---
license: cc-by-nc-4.0
base_model: liujiafeng/Khala-MusicGeneration-v1.0
pipeline_tag: text-to-audio
tags:
  - music-generation
  - audio
  - apple-silicon
  - mps
  - khala
  - acoustic-tokens
---

# Khala — Apple Silicon (MPS) pre-converted weights

Pre-converted, **vanilla-PyTorch** weights for running
[**Khala**](https://huggingface.co/liujiafeng/Khala-MusicGeneration-v1.0) — a
high-fidelity, unified acoustic-token song generator — on **Apple Silicon (MPS) or
CPU**, with no NVIDIA / Megatron / TransformerEngine / FlashAttention stack.

These are **format conversions of the original weights**, not a retrain. They are
produced by gathering the upstream Megatron `torch_dist` checkpoint and the DAC-RVQ
decoder, then renaming tensors to the de-Megatron `KhalaModel` layout. The numerics
match the original (backbone greedy decode is bit-identical to the CUDA reference,
64/64 tokens).

## Files

| File | What it is |
|---|---|
| `khala_backbone.safetensors` | Backbone GPT (q0/q1 coarse acoustic tokens), `KhalaModel` naming |
| `khala_superres.safetensors` | Super-resolution GPT (expands to q0…q63), non-causal |
| `decoder_weights.pt` | DAC-RVQ decoder (generator-only), stereo, 64 quantizers |
| `backbone_megatron_args.json` | Backbone config (consumed by `KhalaConfig.from_megatron_args`) |
| `superres_megatron_args.json` | Super-res config |
| `decoder_config.yaml` | Decoder config |

## Usage

Download into the directory the vanilla runtime reads (`_cuda_artifacts/`, or set
`KHALA_VANILLA_WEIGHTS`):

```bash
hf download Vinpolar/Khala-MusicGeneration-v1.0-MPS --local-dir _cuda_artifacts
```

Then run the CLI generator or the Mac web stack from the Khala repo (Apple Silicon
section of the README):

```bash
# one-off track from the command line
KHALA_BACKEND=vanilla .venv-mac/bin/python -u tools/generate_vanilla.py \
    --duration 3 --tags "upbeat, pop, piano"

# or the full web UI (worker + API)
bash backend/run_backend_mac.sh        # --device cpu also supported
```

## Attribution & license

- Original model, weights, and research: **liujiafeng / the Khala team** —
  [liujiafeng/Khala-MusicGeneration-v1.0](https://huggingface.co/liujiafeng/Khala-MusicGeneration-v1.0),
  [paper](https://arxiv.org/abs/2605.01790).
- Released under **CC BY-NC 4.0**, the same license as the original weights. This
  repository only re-packages those weights for Apple-Silicon inference.
- ⚠️ The upstream team noted (2026-05-07) a possible inference-quality precision
  issue under investigation; treat generation quality as not yet final.