Browsing: Tools

This blog post introduces a method to train static embedding models that run 100x to 400x faster on CPU than…

Since June 2024, we have evaluated more than 3,000 models on the Open LLM Leaderboard, a worldwide ranking of open…

TL;DR: We present vdr-2b-multi-v1, the best multilingual embedding model for visual document retrieval. We also release its English-only twin vdr-2b-v1…

Finding the best LLM models for finance use cases The growing complexity of financial language models (LLMs) necessitates evaluations that…

Company Published 22 December 2023 Authors By Jeff Dean, Chief Scientist, Google DeepMind & Google Research, Demis Hassabis, CEO, Google…

After more than a year of development, we’re excited to announce the release of 🤗 Transformers.js v3! Highlights include: Installation…

Research Published 14 December 2023 Authors Alhussein Fawzi and Bernardino Romera Paredes By searching for “functions” written in computer code,…

We introduce Bamba-9B, an inference-efficient Hybrid Mamba2 model trained by IBM, Princeton, CMU, and UIUC on completely open data. At…

You must be familiar with this message 🤬: RuntimeError: CUDA out of memory. Tried to allocate 20.00 MiB (GPU 0;…

Generating text with language models often involves selecting the next token based on a distribution of probabilities. A straightforward approach…