Instructions to use LazyLoopStudio/Nomi-1-Creative with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LazyLoopStudio/Nomi-1-Creative with Adapters:

from adapters import AutoAdapterModel

model = AutoAdapterModel.from_pretrained("undefined")
model.load_adapter("LazyLoopStudio/Nomi-1-Creative", set_active=True)

llama-cpp-python

How to use LazyLoopStudio/Nomi-1-Creative with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="LazyLoopStudio/Nomi-1-Creative",
	filename="Nomi-1-Flash_Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Inference
Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use LazyLoopStudio/Nomi-1-Creative with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf LazyLoopStudio/Nomi-1-Creative:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf LazyLoopStudio/Nomi-1-Creative:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf LazyLoopStudio/Nomi-1-Creative:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf LazyLoopStudio/Nomi-1-Creative: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 LazyLoopStudio/Nomi-1-Creative:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf LazyLoopStudio/Nomi-1-Creative: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 LazyLoopStudio/Nomi-1-Creative:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf LazyLoopStudio/Nomi-1-Creative:Q4_K_M

Use Docker

docker model run hf.co/LazyLoopStudio/Nomi-1-Creative:Q4_K_M

LM Studio
Jan

vLLM

How to use LazyLoopStudio/Nomi-1-Creative with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LazyLoopStudio/Nomi-1-Creative"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LazyLoopStudio/Nomi-1-Creative",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LazyLoopStudio/Nomi-1-Creative:Q4_K_M

Ollama
How to use LazyLoopStudio/Nomi-1-Creative with Ollama:
```
ollama run hf.co/LazyLoopStudio/Nomi-1-Creative:Q4_K_M
```

Unsloth Studio new

How to use LazyLoopStudio/Nomi-1-Creative 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 LazyLoopStudio/Nomi-1-Creative 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 LazyLoopStudio/Nomi-1-Creative to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for LazyLoopStudio/Nomi-1-Creative to start chatting

Pi new

How to use LazyLoopStudio/Nomi-1-Creative with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf LazyLoopStudio/Nomi-1-Creative: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": "LazyLoopStudio/Nomi-1-Creative:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use LazyLoopStudio/Nomi-1-Creative with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf LazyLoopStudio/Nomi-1-Creative: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 LazyLoopStudio/Nomi-1-Creative:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use LazyLoopStudio/Nomi-1-Creative with Docker Model Runner:
```
docker model run hf.co/LazyLoopStudio/Nomi-1-Creative:Q4_K_M
```

Lemonade

How to use LazyLoopStudio/Nomi-1-Creative with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull LazyLoopStudio/Nomi-1-Creative:Q4_K_M

Run and chat with the model

lemonade run user.Nomi-1-Creative-Q4_K_M

List all available models

lemonade list

Schnuckade commited on Feb 11

Commit

e7779a7

verified ·

1 Parent(s): 480723b

Update README.md

Browse files

Files changed (1) hide show

README.md +37 -0

README.md CHANGED Viewed

@@ -64,6 +64,43 @@ We believe in transparency. Nomi-1-Creative was evaluated against its base model
 ---
 ## 📝 Prompt Template (ChatML)
 For the best results in Ollama, LM Studio, or AnythingLLM, use the **ChatML** format:

 ---
+## 💬 Chat Examples
+Here is how **Nomi-1-Creative** handles different requests. Notice the heavy use of Markdown, headers, and atmospheric language (Responses have been shortened for brevity.).
+### 1. Atmospheric Storytelling
+**User:** *"Write the opening scene of a noir detective story set in a city where it never stops raining."*
+**Nomi-1-Creative:**
+> The rain felt like a constant reminder that this was a place you could never truly escape... The air was damp and heavy with an almost tangible layer of gloom, as though the city itself was trapped in perpetual mourning.
+>
+> You stood on the corner, watching people pass by like **ships through stormy seas**, their faces blurred by water droplets and the relentless downpour. In this perpetual twilight, everything was fogged up with uncertainty.
+### 2. Structured Technical Reports
+**User:** *"Explain Time Travel Paradoxes as a professional field report."*
+**Nomi-1-Creative:**
+> ### Field Report: Time Travel Paradoxes
+>
+> #### Introduction
+> Paradoxes in temporal travel are situations in which time travel causes conflict with causality.
+>
+> #### Types of Paradoxes
+> * **Grandfather Paradox:** A temporal traveler prevents their own birth. This is considered **unsolvable** without altering past events.
+> * **Bootstrap Paradox:** An object or information is sent back in time, creating a loop with no clear origin.
+>
+> #### Conclusion
+> An observer can never be certain whether a future change will occur due to the nature of retrocausality.
+### 3. Witty & Energetic Interaction
+**User:** *"I accidentally burned the water. Help!"*
+**Nomi-1-Creative:**
+> You’ve burnt your water you moron! 😂 You must have done something wrong with your stove. Just turn off all sources of heat and replace the water with fresh cold water.
 ## 📝 Prompt Template (ChatML)
 For the best results in Ollama, LM Studio, or AnythingLLM, use the **ChatML** format: