That's a really cool feature! The biggest problem with the 1T model was the download/upload. Great news 🙂
LLMS
-

Chinese Open-Weights Model Surpasses All Previous MATH Benchmarks
By
–
Chinese open weights model that easily surpasses all previous models, both closed and open, at MATH:
-
Hub Announcement Features Maxime Labonne and Bartowski
By
–
the announcement mentions you two @maximelabonne @bartowski1182 and you might be excited about what's coming to the hub
-

OpenAI Q* Strawberry Announcement Expected Soon
By
–
Mucho ruido incentivado desde OpenAI apunta a que podría haber un anuncio próximo. Algo relacionado con Q*/strawberry. No lo sé, a veces prefiero un blog post anunciando cosas que tanto jaleo por Twitter.
-
Redirecting VC Funding from Hyped LLMs to AI4Science and Sustainability
By
–
So maybe it is time to reroute all those VC $$ to AI4Science and AI4Sustainability and away from LLMs which are currently too hyped up. That bubble is about to deflate to a more reasonable valuation I would think.
-
English Translation to Math Impossible with LLMs
By
–
English can be translated into math, but not with LLMs.
-
Optimus-1: Hybrid Multimodal Memory Agents for Long-Horizon Tasks
By
–
Optimus-1
— AK (@_akhaliq) 8 août 2024
Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks
discuss: https://t.co/EhNN4PZi7E
Building a general-purpose agent is a long-standing vision in the field of artificial intelligence. Existing agents have made remarkable progress in many domains,… pic.twitter.com/wmdtV7MjiaOptimus-1 Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks discuss: https://
huggingface.co/papers/2408.03
615
… Building a general-purpose agent is a long-standing vision in the field of artificial intelligence. Existing agents have made remarkable progress in many domains, -
Community Demo: EXAONE-3.0-7.8B-Instruct Model
By
–
community demo: https://
huggingface.co/spaces/kabbi/E
XAONE-3.0-7.8B-Instruct
… -
Model Providers Race to Match OpenAI Endpoint Compatibility
By
–
My hunch is that the rest of the model providers will quickly follow suit to maintain compatibility with the OpenAI endpoint.