Instructions to use onblueroses/phila-ft-v2-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use onblueroses/phila-ft-v2-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="onblueroses/phila-ft-v2-GGUF",
	filename="phila-ft-v2.Q4_K_M.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 onblueroses/phila-ft-v2-GGUF 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 onblueroses/phila-ft-v2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf onblueroses/phila-ft-v2-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf onblueroses/phila-ft-v2-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf onblueroses/phila-ft-v2-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 onblueroses/phila-ft-v2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf onblueroses/phila-ft-v2-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 onblueroses/phila-ft-v2-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf onblueroses/phila-ft-v2-GGUF:Q4_K_M

Use Docker

docker model run hf.co/onblueroses/phila-ft-v2-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use onblueroses/phila-ft-v2-GGUF with Ollama:
```
ollama run hf.co/onblueroses/phila-ft-v2-GGUF:Q4_K_M
```

Unsloth Studio

How to use onblueroses/phila-ft-v2-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 onblueroses/phila-ft-v2-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 onblueroses/phila-ft-v2-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for onblueroses/phila-ft-v2-GGUF to start chatting

How to use onblueroses/phila-ft-v2-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf onblueroses/phila-ft-v2-GGUF:Q4_K_M

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": "onblueroses/phila-ft-v2-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use onblueroses/phila-ft-v2-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf onblueroses/phila-ft-v2-GGUF: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://127.0.0.1:8080/v1
hermes config set model.default onblueroses/phila-ft-v2-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use onblueroses/phila-ft-v2-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf onblueroses/phila-ft-v2-GGUF: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://127.0.0.1:8080/v1 \
  --custom-model-id "onblueroses/phila-ft-v2-GGUF: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"

Docker Model Runner
How to use onblueroses/phila-ft-v2-GGUF with Docker Model Runner:
```
docker model run hf.co/onblueroses/phila-ft-v2-GGUF:Q4_K_M
```

Lemonade

How to use onblueroses/phila-ft-v2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull onblueroses/phila-ft-v2-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.phila-ft-v2-GGUF-Q4_K_M

List all available models

lemonade list

phila-ft-v2

QLoRA fine-tune of Llama 3.2 3B Instruct for the phila speak gate - a silence-first iMessage group chat agent.

What this model does

Binary classification: given a batch of group chat messages, decide SPEAK or SILENT. The model is tuned to default to silence and only speak for factual corrections, unanswered questions, or direct address.

Training

Base model: unsloth/Llama-3.2-3B-Instruct
Method: QLoRA, r=16, alpha=16, dropout=0
Training data: 1,138 examples across 4 targeted categories (755 base + 150 speak-unanswered + 153 silent-sarcasm + 80 near-miss)
Hardware: Vast.ai RTX 4090, 429 steps, ~40 minutes
Quantization: Q4_K_M GGUF

Results

Metric	llama3.2 (base)	phila-ft-v2
Gate accuracy (holdout, 43 scenarios)	87.9%	93.0%
Gate accuracy (all 101 scenarios)	94.1%	95.8%
Response quality	0.951	0.965
Composite score	0.8487	0.8638
Avg latency	515ms	544ms

The fine-tune specifically fixed the "buried thread" failure category (question asked, topic changes, nobody answers) which was a 0% pass rate across all prompt engineering attempts on 4 base models.

Usage with Ollama

# download the GGUF
# then create with the included Modelfile:
ollama create phila-ft-v2 -f Modelfile

# or manually:
ollama create phila-ft-v2 -f - <<EOF
FROM ./phila-ft-v2.Q4_K_M.gguf
TEMPLATE \"\"\"{{- if .System }}<|start_header_id|>system<|end_header_id|>

{{ .System }}<|eot_id|>{{ end }}{{- range .Messages }}<|start_header_id|>{{ .Role }}<|end_header_id|>

{{ .Content }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>

\"\"\"
PARAMETER stop "<|start_header_id|>"
PARAMETER stop "<|end_header_id|>"
PARAMETER stop "<|eot_id|>"
PARAMETER temperature 0.1
PARAMETER top_p 0.52
PARAMETER num_predict 64
EOF