DeepSeek is back! JanusFlow 1.3B – Unified multimodal LLM > Key Finding: Rectified flow can be trained within the large language model framework without complex modifications. > Base Model: Built on DeepSeek-LLM-1.3b-base. > Vision Encoder: SigLIP-L, supports 384 x 384
@reach_vb
-
OpenAI Returns with Open Artifacts on Hugging Face
By
–
Welcome back! Hoping that your return also brings some life to open artefacts on the OpenAI org on the Hugging Face Hub too: https://
huggingface.co/openai -
BRIA-RMBG-2.0 AI Model for Background Removal Now Live
By
–
You can try the model live on the space here: https://
huggingface.co/spaces/briaai/
BRIA-RMBG-2.0
… -
Open Source Model Beats GPT4o, Runs on Budget GPU
By
–
Beats GPT4o, rivals Claude Sonnet – can run on the cheapest GPU VPS available! Open source is the way to go!
-
32B Open Source LLM Fits Affordable GPU Hardware
By
–
If this doesn’t make you bullish on Open Source – I don’t know what will! That’s a 32B LLM that can easily fit on a ~0.8 USD/ hour GPU – spitting ungodly num of tokens Back of the napkin math:
– fp16/ bf16 – 32GB VRAM (would fit on a L40S)
– 8-bit – 16GB VRAM (L4)
– 4-bit – -
Open Weights Models Represent Major Victory for AI Community
By
–
Not really – open weights is a huge win in itself.
-
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
…