MacOS 15.1 Apple Intelligence Prompt Templates are out! "Do not hallucinate. Do not make up factual information." Query creation is quite interesting too: – Ensure music artist names are specifically marked as a music artist, not simply as a 'who'. – Identify named locations
@reach_vb
-
Hugging Face Congratulates Company on Successful Funding Round
By
–
Congrats on the well deserved round! If there's anything Hugging Face can do to help you, do let me know! Looking forward to the releases ahead!
-
GPT-4o System Card: Capabilities, Limitations and Safety
By
–
GPT-4o System Card “In this System Card, we provide a detailed look at GPT-4o's capabilities, limitations, and safety evaluations across multiple categories, focusing on speech-to-speech while also evaluating text and image capabilities, and measures we've implemented to ensure
-
Hugging Face calls for open source model checkpoint sharing
By
–
Open call @papla_media – if you consider Open Sourcing your model checkpoints I'd be more than happy to help from Hugging Face Hub side!
-
Breakthrough: Open GPT-4o Reproduction Achieves Multimodal Capabilities
By
–
This is the closest we've been to Open GPT4o reproduction! 🔥
— Vaibhav (VB) Srivastav (@reach_vb) 28 octobre 2024
Text + Audio + Image modalities combined, one-shot. https://t.co/13NJtqT5Bv pic.twitter.com/mg6v587f6EThis is the closest we've been to Open GPT4o reproduction! Text + Audio + Image modalities combined, one-shot.
-
Mini-Omni 2: Multimodal AI with Real-Time Voice Conversations
By
–
Mini-Omni 2 understands image, audio and text inputs all via end-to-end voice conversations with users 🔥
— Vaibhav (VB) Srivastav (@reach_vb) 28 octobre 2024
> Understands and processes images, speech, and text
> Generates real-time speech responses
> Supports interruptions during speech
Technical Overview:
> Concatenates image,… pic.twitter.com/VrmlAWX0JjMini-Omni 2 understands image, audio and text inputs all via end-to-end voice conversations with users > Understands and processes images, speech, and text
> Generates real-time speech responses
> Supports interruptions during speech Technical Overview:
> Concatenates image, -
Free AI Spaces Available on Hugging Face Platform
By
–
It's free, you just go on http://
hf.co/spaces and click on any of them – use as you like. -
Explore Hugging Face Spaces for AI Models and Applications
By
–
Check'em out here: https://
huggingface.co/spaces -
Weekly AI Spaces: Text to Image, Video, Multilingual LLMs
By
–
Spaces of the week! – we've got Text to Image, Text to Video, Multilingual LLMs and much more!
-
Open Source AI Project Code Available for Experimentation
By
–
But, it’s open – with all the code open source, you can fiddle with it, try different prompts, things etc The final output is not at that level, but, it only gets better from here,