home.social

#crfm — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #crfm, aggregated by home.social.

  1. Folx, if you're into #LLM #LLMs, and #ResponsibleAI, then you're going to enjoy this workshop by #Princeton #CITP and #Stanford #CRFM on Responsible and Open Foundation Models, on September 21, 11AM-5:30PM Eastern time (8AM-2:30PM Pacific Time). All welcome.

    From the website:
    Workshop participants will learn from experts in different fields who have worked on release strategies, risk mitigation, and policy interventions for developing open foundation models responsibly.

    🔗 Workshop website:
    sites.google.com/view/open-fou

    🔗 To RSVP and receive the Zoom link for the event, please use this form.
    docs.google.com/forms/d/e/1FAI

    Thanks to @sayashk, Rishi Bommasani, Percy Liang, and @randomwalker for organising.

  2. Releasing 3B and 7B #RedPajama-#INCITE family of models including base, instruction-tuned & chat models — #TOGETHER

    "The biggest takeaway is the demonstration that performant #LLMs can be built quickly by the open-source community. This work builds on top of our 1.2 trillion token RedPajama dataset, EleutherAI’s #Pythia training code, #FlashAttention from #Stanford and #Together, the #HELM benchmarks from Stanford #CRFM and generous support from #MILA, #EleutherAI & #LAION for compute time on the #Summit #supercomputer within the INCITE program award 'Scalable Foundation Models for Transferable Generalist AI'. We believe these kind of open collaborations, at larger scales, will be behind the best #AI systems of the future. "

    together.xyz/blog/redpajama-mo

  3. Releasing 3B and 7B #RedPajama-#INCITE family of models including base, instruction-tuned & chat models — #TOGETHER

    "The biggest takeaway is the demonstration that performant #LLMs can be built quickly by the open-source community. This work builds on top of our 1.2 trillion token RedPajama dataset, EleutherAI’s #Pythia training code, #FlashAttention from #Stanford and #Together, the #HELM benchmarks from Stanford #CRFM and generous support from #MILA, #EleutherAI & #LAION for compute time on the #Summit #supercomputer within the INCITE program award 'Scalable Foundation Models for Transferable Generalist AI'. We believe these kind of open collaborations, at larger scales, will be behind the best #AI systems of the future. "

    together.xyz/blog/redpajama-mo

  4. Releasing 3B and 7B #RedPajama-#INCITE family of models including base, instruction-tuned & chat models — #TOGETHER

    "The biggest takeaway is the demonstration that performant #LLMs can be built quickly by the open-source community. This work builds on top of our 1.2 trillion token RedPajama dataset, EleutherAI’s #Pythia training code, #FlashAttention from #Stanford and #Together, the #HELM benchmarks from Stanford #CRFM and generous support from #MILA, #EleutherAI & #LAION for compute time on the #Summit #supercomputer within the INCITE program award 'Scalable Foundation Models for Transferable Generalist AI'. We believe these kind of open collaborations, at larger scales, will be behind the best #AI systems of the future. "

    together.xyz/blog/redpajama-mo

  5. Releasing 3B and 7B #RedPajama-#INCITE family of models including base, instruction-tuned & chat models — #TOGETHER

    "The biggest takeaway is the demonstration that performant #LLMs can be built quickly by the open-source community. This work builds on top of our 1.2 trillion token RedPajama dataset, EleutherAI’s #Pythia training code, #FlashAttention from #Stanford and #Together, the #HELM benchmarks from Stanford #CRFM and generous support from #MILA, #EleutherAI & #LAION for compute time on the #Summit #supercomputer within the INCITE program award 'Scalable Foundation Models for Transferable Generalist AI'. We believe these kind of open collaborations, at larger scales, will be behind the best #AI systems of the future. "

    together.xyz/blog/redpajama-mo

  6. Releasing 3B and 7B #RedPajama-#INCITE family of models including base, instruction-tuned & chat models — #TOGETHER

    "The biggest takeaway is the demonstration that performant #LLMs can be built quickly by the open-source community. This work builds on top of our 1.2 trillion token RedPajama dataset, EleutherAI’s #Pythia training code, #FlashAttention from #Stanford and #Together, the #HELM benchmarks from Stanford #CRFM and generous support from #MILA, #EleutherAI & #LAION for compute time on the #Summit #supercomputer within the INCITE program award 'Scalable Foundation Models for Transferable Generalist AI'. We believe these kind of open collaborations, at larger scales, will be behind the best #AI systems of the future. "

    together.xyz/blog/redpajama-mo