Hello guys. I want to introduce my recent research presented at ICML workshop. github link : genji970/SRM-LoRA: official implementation of "SRM-LoRA: Sub-Riemannian-Metric Updates for Mitigating LLM…
Does anyone know of any evidence/forum/paper analyzing benchmark result differences between cloud inference platforms (togetherai) and running models locally with vLLM under greedy decoding? submitted by…
Hello community, just a short reminder that Raffi Krikorian (CTO @ Mozilla) is live today for an AMA to discuss Mozilla's inaugural State of Open Source…
I’m training a single-class segmentation model for large rectangular artwork placed on the floor and photographed from above. We have around 3,000 accurately masked original images…
NB: Reposting due to a typo in the title Putting this here instead of the other subs since I figured a question on deep learning theory…
Disclosure: I built it, it is open source, Apache-2.0 licensed, and currently alpha. Repository: https://github.com/mireklzicar/gpuhedge I started working on it after benchmarking a 17 GB AI…
Read a long piece on the future of LLM reasoning that makes a provocative claim: Chain of Thought is a useful hack but we've started to…
LLM's seem to make it so much easier to run experiments, write papers, etc. As a result, are we seeing phd students finish their phds sooner…
Left: Telegram digest (optional); Right: detailed digest on HTML Like probably everyone here, my to-read list only grows. Skimming arXiv listings or my feeds takes 30-60…
My TMLR paper was assigned to reviewers on April 23, and as of July 13 I've received 2 reviews, but the third is still pending. The…