Instructions to use GarethEvs/orpheus-cy-quantised with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use GarethEvs/orpheus-cy-quantised with Transformers:

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

pipe = pipeline("text-to-speech", model="GarethEvs/orpheus-cy-quantised")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("GarethEvs/orpheus-cy-quantised", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use GarethEvs/orpheus-cy-quantised 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 GarethEvs/orpheus-cy-quantised:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf GarethEvs/orpheus-cy-quantised:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf GarethEvs/orpheus-cy-quantised:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf GarethEvs/orpheus-cy-quantised: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 GarethEvs/orpheus-cy-quantised:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf GarethEvs/orpheus-cy-quantised: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 GarethEvs/orpheus-cy-quantised:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf GarethEvs/orpheus-cy-quantised:Q4_K_M

Use Docker

docker model run hf.co/GarethEvs/orpheus-cy-quantised:Q4_K_M

LM Studio
Jan
Ollama
How to use GarethEvs/orpheus-cy-quantised with Ollama:
```
ollama run hf.co/GarethEvs/orpheus-cy-quantised:Q4_K_M
```

Unsloth Studio

How to use GarethEvs/orpheus-cy-quantised 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 GarethEvs/orpheus-cy-quantised 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 GarethEvs/orpheus-cy-quantised to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for GarethEvs/orpheus-cy-quantised to start chatting

How to use GarethEvs/orpheus-cy-quantised with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GarethEvs/orpheus-cy-quantised: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": "GarethEvs/orpheus-cy-quantised:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use GarethEvs/orpheus-cy-quantised with Docker Model Runner:
```
docker model run hf.co/GarethEvs/orpheus-cy-quantised:Q4_K_M
```

Lemonade

How to use GarethEvs/orpheus-cy-quantised with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull GarethEvs/orpheus-cy-quantised:Q4_K_M

Run and chat with the model

lemonade run user.orpheus-cy-quantised-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use GarethEvs/orpheus-cy-quantised with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GarethEvs/orpheus-cy-quantised: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 GarethEvs/orpheus-cy-quantised:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use GarethEvs/orpheus-cy-quantised with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GarethEvs/orpheus-cy-quantised: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 "GarethEvs/orpheus-cy-quantised: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"

orpheus-cy-quantised / README.md

GarethEvs

Update README.md

20ba5de verified 4 days ago

preview code

Raw

History Blame Contribute Delete

1.04 kB

	---
	base_model:
	- unsloth/orpheus-3b-0.1-pretrained
	language:
	- cy
	library_name: transformers
	tags:
	- text-to-speech
	- orpheus
	- welsh
	- quantized
	datasets:
	- sarulab-speech/commonvoice22_sidon
	- techiaith/corpws-clllc-wlga
	- techiaith/banc-trawsgrifiadau-bangor
	- cymen-arfor/lleisiau-arfor
	- techiaith/bu-tts-cy-en
	---

	# Orpheus-cy — quantised variants

	Quantised builds of [`unsloth/orpheus-3b-0.1-pretrained`](https://huggingface.co/unsloth/orpheus-3b-0.1-pretrained)

	## Files
	- `bnb-8bit/`, `bnb-4bit/` — bitsandbytes, load with transformers:
	`AutoModelForCausalLM.from_pretrained("GarethEvs/orpheus-cy-quantised", subfolder="bnb-4bit", device_map="cuda")`
	- `orpheus-cy-*.gguf` — llama.cpp / orpheus-cpp.

	Quantisations yn gwython dda. Q4 yn perfformio'n dda, bach yn robotic ond well na ONIX models

	Optionau lleisau:
	1. Aled - Llawer o training data
	2. Leila - Llawer o training data
	3. Myfanwy - Llawer o training data
	4. Guto
	5. Tomos
	6. Dafydd
	7. Gwennan

	Dataset techiaith/bu-tts-cy-en yw le maer lleisiau di dod o.