🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

First, an instruction-tuned large language model, fine-tuned for chat from EleutherAI’s GPT-NeoX-20B with over 43 million instructions on 100% carbon negative compute available under Apache-2.0 license on Hugging Face. huggingface.co/togethercomput…

Informer, from "Beyond Efficient Transformer for Long Sequence Time-Series Forecasting" (AAAI'21 Best Paper) is now available Hugging Face Transformers! 🙌 We created a tutorial for multi-variate forecasting, check it out: huggingface.co/blog/informer Colab with @ESimhayev (1/2)

OpenAI's speech-to-text API "Whisper" just got supercharged: This tool transcribes audio 70x faster than Whisper A 2-hour podcast can now be transcribed in ~30 seconds using Whisper JAX: The Fastest Whisper API Try it here using your mic: huggingface.co/spaces/sanchit…

Want to adopt the latest LLMs for a specific target domain (e.g., finance data) or target task like document classification? Finetuning becomes more feasible as we see more and more pretrained LLMs become available under open-source licenses. magazine.sebastianraschka.com/p/finetuning-l… Here's an

Added more OSS language models to the Vercel AI Playground via Hugging Face: ◆ OpenAssistant/oasst-sft-4-pythia-12b-epoch-3.5 ◆ EleutherAI/gpt-neox-20b ◆ bigcode/santacoder ◆ bigscience/bloom → play.vercel.ai/r/MsqSVto

I had no idea about Hugging Face. Ppl can create and share interfaces to AI apps called Spaces. This one here can: - take any Youtube link - transcribes the linked video using Whisper - separates speakers and outputs the transcript huggingface.co/spaces/vumichi…

What was going on with the Open LLM Leaderboard? Its numbers didn't match the ones reported in the LLaMA paper! We've decided to dive in this rabbit hole with friends from the LLaMA & Falcon teams and got back with a blog post of learnings & surprises: huggingface.co/blog/evaluatin…

In our current project (coming soon, stay tuned!), we (with @irubachev) have evaluated our tabular DL models on the datasets from this paper by Léo Grinsztajn Gael Varoquaux 🦋 et al. Let's discuss the results! 🧵 1/7

The longer people are in academia, the more they realize that when reading papers it's best to ignore Intro, Discussion etc. and just look at Methods and Results journals.plos.org/plosone/articl…

Code Llama with Hugging Face🤗 Yesterday, @MetaAI released Code Llama, a family of open-access code LLMs! Today, we release the integration in the Hugging Face ecosystem🔥 Models: 👉 huggingface.co/codellama blog post: 👉 hf.co/blog/codellama Blog post covers how to use it!

I just uploaded a 90 minute tutorial, which is designed to be the one place I point coders at when they ask "hey, tell me everything I need to know about LLMs!" It starts at the basics: the 3-step pre-training / fine-tuning / classifier ULMFiT approach used in all modern LLMs.

Re LLM in medicine: “We encourage efforts to understand how and when models report wrong results, with examples of such responses.” jamanetwork.com/journals/jaman…

Important to watch out for AI regulations that effectively bolster the position of big tech incumbents by shutting out open source researchers and developers. More of the right overwatch is good. Less of the FTX crypto - esque regulation lobbying businessinsider.com/andrew-ng-goog…

We showed the problem with math in 2009 (pubmed.ncbi.nlm.nih.gov/19494805/): the conditions under which personalized standard antidepressant selection is particularly useful are often unrealistic, in terms of differences in effectiveness (bc much of benefit placebo-like)

Neuroimaging research in psychology has led to so many false positive, non replicable findings due to questionable research practices & publication bias that Science Advances now publishes null findings to clean up the literature (this is from 2022). science.org/doi/10.1126/sc…

Introducing OpenBioLLM-Llama3-70B & 8B: The most capable openly available Medical-domain LLMs to date! 🩺💊🧬 Outperforms industry giants like GPT-4, Gemini, Meditron-70B, Med-PaLM-1, and Med-PaLM-2 in the biomedical domain. 🏥📈 🌟 OpenBioLLM-70B delivers SOTA performance,

The new interpretability paper from Anthropic is totally based. Feels like analyzing an alien life form. If you only read one 90-min-read paper today, it has to be this one transformer-circuits.pub/2024/scaling-m…

How well can AI (GPT4+RAG) identify patients for clinical trials relative to experts using human-defined queries? NEJM AI ai.nejm.org/doi/full/10.10… (spoiler: Very well) CODA: Which one of the authors is featured in nomenomen.us ?

When medicine is failing, the question for AI applications becomes: Compared To What?

Excited to introduce 𝐋𝐀𝐏𝐀: the first unsupervised pretraining method for Vision-Language-Action models. Outperforms SOTA models trained with ground-truth actions 30x more efficient than conventional VLA pretraining 📝: arxiv.org/abs/2410.11758 🧵 1/9