Instructions to use Joe57005/Ramius3B-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Joe57005/Ramius3B-v1 with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Joe57005/Ramius3B-v1",
	filename="ramius_f16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Joe57005/Ramius3B-v1 with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Joe57005/Ramius3B-v1:F16
# Run inference directly in the terminal:
llama-cli -hf Joe57005/Ramius3B-v1:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Joe57005/Ramius3B-v1:F16
# Run inference directly in the terminal:
llama-cli -hf Joe57005/Ramius3B-v1:F16

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 Joe57005/Ramius3B-v1:F16
# Run inference directly in the terminal:
./llama-cli -hf Joe57005/Ramius3B-v1:F16

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 Joe57005/Ramius3B-v1:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Joe57005/Ramius3B-v1:F16

Use Docker

docker model run hf.co/Joe57005/Ramius3B-v1:F16

LM Studio
Jan

vLLM

How to use Joe57005/Ramius3B-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Joe57005/Ramius3B-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Joe57005/Ramius3B-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Joe57005/Ramius3B-v1:F16

Ollama
How to use Joe57005/Ramius3B-v1 with Ollama:
```
ollama run hf.co/Joe57005/Ramius3B-v1:F16
```

Unsloth Studio

How to use Joe57005/Ramius3B-v1 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 Joe57005/Ramius3B-v1 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 Joe57005/Ramius3B-v1 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Joe57005/Ramius3B-v1 to start chatting

How to use Joe57005/Ramius3B-v1 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Joe57005/Ramius3B-v1:F16

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": "Joe57005/Ramius3B-v1:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Joe57005/Ramius3B-v1 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Joe57005/Ramius3B-v1:F16

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 Joe57005/Ramius3B-v1:F16

Run Hermes

hermes

Docker Model Runner
How to use Joe57005/Ramius3B-v1 with Docker Model Runner:
```
docker model run hf.co/Joe57005/Ramius3B-v1:F16
```

Lemonade

How to use Joe57005/Ramius3B-v1 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Joe57005/Ramius3B-v1:F16

Run and chat with the model

lemonade run user.Ramius3B-v1-F16

List all available models

lemonade list

Ramius

This is Ramius, an uncensored function calling model.

Model Description

I needed an LLM for Home Assistant that is small and performant and I wanted one with some personality.
Qwen2.5-3B is small, fast and can call functions pretty well. But it's [REDACTED], and doesn't like to roleplay.
Arch-Function-3B is fantastic at calling functions, and absolutely nothing else.
Dolphin3.0-Qwen2.5-3b is great at roleplay and refuses to refuse anything. But it sucks at calling functions.

So I created Ramius with MergeKit to try and get the best of both.
Plus I'm GPU poor and can't train. (Intel ARC cards come with buyer's remorse at no extra charge!)

The result is... mediocre. It correctly calls functions most of the time, but it tends to hallucinate function responses instead of calling the actual function.
But it does stay in character. YMMV.

The name comes from Marko Ramius, a fictional communist submarine commander who defects to the United States in Tom Clancy's The Hunt for Red October.
He's a former communist and the name sounded cool.

I've included the F16 and Q4_0 weights.

Developed by: Other people's hard work.
Funded by [optional]: Also other people's hard work.
Shared by [optional]: Me.
Model type: Autoregressive transformer.
Language(s) (NLP): English, and others, probably.
License: [More Information Needed]

Model Sources [optional]

Created with MergeKit.

models:
  - model: katanemo/Arch-Function-3B
    lambda: 1.0
    select_topk: 0.4
    weight: 0.7
  - model: cognitivecomputations/Dolphin3.0-Qwen2.5-3b
    density: 1.0
    lambda: 1.0
    select_topk: 0.6
    weight: 0.3
merge_method: sce
base_model: katanemo/Arch-Function-3B
parameters:
  int8_mask: true
  normalize: true
dtype: bfloat16

Bias, Risks, and Limitations

This is uncensored and does hallucinate. frequently.

[More Information Needed]

Recommendations

I use this with Ollama and Home Assistant via the Extended OpenAI conversation integration. Works best with a top P of around 0.95 and temperature around 0.85.

I also recommend you DO NOT put your entity states in your system prompt, and instead write functions to get the information. This will keep your system prompt static and more easily cached, which should reduce prompt processing time.

Downloads last month: 15

GGUF

Model size

3B params

Architecture

qwen2

Hardware compatibility

4-bit

16-bit

Model tree for Joe57005/Ramius3B-v1

Base model

Qwen/Qwen2.5-3B

Finetuned

dphn/Dolphin3.0-Qwen2.5-3b

Quantized

(29)

this model