have you exposed the ip? Ollama requires a few extra steps. You could also try LM studio and it’s just a tab
OPEN SOURCE
-
ASAL Releases Lifeforms Dataset from Large Scale Searches
By
–
We are releasing a dataset of the lifeforms found by ASAL from our large scale searches!
— Sakana AI (@SakanaAILabs) 10 janvier 2025
You can view the datasets here:https://t.co/EYJ30bePnuhttps://t.co/U6pQql6Xn8
To load them up and play around with them visit the ASAL github repo or this colab notebook:… pic.twitter.com/0RpewVet4KWe are releasing a dataset of the lifeforms found by ASAL from our large scale searches! You can view the datasets here: https://
pub.sakana.ai/asal/data/illu
mination_poster_lenia.png
… https://
pub.sakana.ai/asal/data/illu
mination_poster_boids.png
… To load them up and play around with them visit the ASAL github repo or this colab notebook: -
Microsoft’s Phi-4 14B Model Weights Now Publicly Available in LitGPT
By
–
The model weights of Microsoft’s phi-4 14B LLM are now finally publicly available. Thanks to a kind community contribution, it’s now also available in LitGPT already (litgpt finetune microsoft/phi-4):
https://
github.com/Lightning-AI/l
itgpt/pull/1904
… I will have more to say about phi-4 in my upcoming AI -
Nonprofit Tech Outperforms Big Tech During Crisis
By
–
Not lost on me that it's nonprofit tech, https://
app.watchduty.org, showing up & actually working in the midst of the LA fires (donate to them!) Meanwhile platforms fail to surface key news, vital info is paywalled… As I've been saying, we need a new tech paradigm, yesterday! -
Building LLMs from Scratch: Is It Really Necessary?
By
–
We’d all love to build a model from scratch like Llama, but how realistic is that? The computing, architecture, and training data they have access to are so vast that it’s fair to say most of us wouldn’t be able to replicate it. But is it really necessary to train such large
-
Apache Spark Python Data Source API Simplifies Custom Data Ingestion
By
–
Apache Spark’s Python Data Source API simplifies data ingestion from custom sources. Now, data engineers can efficiently integrate a broader array of data sources and sinks into their Spark pipelines. "The fact that we can now build, test, and surface reusable Spark data sources
-
Dutch Government Adopts Open Source Strategy Contributions
By
–
“We are a user of open source, which also includes giving back as much as possible,” says DICTU team leader Corien Potkamp. Read more about how the Dutch government chooses open source https://
bit.ly/4fulNJL #drupal #drupaldevdays #opensource -
Local AI Models Win: Phi-4 GGUF Released
By
–
Yayy! Local models for the win! https://
huggingface.co/lmstudio-commu
nity/phi-4-GGUF
… -
MIT Licensed Release Kickstarts 2025 Development
By
–
What a lovely way to kickstart 2025! Congratulations again on the release – MIT license looks lovely!
-
LangGraph JS: Build AI Agents and Workflows
By
–
Langgraph js! https://
langchain-ai.github.io/langgraphjs/