Ichigo Llama3.1 S Instruct V0.4

🚀 Ichigo-llama3s Family Model

The Ichigo-llama3s family is a model that natively understands audio and text input, aiming to improve the sound understanding capabilities of LLMs.

🚀 Quick Start

Try this model using Google Colab Notebook.

First, convert the audio file to sound tokens:

device = "cuda" if torch.cuda.is_available() else "cpu"
if not os.path.exists("whisper-vq-stoks-medium-en+pl-fixed.model"):
    hf_hub_download(
        repo_id="jan-hq/WhisperVQ",
        filename="whisper-vq-stoks-medium-en+pl-fixed.model",
        local_dir=".",
    )
vq_model = RQBottleneckTransformer.load_model(
        "whisper-vq-stoks-medium-en+pl-fixed.model"
    ).to(device)
vq_model.ensure_whisper(device)
def audio_to_sound_tokens(audio_path, target_bandwidth=1.5, device=device):

    wav, sr = torchaudio.load(audio_path)
    if sr != 16000:
        wav = torchaudio.functional.resample(wav, sr, 16000)
    with torch.no_grad():
        codes = vq_model.encode_audio(wav.to(device))
        codes = codes[0].cpu().tolist()

    result = ''.join(f'<|sound_{num:04d}|>' for num in codes)
    return f'<|sound_start|>{result}<|sound_end|>'

Then, infer the model the same as any other LLM:

def setup_pipeline(model_path, use_4bit=False, use_8bit=False):
    tokenizer = AutoTokenizer.from_pretrained(model_path)

    model_kwargs = {"device_map": "auto"}

    if use_4bit:
        model_kwargs["quantization_config"] = BitsAndBytesConfig(
            load_in_4bit=True,
            bnb_4bit_compute_dtype=torch.bfloat16,
            bnb_4bit_use_double_quant=True,
            bnb_4bit_quant_type="nf4",
        )
    elif use_8bit:
        model_kwargs["quantization_config"] = BitsAndBytesConfig(
            load_in_8bit=True,
            bnb_8bit_compute_dtype=torch.bfloat16,
            bnb_8bit_use_double_quant=True,
        )
    else:
        model_kwargs["torch_dtype"] = torch.bfloat16

    model = AutoModelForCausalLM.from_pretrained(model_path, **model_kwargs)

    return pipeline("text-generation", model=model, tokenizer=tokenizer)

def generate_text(pipe, messages, max_new_tokens=64, temperature=0.0, do_sample=False):
    generation_args = {
        "max_new_tokens": max_new_tokens,
        "return_full_text": False,
        "temperature": temperature,
        "do_sample": do_sample,
    }

    output = pipe(messages, **generation_args)
    return output[0]['generated_text']

# Usage
llm_path = "homebrewltd/llama3.1-s-instruct-v0.2"
pipe = setup_pipeline(llm_path, use_8bit=True)

✨ Features

• The Ichigo-llama3s family natively understands audio and text input.
• The model is a supervised fine - tuned (SFT) version, trained on over 1 billion tokens, adding multi - turn speech conversations and noise rejection capabilities.
• It demonstrates improved robustness against noisy environmental inputs and enhanced multi - turn conversation capabilities.

📚 Documentation

Model Details

We have developed and released the family Ichigo-llama3s. This family is natively understanding audio and text input.

This model is a supervised fine - tuned (SFT) version of homebrewltd/Ichigo-llama3.1-s-base-v0.3, trained on over 1 billion tokens from the Instruction Speech WhisperVQ v4 dataset which built upon Instruction Speech WhisperVQ v3, adding multi - turn speech conversations and noise rejection capabilities for enhanced performance. As a result, the model demonstrates improved robustness against noisy environmental inputs and enhanced multi - turn conversation capabilities, making it more reliable in real - world applications.

Intended Use

Intended Use Cases This family is primarily intended for research applications. This version aims to further improve the LLM on sound understanding capabilities.

Out - of - scope The use of llama3 - s in any manner that violates applicable laws or regulations is strictly prohibited.

🔧 Technical Details

Training process

Training Metrics Image: Below is a snapshot of the training loss curve visualized.

MMLU:

AudioBench Eval:

Hardware

GPU Configuration: Cluster of 8x NVIDIA H100 - SXM - 80GB.

GPU Usage:

• Continual Training: 12 hours.

Training Arguments

We utilize torchtune library for the latest FSDP2 training code implementation.

Examples

1. Good example:

2. Misunderstanding example:

3. Off - tracked example:

📄 License

The model is under the apache - 2.0 license.

📖 Citation Information

BibTeX:

@article{Llama3-S: Sound Instruction Language Model 2024,
  title={Llama3 - S},
  author={Homebrew Research},
  year=2024,
  month=August},
  url={https://huggingface.co/homebrewltd/llama3.1 - s - 2024 - 08 - 20}

🙏 Acknowledgement

• WhisperSpeech
• [Meta - Llama - 3.1 - 8B - Instruct ](https://huggingface.co/meta - llama/Meta - Llama - 3.1 - 8B - Instruct)