Infinite London
🎡
3
Explore an endless, procedurally generated 3D London
Dan PRO
Daankular
AI & ML interests
None yet
Recent Activity
liked a Space about 1 hour ago
mishig/infinite-london liked a Space about 8 hours ago
victor/LongCat-Video-Avatar-1.5 liked a model about 8 hours ago
SupraLabs/Supra-Title-350M-exp-GGUFOrganizations
liked a
Space about 1 hour ago
liked a
Space about 8 hours ago
liked a
model about 8 hours ago
30 min of ZeroGPU gone
👀😔 2
2
#2 opened 8 days ago
by Daankular
Feature Request: Export / Imports settings as profiles
1
#3 opened about 10 hours ago
by Daankular
liked a
model about 12 hours ago
updated a
Space 1 day ago
liked a
model 1 day ago
liked 2
Spaces 2 days ago
liked a
model 3 days ago
liked a
model 4 days ago
liked a
Space 5 days ago
reacted to danielhanchen's post with 👍 6 days ago
Post
3990
Google releases Gemma 4 QAT. ✨
You can now run Gemma 4 at 3x less memory with near original performance.
QAT makes it possible to run Gemma 4 26B-A4B on 16GB RAM.
GGUFs: https://huggingface.co/collections/unsloth/gemma-4-qat
QAT Guide: https://unsloth.ai/docs/models/gemma-4/qat
You can now run Gemma 4 at 3x less memory with near original performance.
QAT makes it possible to run Gemma 4 26B-A4B on 16GB RAM.
GGUFs: https://huggingface.co/collections/unsloth/gemma-4-qat
QAT Guide: https://unsloth.ai/docs/models/gemma-4/qat
- 1 reply
liked a
model 6 days ago
liked a
Space 6 days ago
liked a
model 6 days ago
liked a
dataset 6 days ago
reacted to matteospanio's post with 🚀 6 days ago
Post
7029
🎶 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
🤗 Weights: 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.
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 doespip install mule-torchfrom mule_torch import MuleModel
emb = MuleModel.from_pretrained()(waveform) # (B, T)@16kHz -> (B, 1728)🤗 Weights: 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 7 days ago