Instructions to use actionpace/spicyboros-13b-2.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use actionpace/spicyboros-13b-2.2 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 actionpace/spicyboros-13b-2.2:Q5_1
# Run inference directly in the terminal:
llama cli -hf actionpace/spicyboros-13b-2.2:Q5_1

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf actionpace/spicyboros-13b-2.2:Q5_1
# Run inference directly in the terminal:
llama cli -hf actionpace/spicyboros-13b-2.2:Q5_1

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 actionpace/spicyboros-13b-2.2:Q5_1
# Run inference directly in the terminal:
./llama-cli -hf actionpace/spicyboros-13b-2.2:Q5_1

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 actionpace/spicyboros-13b-2.2:Q5_1
# Run inference directly in the terminal:
./build/bin/llama-cli -hf actionpace/spicyboros-13b-2.2:Q5_1

Use Docker

docker model run hf.co/actionpace/spicyboros-13b-2.2:Q5_1

LM Studio
Jan
Ollama
How to use actionpace/spicyboros-13b-2.2 with Ollama:
```
ollama run hf.co/actionpace/spicyboros-13b-2.2:Q5_1
```

Unsloth Studio

How to use actionpace/spicyboros-13b-2.2 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 actionpace/spicyboros-13b-2.2 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 actionpace/spicyboros-13b-2.2 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for actionpace/spicyboros-13b-2.2 to start chatting

Docker Model Runner
How to use actionpace/spicyboros-13b-2.2 with Docker Model Runner:
```
docker model run hf.co/actionpace/spicyboros-13b-2.2:Q5_1
```

Lemonade

How to use actionpace/spicyboros-13b-2.2 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull actionpace/spicyboros-13b-2.2:Q5_1

Run and chat with the model

lemonade run user.spicyboros-13b-2.2-Q5_1

List all available models

lemonade list

Atomic Chat

Some of my own quants:

spicyboros-13b-2.2_Q5_1.gguf

Source: jondurbin

Source Model: spicyboros-13b-2.2

Source models for jondurbin/spicyboros-13b-2.2 (Finetune, jondurbin/airoboros-2.2)

meta-llama/Llama-2-13b-hf (Ref)

Downloads last month: 5

GGUF

Model size

13B params

Architecture

llama

Hardware compatibility

5-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support