Hugging Face's logo
Doron Adler's picture
121 110 990

Doron Adler PRO

Norod78
Nicholas0228's profile picture securetechnix's profile picture Ale131313's profile picture
·
https://linktr.ee/Norod78

AI & ML interests

Fooling around with Generative machine learning models.

Recent Activity

reacted to matteospanio's post with 🚀 2 days ago
🎶 Released mule-torch — an unofficial PyTorch port of MULE (SF-NFNet-F0), SiriusXM/Pandora's music-audio embedding model (McCallum et al., ISMIR 2022). No retraining: I re-implemented the architecture in pure PyTorch and transferred the original TensorFlow weights, then checked it layer by layer against the genuine TF pipeline. ✅ End-to-end clip-embedding cosine 0.9999999 vs the original ✅ ONNX backbone parity < 1e-6 ✅ 62.35M params (paper: ~62.4M) ✅ Batched, GPU-native, ONNX-exportable — none of which the original `Analysis` pipeline does ```python pip install mule-torch ``` ```python from mule_torch import MuleModel emb = MuleModel.from_pretrained()(waveform) # (B, T)@16kHz -> (B, 1728) ``` 🤗 Weights: https://huggingface.co/matteospanio/mule 💻 Code: https://github.com/matteospanio/mule-torch 📦 PyPI: https://pypi.org/project/mule-torch/ The fun bug: parity was perfect through every conv but the block output was anti-correlated (cos = −1). Cause: the learnable skip-init gains couldn't be mapped by layer name (Keras scrambles the order) — they had to be recovered from the graph. ⚠️ Unofficial, community port — not affiliated with or endorsed by the original authors. All credit to them; please cite the paper. Weights inherit CC-BY-NC-4.0.
liked a Space 2 days ago
google/TIPSv2
liked a Space 3 days ago
ideogram-ai/ideogram4
View all activity

Organizations

Spaces-explorers's profile picture Gradio-Blocks-Party's profile picture Yam Peleg's profile picture ZeroGPU Explorers's profile picture Mixtiles's profile picture Social Post Explorers's profile picture Hugging Face Discord Community's profile picture Endless Technologies Ltd. 's profile picture Unsloth Jobs Explorers's profile picture