If you've never created your own fine-tuned LoRA, it's not too late to start. Check out this guide:
OPEN SOURCE
-
Run LoRAs on Hugging Face Hub via Replicate Inference
By
–
You can now run LoRAs directly on the Hugging Face Hub using Replicate for inference. This is possible thanks to a small update to Hugging Face’s inference client that hooks into Replicate behind the scenes. The result: fast, low-cost inference with your favorite LoRAs, right
-
Execute 30000 LoRAs on Hugging Face via Replicate
By
–
Run 30,000+ LoRAs on Hugging Face with Replicate
-
Discover awesome-langgraphjs open source projects collection
By
–
Checkout "awesome-langgraphjs" for a collection of open source projects built with LangGraph.js! Have your own open source LangGraph.js project? Please open a PR adding a link to it!
-
Drupal Development Updates Before Midwest Camp
By
–
If you want to know what we've been working on before you see us at @midwestcamp , check out our blog –> https://
bit.ly/4hQnWBJ #midcamp #drupal #foss -
Kaggle and Hugging Face Collaboration Enables Direct Model Integration
By
–
Awesome to see the collab between @kaggle and @huggingface. Now you can use any model from Hugging Face directly in Kaggle. Previously, we had to download and upload the models as datasets. This was much needed 🚀 pic.twitter.com/VtCVKIyS8N
— abhishek (@abhi1thakur) 16 mai 2025Awesome to see the collab between @kaggle and @huggingface
. Now you can use any model from Hugging Face directly in Kaggle. Previously, we had to download and upload the models as datasets. This was much needed -
BLIP3-o: Open Unified Multimodal Models Architecture Training
By
–
BLIP3-o: A Family of Fully Open Unified Multimodal
Models—Architecture, Training and Dataset Paper: https://
arxiv.org/pdf/2505.09568
v1
…
Code: https://
github.com/JiuhaiChen/BLI
P3o
…
Models: https://
huggingface.co/BLIP3o/BLIP3o-
Model
…
Pretrain Data: https://
huggingface.co/datasets/BLIP3
o/BLIP3o-Pretrain
…
Instruction Tuning Data: https://
huggingface.co/datasets/BLIP3
o/BLIP3o-60k
… -
Arm’s Learning Path: Stable Audio Open on CPUs
By
–
You can check out Arm's Learning Path, which offers hands-on guidance using Stable Audio Open Small on Arm CPUs:
-
Windsurf Releases SWE-1 Foundational Models
By
–
Windsurf announced their own foundational models: SWE-1, SWE-1-lite, and SWE-1-mini!
— 🚨 AI News | TestingCatalog (@testingcatalog) 15 mai 2025
These models are tailored towards SWE tasks that perform at a level of frontier models from leading AI labs. https://t.co/HvV4i13hCj pic.twitter.com/mTj8P0ni7xWindsurf announced their own foundational models: SWE-1, SWE-1-lite, and SWE-1-mini! These models are tailored towards SWE tasks that perform at a level of frontier models from leading AI labs.
-
Google Testing New Gemma 3 75b Model
By
–
Seems like Google is testing a new Gemma 3 75b model on lmarena under the "cutiepie-75" name.