Welcome to /m/localllama! Links & FAQ
Run LLaMa locally...
Mistral 7B Released Under Apache 2.0 (mistral.ai)
From their website...
Free Open-Source AI LLM Guide
cross-posted from: lemmy.world/post/2219010...
Introducing Llama 2 - Meta's Next-Generation Commercially Viable Open-Source AI & LLM
cross-posted from: lemmy.world/post/1750098...
Introducing OpenLLaMA: An Open-Source Reproduction of Meta's LLaMA
cross-posted from: lemmy.world/post/1305651...
Long Sequence Modeling with XGen: A 7B LLM Trained on 8K Input Sequence Length (blog.salesforceairesearch.com)
TLDR We trained a series of 7B LLMs named XGen-7B with standard dense attention on up to 8K sequence length for up to 1.5T tokens. We also fine tune the models on public-domain instructional data. The main take-aways are: * On standard NLP benchmarks, XGen achieves comparable or better results
EXLlama support added to oobabooga-text-generation-webui (github.com)
Baichuan 7B reaches top of LLM leaderboard for it's size? (github.com)
baichuan-7B is an open-source large-scale pre-trained model developed by Baichuan Intelligent Technology. Based on the Transformer architecture, it is a model with 7 billion parameters trained on approximately 1.2 trillion tokens. It supports both Chinese and English, with a context window length of 4096. It achieves the best...
open_llama_13b trained on 1T tokens now available ! (huggingface.co)
Exciting stuff!
SlimPajama: A 627B token cleaned and deduplicated version of RedPajama (www.cerebras.net)
Sounds like Cerebras will be training a model soon based on this dataset, will likely rival OpenLLaMa and RedPajamas models – thoughts??
Vicuna v1.5 Has Been Released!
Click Here to be Taken to the Megathread!...
Llama-2 FOSAI & LLM Roundup Series! (Summer 2023 Edition)
cross-posted from: lemmy.world/post/1894070...