This is a really cool new model, and a hint at the future of open source language models. Synthetic data, model merges and RLHF are becoming crucial tools in the AI hacker's toolkit. Try Hermes 2 Θ on Replicate right now at https://
replicate.com/nousresearch/h
ermes-2-theta-llama-8b
… and let us know what you think!
OPEN SOURCE
-
Hermes 2 Θ: Open Source Language Model Innovation
By
–
-
Open-source Framework for Building AI Applications in Databases
By
–
AI in your Database. An open-source framework for building AI Applications right in your databases:
-
Meta’s Omni Models Challenge OpenAI’s GPT-4o
By
–
Meta has had GPT-4o-style omni models for at least five months. I’d be shocked if they don’t release an answer to GPT-4o soon. Imagine what a world with open-source omni models would look like…
-
Hands-on Tutorial on Cloud and Fog Robotics with ROS2 and FogROS2
By
–
Excited about the Hands-on Tutorial on Cloud and Fog Robotics: with ROS2 and FogROS2 today #ICRA2024 in CC-304 8:30am-12:30pm:
-
Mosaic AI Releases 70M Image-Text Dataset on Hugging Face
By
–
Awesome models and datasets released by our friends at @DbrxMosaicAI Not only is this a large openly licensed image-text pair dataset (~70M images), it is also the largest dataset hosted on the Hugging Face Hub
-
Llama3 Local RAG Python Script GitHub Repository
By
–
Here is the python script and instructions ar in redme: https://
github.com/Shubhamsaboo/a
wesome-llm-apps/tree/main/llama3_local_rag
… -
Hugging Face Spaces Dev Mode Enables Remote SSH Debugging
By
–
Have you ever wanted to connect to your @huggingface Space over SSH? For instance to debug a nasty GPU error remotely? Well… now you can Introducing Spaces Dev Mode:
-
ZeroGPU Infrastructure Success at Sakana AI Labs
By
–
ZeroGPU is a fantastic example of great AI infrastructure developed by @HuggingFace
. At @SakanaAILabs we’ve already been using it to showcase models like EvoVLM and EvoSDXL and it works like a charm. -
RAPIDS cuDF Library Now Integrated in Google Colab
By
–
Also their cuDF library will automatically know if you're running on GPU or CPU and speed up your processing. RAPIDS cuDF is now integrated directly into Google Colab. Checkout the Colab Notebook: https://
colab.research.google.com/github/rapidsa
i-community/showcase/blob/main/getting_started_tutorials/cudf_pandas_colab_demo.ipynb?ncid=ref-inor-594904
… Check out the Repo: -
ObjectBox: Fast Vector Database for Offline Mobile AI Apps
By
–
I just came across an amazing Vectordb,ObjectBox which is designed to operate on mobile phones and various restricted devices, empowering developers to create AI-powered apps that work flawlessly offline. And it’s fast and easy-to-use. Check it out: