Any-to-Any
Transformers
Safetensors
GGUF
qwen2_5_omni
multimodal
voice-assistant
vibe-coach
note-taker
conversational
background-music
music-generation
darwin-family
evolutionary-merging
weight-space-recombination
arxiv-2605.14386
southpawin
senter
gpt-4o
Instructions to use sovthpaw/omnistep-12a3b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sovthpaw/omnistep-12a3b with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("sovthpaw/omnistep-12a3b") model = AutoModel.from_pretrained("sovthpaw/omnistep-12a3b") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - llama-cpp-python
How to use sovthpaw/omnistep-12a3b with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="sovthpaw/omnistep-12a3b", filename="omnistep-12a3b-f16.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use sovthpaw/omnistep-12a3b with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf sovthpaw/omnistep-12a3b:Q4_K_M # Run inference directly in the terminal: llama-cli -hf sovthpaw/omnistep-12a3b:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf sovthpaw/omnistep-12a3b:Q4_K_M # Run inference directly in the terminal: llama-cli -hf sovthpaw/omnistep-12a3b: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 sovthpaw/omnistep-12a3b:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf sovthpaw/omnistep-12a3b: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 sovthpaw/omnistep-12a3b:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf sovthpaw/omnistep-12a3b:Q4_K_M
Use Docker
docker model run hf.co/sovthpaw/omnistep-12a3b:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use sovthpaw/omnistep-12a3b with Ollama:
ollama run hf.co/sovthpaw/omnistep-12a3b:Q4_K_M
- Unsloth Studio
How to use sovthpaw/omnistep-12a3b 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 sovthpaw/omnistep-12a3b 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 sovthpaw/omnistep-12a3b to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for sovthpaw/omnistep-12a3b to start chatting
- Atomic Chat new
- Docker Model Runner
How to use sovthpaw/omnistep-12a3b with Docker Model Runner:
docker model run hf.co/sovthpaw/omnistep-12a3b:Q4_K_M
- Lemonade
How to use sovthpaw/omnistep-12a3b with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull sovthpaw/omnistep-12a3b:Q4_K_M
Run and chat with the model
lemonade run user.omnistep-12a3b-Q4_K_M
List all available models
lemonade list
Upload scripts/omnistep-jammit with huggingface_hub
Browse files- scripts/omnistep-jammit +70 -0
scripts/omnistep-jammit
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/bin/bash
|
| 2 |
+
# omnistep-jammit — bash wrapper for ACE-Step music generation
|
| 3 |
+
# (the legacy `jammit` script at ~/bin/jammit, updated for OmniStep 12A3B)
|
| 4 |
+
#
|
| 5 |
+
# Usage:
|
| 6 |
+
# omnistep-jammit "your prompt" [options]
|
| 7 |
+
#
|
| 8 |
+
# Options:
|
| 9 |
+
# --duration_seconds SECONDS Duration in seconds (default: 60)
|
| 10 |
+
# --infer_steps STEPS Inference steps (default: 8 turbo)
|
| 11 |
+
# --guidance_scale SCALE Guidance scale (default: 7.0)
|
| 12 |
+
# --infinite false|true Infinite loop mode (default: false)
|
| 13 |
+
# --lyrics TEXT Lyrics (default: none, instrumental)
|
| 14 |
+
# --instrumental Force instrumental
|
| 15 |
+
# --help, -h Show this help
|
| 16 |
+
|
| 17 |
+
set -e
|
| 18 |
+
|
| 19 |
+
OMNISTEP_DIR="$(cd "$(dirname "$0")/.." && pwd)"
|
| 20 |
+
SCRIPTS_DIR="$OMNISTEP_DIR/scripts"
|
| 21 |
+
|
| 22 |
+
if [ ! -f "$SCRIPTS_DIR/run_omnistep_6a3b.py" ]; then
|
| 23 |
+
echo "❌ Error: run_omnistep_6a3b.py not found at $SCRIPTS_DIR"
|
| 24 |
+
echo " Make sure you're running this from the OmniStep 12A3B repo."
|
| 25 |
+
exit 1
|
| 26 |
+
fi
|
| 27 |
+
|
| 28 |
+
if [ "$1" = "--help" ] || [ "$1" = "-h" ] || -z "$1" ]; then
|
| 29 |
+
cat <<EOF
|
| 30 |
+
🎵 omnistep-jammit — OmniStep 12A3B ACE-Step music generation
|
| 31 |
+
(OmniStep 12A3B = Qwen2.5-Omni-3B + ACE-Step v1.5 XL 4B, Darwin-merged)
|
| 32 |
+
|
| 33 |
+
Usage:
|
| 34 |
+
omnistep-jammit "your prompt" [options]
|
| 35 |
+
|
| 36 |
+
Options:
|
| 37 |
+
--duration_seconds SECONDS Duration in seconds (default: 60)
|
| 38 |
+
--infer_steps STEPS Inference steps (default: 8 turbo)
|
| 39 |
+
--guidance_scale SCALE Guidance scale (default: 7.0)
|
| 40 |
+
--infinite Infinite background music loop (Evolutionary Radio)
|
| 41 |
+
--lyrics TEXT Add lyrics
|
| 42 |
+
--instrumental Force instrumental
|
| 43 |
+
--help, -h This help
|
| 44 |
+
|
| 45 |
+
Examples:
|
| 46 |
+
omnistep-jammit "chill lofi beats for late-night coding" --duration 120
|
| 47 |
+
omnistep-jammit "aggressive metal, 808s" --infer_steps 20
|
| 48 |
+
omnistep-jammit "warm ambient pad" --infinite # infinite background music
|
| 49 |
+
|
| 50 |
+
The diffusion (music) part runs at F16 (unquantized) for max quality.
|
| 51 |
+
The transformer (text/multimodal) part can be quantized via the 4 GGUF
|
| 52 |
+
quantizations (F16, Q8_0, Q4_K_M, Q4_0) shipped in this repo.
|
| 53 |
+
EOF
|
| 54 |
+
exit 0
|
| 55 |
+
fi
|
| 56 |
+
|
| 57 |
+
# Detect --infinite mode → delegate to the radio script
|
| 58 |
+
if [[ " $* " == *" --infinite "* ]] || [[ "$1" == "--infinite" ]]; then
|
| 59 |
+
# Strip --infinite from args, delegate to omnistep_radio.py
|
| 60 |
+
args=()
|
| 61 |
+
for arg in "$@"; do
|
| 62 |
+
if [ "$arg" != "--infinite" ]; then
|
| 63 |
+
args+=("$arg")
|
| 64 |
+
fi
|
| 65 |
+
done
|
| 66 |
+
exec python3 "$SCRIPTS_DIR/omnistep_radio.py" "${args[@]}"
|
| 67 |
+
fi
|
| 68 |
+
|
| 69 |
+
# One-shot mode → delegate to run_omnistep_6a3b.py music
|
| 70 |
+
exec python3 "$SCRIPTS_DIR/run_omnistep_6a3b.py" music "$@"
|