Not really – open weights is a huge win in itself.
@reach_vb
-
Gated Repositories and Access Control for AI Model Weights
By
–
That’s precisely why we have gated repos and then we could have a Sign in with HF to ensure only people on ACL are able to access the weights.
-
AlphaFold Server Enables On-Demand Protein Structure Prediction
By
–
You can also check out the AlphaFold Server for on-demand inference! https://
alphafoldserver.com/about -
Google DeepMind Model Weights Distribution Process and Timeline
By
–
The model weights require you to fill a Google Form and wait for 3-4 business days, but hoping @GoogleDeepMind brings the model weights over to the Hub.
-
AlphaFold3 inference codebase released by Google DeepMind
By
–
Inference codebase: https://
github.com/google-deepmin
d/alphafold3
… -
DeepMind Releases AlphaFold 3 Model Weights and Server
By
–
Wohoo! DeepMind released AlphaFold 3 inference codebase, model weights and an on-demand server! AlphaFold can generate highly accurate biomolecular structure predictions containing proteins, DNA, RNA, ligands, ions, and also model chemical modifications for proteins and
-
Hugging Face Hub hosts model weights with gated repository access
By
–
Congratulations on the release – Would love to help get these model weights on the Hugging Face hub. We can set up gated repositories so you have full ACL of who accesses the model repositories as well. (We do the same for Gemma repos as well, lmk if that’s helpful)
-
Fine-tune AI models with custom datasets and voice personas
By
–
You would be able to fine-tune it on your own dataset/ voice persona soon!
-
Two-Channel Audio Models with Text Pretraining Architecture
By
–
One-Channel Stack: > Trained on 20M hours of audio
> Primary checkpoint initialized from pretrained language model on 2T text tokens
> Text-pretrained model shows higher coherence in subjective evaluations Two-Channel Hertz-lm: > Predicts two quantized latents for two separate -
Hertz-VAE: 1.8B Parameter Decoder-Only Transformer Architecture
By
–
Hertz-vae: > 1.8B parameters, 8-layer decoder-only transformer
> First four layers receive latent history
> Layer 5 receives ground-truth 15-bit quantized representation during training
> Directly samples hertz-lm's next token prediction during inference
> Near-perfect at