From e0ffc861fae5ac8b40ce973f822d03db02929d36 Mon Sep 17 00:00:00 2001 From: Kevin Kwok Date: Tue, 21 Mar 2023 08:34:49 -0700 Subject: [PATCH] Update IPFS links to quantized alpaca with new tokenizer format (#352) --- README.md | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index c7e5d33c7..349e82c56 100644 --- a/README.md +++ b/README.md @@ -192,17 +192,16 @@ First, download the `ggml` Alpaca model into the `./models` folder: ``` # use one of these -# NOTE: these are copied from the alpaca.cpp repo - not sure how long these will work # TODO: add a script to simplify the download -curl -o ggml-alpaca-7b-q4.bin -C - https://gateway.estuary.tech/gw/ipfs/QmQ1bf2BTnYxq73MFJWu1B7bQ2UD6qG7D7YDCxhTndVkPC -curl -o ggml-alpaca-7b-q4.bin -C - https://ipfs.io/ipfs/QmQ1bf2BTnYxq73MFJWu1B7bQ2UD6qG7D7YDCxhTndVkPC -curl -o ggml-alpaca-7b-q4.bin -C - https://cloudflare-ipfs.com/ipfs/QmQ1bf2BTnYxq73MFJWu1B7bQ2UD6qG7D7YDCxhTndVkPC +curl -o ggml2-alpaca-7b-q4.bin -C - https://gateway.estuary.tech/gw/ipfs/QmUp1UGeQFDqJKvtjbSYPBiZZKRjLp8shVP9hT8ZB9Ynv1 +curl -o ggml2-alpaca-7b-q4.bin -C - https://ipfs.io/ipfs/QmUp1UGeQFDqJKvtjbSYPBiZZKRjLp8shVP9hT8ZB9Ynv1 +curl -o ggml2-alpaca-7b-q4.bin -C - https://cloudflare-ipfs.com/ipfs/QmUp1UGeQFDqJKvtjbSYPBiZZKRjLp8shVP9hT8ZB9Ynv1 ``` Now run the `main` tool like this: ``` -./main -m ./models/ggml-alpaca-7b-q4.bin --color -f ./prompts/alpaca.txt -ins +./main -m ./models/ggml2-alpaca-7b-q4.bin --color -f ./prompts/alpaca.txt -ins ``` Sample run: