Falcon-H1: A Family of Hybrid-Head Models Redefining Efficiency and Performance (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: Falcon-H1: A Family of Hybrid-Head Models Redefining Efficiency and Performance

First screen, captured 1 year ago.

Looks similar

Screenshot of arxiv.org: Zebra-Llama – Towards efficient hybrid models

Zebra-Llama – Towards efficient hybrid models (arxiv.org)

104 points by mirrir 10 months ago | 52 comments

Screenshot of arxiv.org: Hierarchical Autoregressive Modeling for Memory-Efficient Language Generation

Hierarchical Autoregressive Modeling for Memory-Efficient Language Generation (arxiv.org)

40 points by PaulHoule 9 months ago | 1 comments

Screenshot of arxiv.org: Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing

Making LLMs Cheaper and Better via Performance-Efficiency Optimized Routing (arxiv.org)

118 points by omarsar 1 year ago | 22 comments

Screenshot of arxiv.org: Jamba: A Hybrid Transformer-Mamba Language Model

Jamba: A Hybrid Transformer-Mamba Language Model (arxiv.org)

58 points by eitanturok 2 years ago | 6 comments

Screenshot of arxiv.org: Inferring the Phylogeny of Large Language Models

Inferring the Phylogeny of Large Language Models (arxiv.org)

62 points by weinzierl 1 year ago | 5 comments

Screenshot of arxiv.org: Chameleon: Meta’s New Multi-Modal LLM

Chameleon: Meta’s New Multi-Modal LLM (arxiv.org)

272 points by gabrielbirnbaum 2 years ago | 39 comments