🍓 Ichigo: Local real-time voice AI (Formerly llama3-s).

Homebrewed early-fusion speech model

Note

Update: September 30, 2024

• We have rebranded from llama3-s to 🍓 Ichigo.
• Our custom-built early-fusion speech model now has a name and a voice.
• It has improved multiturn capabilities and can now refuse to process inaudible queries.

Warning

🍓 Ichigo is an open research experiment

• Join us in the #research channel in Homebrew's Discord
• We livestream training runs in #research-livestream

About

🍓 Ichigo is an open, ongoing research experiment to extend a text-based LLM to have native "listening" ability. Think of it as an open data, open weight, on device Siri.

It uses an early fusion technique inspired by Meta's Chameleon paper.

We build train in public:

• Ichigo v0.3 Checkpoint Writeup
• Ichigo v0.2 Checkpoint Writeup
• Ichigo v0.1 Checkpoint Writeup

Progress

• 22 Oct: 📑 Research Paper Release: We are pleased to announce the publication of our research paper detailing the development and technical innovations behind Ichigo series. The full technical details, methodology, and experimental results are now available in our paper.
• 4 Oct: Ichigo v0.3 models are now available. Utilizing cleaner and improved data, our model has achieved an enhanced MMLU score of 63.79 and demonstrates stronger speech instruction-following capabilities, even in multi-turn interactions. Additionally, by incorporating noise-synthetic data, we have successfully trained the model to refuse processing non-speech audio inputs from users, further improving its functionality and user experience.
• 23 Aug: We’re excited to share Ichigo-llama3.1-s-instruct-v0.2, our latest multimodal checkpoint with improved speech understanding by enhancing the model's audio instruction-following capabilities through training on interleaving synthetic data.
• 17 Aug: We pre-trained our LLaMA 3.1 model on continuous speech data, tokenized using WhisperSpeechVQ. The final loss converged to approximately 1.9, resulting in our checkpoint: Ichigo-llama3.1-s-base-v0.2
• 1 Aug: Identified typo in original training recipe, causing significant degradation (MMLU: 0.6 -> 0.2), proposed fixes.
• 30 July: Presented llama3-s progress at: AI Training: From PyTorch to GPU Clusters
• 19 July: llama3-s-2024-07-19 understands synthetic voice with limited results
• 1 July: llama3-s-2024-07-08 showed converging loss (1.7) with limited data

Join Us

🍓 Ichigo is an open research project. We're looking for collaborators, and will likely move towards crowdsourcing speech datasets in the future.

Quickstart with Google Colab

Checkout this notebook to try our latest model:

Synthetic Generation

For detailed information on synthetic generation, please refer to the Synthetic Generation Guide.

Organize the input/output directory

1. First Clone the Repo from github:

git clone --recurse-submodules https://github.com/homebrewltd/llama3-s.git

2. The folder structure is as follows:

Ichigo
├── HF_Trainer                               # HF training code (deprecated)
├── synthetic_data                           # Synthetic data generation pipeline
    ├── configs                              # Audio pipeline configs
        ├── audio_to_audio                   # Parler audio (.wav) to semantic tokens
        ├── synthetic_generation_config      # TTS semantic tokens
├── scripts                                  # Setup scripts for Runpod
├── torchtune                                # Submodule: our fork of fsdp with checkpointing
├── model_zoo                                # Model checkpoints
│   ├── LLM
│   │   ├── Meta-Llama-3-8B-Instruct
│   │   ├── Meta-Llama-3-70B-Instruct
├── demo                                     # Selfhost this demo (vllm)
├── inference                                # Google Colab

Training with HF Trainer

1. Install Dependencies

python -m venv hf_trainer
chmod +x scripts/install.sh
./scripts/install.sh

Restart shell now

chmod +x scripts/setup.sh
./scripts/setup.sh
source myenv/bin/activate

2. Logging Huggingface

huggingface-cli login --token=<token>

3. Training

export CUTLASS_PATH="cutlass"
export CUDA_VISIBLE_DEVICES=0,1,2,3,4,5,6,7
accelerate launch --config_file ./accelerate_config.yaml train.py 

Training with Torchtune

1. Install Package

python -m venv torchtune
pip install torch torchvision tensorboard
cd ./torchtune
pip install -e .

You can also download the model using tune:

tune download homebrewltd/llama3.1-s-whispervq-init --hf-token <token>  --output-dir ../model_zoo/llama3.1-s-whispervq-init --ignore-patterns "original/consolidated*"

Setup the Dataset from HF path by change the path and change the name of the model in the following YAML file.

nano torchtune/recipes/configs/jan-llama3-s/8B_full.yaml

2. Training Multi GPU (1-8GPUs Supported)

tune run --nproc_per_node 4 full_finetune_fsdp2 --config recipes/configs/jan-llama3-1-s/8B_full.yaml

Demo

WebUI

For instructions on how to self-host the Ichigo web UI demo using Docker, please visit: Ichigo demo. To try our demo on a single RTX 4090 GPU, you can go directly to: https://ichigo.homebrew.ltd.

Gradio Web UI

We offer code for users to create a web UI demo. Please follow the instructions below:

python -m venv demo
source demo/bin/activate
# First install all required packages
pip install --no-cache-dir -r ./demo/requirements.txt

Then run the command below to launch a Gradio demo locally. You can add the variables use-4bit and use-8bit for quantized usage:

python -m demo.app --host 0.0.0.0 --port 7860 --max-seq-len 1024 

You can also host a demo using vLLM for faster inference but its not support streaming output:

python -m demo.app_vllm

Alternatively, you can easily try our demo on HuggingFace 🤗

References

@misc{chameleonteam2024chameleonmixedmodalearlyfusionfoundation,
      title={Chameleon: Mixed-Modal Early-Fusion Foundation Models}, 
      author={Chameleon Team},
      year={2024},
      eprint={2405.09818},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      journal={arXiv preprint}
}

@misc{zhang2024adamminiusefewerlearning,
      title={Adam-mini: Use Fewer Learning Rates To Gain More}, 
      author={Yushun Zhang and Congliang Chen and Ziniu Li and Tian Ding and Chenwei Wu and Yinyu Ye and Zhi-Quan Luo and Ruoyu Sun},
      year={2024},
      eprint={2406.16793},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      journal={arXiv preprint}
}

@misc{defossez2022highfi,
      title={High Fidelity Neural Audio Compression},
      author={Défossez, Alexandre and Copet, Jade and Synnaeve, Gabriel and Adi, Yossi},
      year={2022},
      eprint={2210.13438},
      archivePrefix={arXiv},
      journal={arXiv preprint}
}

@misc{WhisperSpeech,
      title={WhisperSpeech: An Open Source Text-to-Speech System Built by Inverting Whisper}, 
      author={Collabora and LAION},
      year={2024},
      url={https://github.com/collabora/WhisperSpeech},
      note={GitHub repository}
}

Acknowledgement

• Torchtune: The codebase we built upon
• Accelerate: Library for easy use of distributed training
• WhisperSpeech: Text-to-speech model for synthetic audio generation
• Encodec: High-fidelity neural audio codec for efficient audio compression
• Llama3: the Family of Models that we based on that has the amazing language capabilities !!!