Downloads · 30 days
9
14% of all-time downloads
maolandaw/HeartMuLa-RL-oss-3B-20260123
HeartMuLa-RL-oss-3B-20260123 is a machine learning model from maolandaw. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for burn. The card lists the license as apache-2.0.
This repository contains Burn-format weights for the upstream model:
Downloads · 30 days
9
14% of all-time downloads
All-time downloads
64
Public
Repo size
15.8 GB
Likes
0
Public
Click a slice to open those files.
.bpk15.8 GB · 100%
From the Hugging Face model README
This repository contains Burn-format weights for the upstream model:
The published artifacts are packaged as Burn Pack (.bpk) archives. The repository also includes Rust tooling to regenerate the raw export manifest and Burn pack from the upstream checkpoint.
Published model assets at the repository root:
heartmula.bpktokenizer.jsongen_config.jsonconfig.jsonLICENSEConversion and packaging sources included in the repository:
convert.sh: one-step export-and-pack script that writes heartmula.bpk at the repository rootsrc/bin/export_heartmula_raw.rs: exports the upstream safetensors checkpoint into .npy tensors plus a manifest filesrc/main.rs: packs exported tensors into Burn Pack archivesCargo.toml, Cargo.lock: Rust dependencies for the packerCKPT_ROOT/
├── HeartMuLa-RL-oss-3B-20260123/
├── tokenizer.json
└── gen_config.json
This conversion repo ships the Apache-2.0 LICENSE directly and copies it into the output artifact directory during conversion.
./convert.sh CKPT_ROOT
This regenerates heartmula.bpk at the repository root and removes the temporary artifact directory when finished.