From 56de950af8a48c7cae221581e2e3e2c342b2ad82 Mon Sep 17 00:00:00 2001 From: Christopher King Date: Thu, 2 Mar 2023 18:05:20 -0500 Subject: [PATCH 1/3] Save bandwidth by using a torrent to distribute more efficiently --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 6627c0b7b..1789071dd 100755 --- a/README.md +++ b/README.md @@ -1,7 +1,7 @@ # LLaMA This repository is intended as a minimal, hackable and readable example to load [LLaMA](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/) ([arXiv](https://arxiv.org/abs/2302.13971v1)) models and run inference. -In order to download the checkpoints and tokenizer, fill this [google form](https://forms.gle/jk851eBVbX1m5TAv5) +In order to download the checkpoints and tokenizer, fill this [google form](https://forms.gle/jk851eBVbX1m5TAv5) or if it you want to save our bandwidth use this bit torrent link: [magnet:?xt=urn:btih:ZXXDAUWYLRUXXBHUYEMS6Q5CE5WA3LVA&dn=LLaMA](magnet:?xt=urn:btih:ZXXDAUWYLRUXXBHUYEMS6Q5CE5WA3LVA&dn=LLaMA) ### Setup In a conda env with pytorch / cuda available, run From 7ab654b73f2c859f7a298130cec1db2f7b9915d4 Mon Sep 17 00:00:00 2001 From: Christopher King Date: Thu, 2 Mar 2023 22:20:47 -0500 Subject: [PATCH 2/3] spelling in README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 1789071dd..3ec97645c 100755 --- a/README.md +++ b/README.md @@ -1,7 +1,7 @@ # LLaMA This repository is intended as a minimal, hackable and readable example to load [LLaMA](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/) ([arXiv](https://arxiv.org/abs/2302.13971v1)) models and run inference. -In order to download the checkpoints and tokenizer, fill this [google form](https://forms.gle/jk851eBVbX1m5TAv5) or if it you want to save our bandwidth use this bit torrent link: [magnet:?xt=urn:btih:ZXXDAUWYLRUXXBHUYEMS6Q5CE5WA3LVA&dn=LLaMA](magnet:?xt=urn:btih:ZXXDAUWYLRUXXBHUYEMS6Q5CE5WA3LVA&dn=LLaMA) +In order to download the checkpoints and tokenizer, fill this [google form](https://forms.gle/jk851eBVbX1m5TAv5) or if you want to save our bandwidth use this bit torrent link: [magnet:?xt=urn:btih:ZXXDAUWYLRUXXBHUYEMS6Q5CE5WA3LVA&dn=LLaMA](magnet:?xt=urn:btih:ZXXDAUWYLRUXXBHUYEMS6Q5CE5WA3LVA&dn=LLaMA) ### Setup In a conda env with pytorch / cuda available, run From 016a53608c5eae1021e171b9c4f06a9783fc14c0 Mon Sep 17 00:00:00 2001 From: Christopher King Date: Fri, 3 Mar 2023 11:43:24 -0500 Subject: [PATCH 3/3] Spelling and punctuation --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 3ec97645c..8c2012bc5 100755 --- a/README.md +++ b/README.md @@ -1,7 +1,7 @@ # LLaMA This repository is intended as a minimal, hackable and readable example to load [LLaMA](https://ai.facebook.com/blog/large-language-model-llama-meta-ai/) ([arXiv](https://arxiv.org/abs/2302.13971v1)) models and run inference. -In order to download the checkpoints and tokenizer, fill this [google form](https://forms.gle/jk851eBVbX1m5TAv5) or if you want to save our bandwidth use this bit torrent link: [magnet:?xt=urn:btih:ZXXDAUWYLRUXXBHUYEMS6Q5CE5WA3LVA&dn=LLaMA](magnet:?xt=urn:btih:ZXXDAUWYLRUXXBHUYEMS6Q5CE5WA3LVA&dn=LLaMA) +In order to download the checkpoints and tokenizer, fill this [google form](https://forms.gle/jk851eBVbX1m5TAv5) or if you want to save our bandwidth use this BitTorrent link: "[magnet:?xt=urn:btih:ZXXDAUWYLRUXXBHUYEMS6Q5CE5WA3LVA&dn=LLaMA](magnet:?xt=urn:btih:ZXXDAUWYLRUXXBHUYEMS6Q5CE5WA3LVA&dn=LLaMA)". ### Setup In a conda env with pytorch / cuda available, run