AI everyday's picture

34 266

AI everyday

ai-everyday

·

AI & ML interests

None yet

Recent Activity

Reacted to fdaudens's post with 👍 about 12 hours ago

Just watched @thomwolf tear down the over-hyped AGI narrative in 30 seconds - and it's refreshingly grounded. No wild speculation about superintelligence timelines or consciousness. Just practical insights from someone who really understands the technology. This is the kind of level-headed perspective that helps us focus on what AI can actually do today (which is already transformative) rather than getting lost in AGI fantasy. Worth your time if you want to understand AI progress without the hype. Watch the full interview at CogX here: https://www.youtube.com/watch?v=IjL_6Th6Ea0

Reacted to Taylor658's post with 👀 about 12 hours ago

The Mystery Bot 🕵️‍♂️ saga I posted about from earlier this week has been solved...🤗 Cohere for AI has just announced its open source Aya Expanse multilingual model. The Initial release supports 23 languages with more on the way soon.🌌 🌍 You can also try Aya Expanse via SMS on your mobile phone using the global WhatsApp number or one of the initial set of country specific numbers listed below.⬇️ 🌍WhatsApp - +14313028498 Germany - (+49) 1771786365 USA – +18332746219 United Kingdom — (+44) 7418373332 Canada – (+1) 2044107115 Netherlands – (+31) 97006520757 Brazil — (+55) 11950110169 Portugal – (+351) 923249773 Italy – (+39) 3399950813 Poland - (+48) 459050281

Reacted to tomaarsen's post with 🔥 about 12 hours ago

I just released Sentence Transformers v3.3.0 & it's huge! 4.5x speedup for CPU with OpenVINO int8 static quantization, training with prompts for a free perf. boost, PEFT integration, evaluation on NanoBEIR, and more! Details: 1. We integrate Post-Training Static Quantization using OpenVINO, a very efficient solution for CPUs that processes 4.78x as many texts per second on average, while only hurting performance by 0.36% on average. There's a new `export_static_quantized_openvino_model` method to quantize a model. 2. We add the option to train with prompts, e.g. strings like "query: ", "search_document: " or "Represent this sentence for searching relevant passages: ". It's as simple as using the `prompts` argument in `SentenceTransformerTrainingArguments`. Our experiments show that you can easily reach 0.66% to 0.90% relative performance improvement on NDCG@10 at no extra cost by adding "query: " before each training query and "document: " before each training answer. 3. Sentence Transformers now supports training PEFT adapters via 7 new methods for adding new adapters or loading pre-trained ones. You can also directly load a trained adapter with SentenceTransformer as if it's a normal model. Very useful for e.g. 1) training multiple adapters on 1 base model, 2) training bigger models than otherwise possible, or 3) cheaply hosting multiple models by switching multiple adapters on 1 base model. 4. We added easy evaluation on NanoBEIR, a subset of BEIR a.k.a. the MTEB Retrieval benchmark. It contains 13 datasets with 50 queries and up to 10k documents each. Evaluation is fast, and can easily be done during training to track your model's performance on general-purpose information retrieval tasks. Additionally, we also deprecate Python 3.8, add better compatibility with Transformers v4.46.0, and more. Read the full release notes here: https://github.com/UKPLab/sentence-transformers/releases/tag/v3.3.0

View all activity

Organizations

ai-everyday's activity

upvoted 2 collections about 16 hours ago

Flux LoRA Collections

Flux THE LoRA • 82 items • Updated about 15 hours ago • 27

LoRA Space Collections

Flux & Sdxl • 4 items • Updated 4 days ago • 10

upvoted a paper about 16 hours ago

Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions

Paper • 2411.14405 • Published 2 days ago • 30

upvoted a paper 2 months ago

Kolmogorov-Arnold Transformer

Paper • 2409.10594 • Published Sep 16 • 38

upvoted an article 3 months ago

Article

The Open Medical-LLM Leaderboard: Benchmarking Large Language Models in Healthcare

Apr 19

• 119

upvoted 2 collections 3 months ago

MiniCPM

The MiniCPM family of LLMs and VLLMs. • 31 items • Updated Oct 22 • 54

SimPO

This collections contains a list of SimPO and baseline models. • 49 items • Updated 17 days ago • 15

upvoted 7 collections 4 months ago

AV LLMs

A collection of Audio, Video and Visual LLMs. • 48 items • Updated about 4 hours ago • 3

PDF Document / OCR Datasets

Document datasets with .pdf files that are usable with pixparse libraries and tools. • 2 items • Updated Mar 30 • 47

Document VQA Datasets

Document question & answer datasets that have been tested with pixparse libraries and tools. • 2 items • Updated Mar 29 • 1

Open LLM Leaderboard 2

8 items • Updated Oct 17 • 7

The Big Benchmarks Collection

Gathering benchmark spaces on the hub (beyond the Open LLM Leaderboard) • 13 items • Updated 6 days ago • 158

Open LLM Leaderboard best models ❤️‍🔥

A daily uploaded list of models with best evaluations on the LLM leaderboard: • 60 items • Updated about 1 hour ago • 443

LLaVA - Visual Question Answering

31 items • Updated Oct 22 • 9

upvoted a collection 5 months ago

Whisper Release

Whisper includes both English-only and multilingual checkpoints for ASR and ST, ranging from 38M params for the tiny models to 1.5B params for large. • 12 items • Updated Sep 13, 2023 • 89

upvoted a paper 5 months ago

PaLI-3 Vision Language Models: Smaller, Faster, Stronger

Paper • 2310.09199 • Published Oct 13, 2023 • 24

upvoted 4 collections 5 months ago

GIT

GIT (Generative Image-to-text Transformer) is a model useful for vision-language tasks such as image/video captioning and question answering. • 18 items • Updated Jul 11 • 10

UDOP

UDOP is a general multimodal model for document AI • 4 items • Updated Jul 11 • 23

Orca

The Orca family of LMs developed by Microsoft. • 2 items • Updated Jul 11 • 7

SpeechT5

The SpeechT5 framework consists of a shared seq2seq and six modal-specific (speech/text) pre/post-nets that can address a few audio-related tasks. • 8 items • Updated Jul 11 • 22