-sql 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 grendo55/qwen2.5-0.5b-diary255-sql to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for grendo55/qwen2.5-0.5b-diary255-sql to start chatting

How to use grendo55/qwen2.5-0.5b-diary255-sql with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf grendo55/qwen2.5-0.5b-diary255-sql

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "grendo55/qwen2.5-0.5b-diary255-sql"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use grendo55/qwen2.5-0.5b-diary255-sql with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf grendo55/qwen2.5-0.5b-diary255-sql

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://127.0.0.1:8080/v1
hermes config set model.default grendo55/qwen2.5-0.5b-diary255-sql

Run Hermes

hermes

Docker Model Runner
How to use grendo55/qwen2.5-0.5b-diary255-sql with Docker Model Runner:
```
docker model run hf.co/grendo55/qwen2.5-0.5b-diary255-sql
```

Lemonade

How to use grendo55/qwen2.5-0.5b-diary255-sql with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull grendo55/qwen2.5-0.5b-diary255-sql

Run and chat with the model

lemonade run user.qwen2.5-0.5b-diary255-sql-{{QUANT_TAG}}

List all available models

lemonade list

Qwen 2.5 0.5B Diary255 Text-to-SQL (GGUF)

This is a specialized, quantized GGUF model fine-tuned on Qwen2.5-0.5B-Instruct to generate safe, read-only SQLite SELECT queries for the Diary255 personal timeline application.

Model Details

Base Model: Qwen/Qwen2.5-0.5B-Instruct
Format: GGUF (q8_0 quantization)
Parameters: 0.5 Billion
Context Window: 1024 tokens

Specialized Capabilities

The model was fine-tuned procedurally on the Diary255 database schema. It strictly follows these operational rules:

Strict Read-Only: Only generates SELECT queries. It will never output INSERT, UPDATE, DELETE, or DDL commands.
Context Isolation: Automatically applies profile_id filters to protect and isolate user data context.
Dynamic Date Logic: Generates SQLite relative offset math (strftime('%s', 'now', ...)) instead of hardcoding static epoch dates.
Relational Joins: Seamlessly handles multi-table queries joining tools, diary entries, and transaction logs.

Recommended Inference Settings

When running inference (such as in llama.cpp or llamadart), we highly recommend applying a GBNF grammar constraint to guarantee syntax validity.