RedPajama replicates LLaMA dataset to build open source, state-of-the-art LLMs

RedPajama, which creates fully open-source large language models, has released a 1.2 trillion token dataset following the LLaMA recipe.

2308.14149] Examining User-Friendly and Open-Sourced Large GPT Models: A Survey on Language, Multimodal, and Scientific GPT Models

今日気になったAI系のニュース【23/4/24】｜shanda

🎮 Replica News

Beyond LLaMA: The Power of Open LLMs, by Cameron R. Wolfe, Ph.D.

Zephyr-7B : HuggingFace's Hyper-Optimized LLM Built on Top of Mistral 7B

static.premai.io/book/models_alpaca-finetuning.png

Ahead of AI #8: The Latest Open Source LLMs and Datasets

GitHub - dsdanielpark/open-llm-datasets: Repository for organizing datasets and papers used in Open LLM.

François Lafond (@FLCompRes) / X

Llama 2: The New Open LLM SOTA (ft. Nathan Lambert, Matt Bornstein, Anton Troynikov, Russell Kaplan, Whole Mars Catalog et al.)

Radical Reads: Ten charts explaining AI today - Radical Ventures

The data that trains AI is under the spotlight — and even I'm weirded out

Best Open Source LLMs of 2024 — Klu

Meta Llama 2: Statistics on Meta AI and Microsoft's Open Source LLM –