Mothersuperior/yue2-mothersuperior-realaudio-tokenizer-v4

AI model by Mothersuperior

Older snapshot: check the original source for current information.

From the publisher

Model card & documentation

Source preview

Read the publisher’s intended use, setup instructions, evaluations and limitations. The original model card is the source of truth.

Real-audio tooling for YuE2-3B: the audio → semantic-token encoder YuE2 doesn't ship, plus a NAR-branch LoRA so the decoder renders real-production latents. Together they let you tokenize your own recordings, LoRA-tune YuE2's AR on an artist, and generate new songs or covers. Same weights as the .pt files, bit-exact in fp32 (the .bf16 variants are half the size; head top-1 agreement with fp32 is 98.6%). The previously published scripts accept either extension via scripts/ckptio.loadckpt(path), which returns the same dict the .pt files hold. Apply as W += loraB @ loraA (scale 1.0, no alpha) to the matching model.layers[i] Linear of YuE2-3B. vae2llm.{weight,bias} and llm2vae.{weight,bias} are full replacement weights for those two Linear layers, not LoRA deltas. Rank and the delta rule are also in the file metadata. narlorajointv4comfyui.safetensors is the same NAR LoRA in ComfyUI's native YuE2 layout: load it with the standard LoraLoader on the MODEL output of the…

Mothersuperior/yue2-mothersuperior-realaudio-tokenizer-v4 on Hugging Face A short preview, not the full document.

Read the full model card ↗ · Preview checked 2026-10-30T13:26:26.101Z

Inside the original model card — Document outline

Headings are captured from the source. Links open the publisher’s document, not a locally hosted copy.

Links from the model card

References supplied by the publisher, not independently verified endorsements. Check the destination before downloading files or entering credentials.

Documentation belongs to its respective authors. Reported project/model license: cc-by-nc-4.0. A listing is not a grant of reuse or training rights. Confirm the document’s own terms at the source.

Model overview

Mothersuperior/yue2-mothersuperior-realaudio-tokenizer-v4 is a task-unspecified model repository published by Mothersuperior on Hugging Face. A library was not reported.

This page summarizes Hub metadata. For intended use, training data, evaluation results and limitations, consult the original model card.

Model facts

Task: Not reported
Library: Not reported
Recent downloads (30 days): 0
Cumulative likes: 165
Hugging Face trending score: 73
Reported safetensors parameters: Not reported
Architecture: Not reported
License: cc-by-nc-4.0
Access: Not gated by Hugging Face
Created: 2026-09-13T21:54:51.000Z
Last modified: 2026-09-19T17:37:54.000Z

Compatibility and lineage

Language coverage was not reported.

Reported base models: m-a-p/YuE2-3B, m-a-p/MERT-v2-FullSong

Parameter count is not a RAM/VRAM requirement. Check precision, quantization, context length and runtime compatibility in the model card; no hardware or API-cost claim is inferred here.

Use and evaluate

Check license terms and access requirements first. Review the model card’s documented loading instructions, evaluations and safety limitations. Benchmark scores are not imported by this directory, and popularity is not an accuracy ranking.

No model weights are downloaded or executed by AltAPIs. Never enable remote model code without reviewing it.

Model card and usage instructions

Model files and configuration

Community discussion

Source and freshness

Source: Hugging Face Hub. Metadata observed 2026-09-22T06:37:15.734Z. Daily imports are snapshots, not real-time monitoring.

Popularity and source listings do not establish security, suitability, licensing rights or benchmark performance.

Open original source