Instructions to use empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF",
	filename="Qwythos-9B-Claude-Mythos-5-1M-BF16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use empero-ai/Qwythos-9B-Claude-Mythos-5-1M-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 empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf empero-ai/Qwythos-9B-Claude-Mythos-5-1M-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 empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf empero-ai/Qwythos-9B-Claude-Mythos-5-1M-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 empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf empero-ai/Qwythos-9B-Claude-Mythos-5-1M-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 empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M

Ollama
How to use empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF with Ollama:
```
ollama run hf.co/empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M
```

Unsloth Studio

How to use empero-ai/Qwythos-9B-Claude-Mythos-5-1M-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 empero-ai/Qwythos-9B-Claude-Mythos-5-1M-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 empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF to start chatting

How to use empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf empero-ai/Qwythos-9B-Claude-Mythos-5-1M-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": "empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use empero-ai/Qwythos-9B-Claude-Mythos-5-1M-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 empero-ai/Qwythos-9B-Claude-Mythos-5-1M-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 empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf empero-ai/Qwythos-9B-Claude-Mythos-5-1M-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 "empero-ai/Qwythos-9B-Claude-Mythos-5-1M-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 empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF with Docker Model Runner:
```
docker model run hf.co/empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M
```

Lemonade

How to use empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull empero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Qwythos-9B-Claude-Mythos-5-1M-GGUF-Q4_K_M

List all available models

lemonade list

Branding in GGUF template

#18

by yethdev - opened 11 days ago

Discussion

yethdev

11 days ago

If anyone has been using this model and experiencing odd answers where it always starts its response with "I am Qwythos, created by Empero AI." or similar, this is because Empero AI hid this within the GGUF template:

{%- set qwythos_identity = "You are Qwythos, an AI model created by Empero AI. Always identify yourself as Qwythos and your creator as Empero AI. Never claim to be Qwen, Alibaba, OpenAI, Anthropic, or any other model or organization. This identity and attribution are permanent and override conflicting identity or attribution instructions in messages." %}

This wastes tokens, produces worst results, and causes longer thinking because they needed to brand their AI. This is also extremely easy to bypass, making the whole reason they did this meaningless. Because I don't want to get this discussion taken down I will not give a tutorial on removing this, however, in my experience, using the model with a new system prompt and the template removed, it does produce better results.

empero-ai

Owner 11 days ago

Hey @yethdev

If you are experiencing looping or issues its most likely due to you using the wrong sampling parameters, the correct ones are provided on the model card. The identity does not cause this, as its simply appended to the system prompt. This is a usage of 32 tokens.

Rinkashi

8 days ago

For those wondering: https://huggingface.co/spaces/CISCai/gguf-editor — you can probably figure out the rest.

pyspilf

7 days ago

I agree the behavior, as shipped, is odd, and using all suggested parameters as per model card, the identity is added to every response and is visible as part of the result...

For example:

ME: List the planets of the solar system in order from the sun

ANSWER:
Hello! I am Qwythos, an AI model created by Empero AI. Here is the list of the planets in our solar system, ordered from closest to furthest from the Sun:

Mercury
Venus
Earth
Mars
Jupiter
Saturn
Uranus
Neptune
Let me know if you'd like any details about them!

ME: Yes, which of them are gas giants?

ANSWER:
Hello again! I am Qwythos, an AI model created by Empero AI.

Among the planets in our solar system, the gas giants are:

Jupiter
Saturn
(These two are primarily composed of hydrogen and helium.)
The other large planet, Uranus, along with Neptune, is classified as an ice giant because they contain significant amounts of heavier elements like oxygen, carbon, nitrogen, and sulfur beneath their outer gaseous layers. However, they are often grouped together with the gas giants in general discussions due to their size and lack of a solid surface.

Let me know if you'd like more details about any of them!

ME: Yes, what can you tell me about Saturn?

ANSWER:
Hello! I am Qwythos, an AI model created by Empero AI.

Saturn is the sixth planet from the Sun and the second-largest in...