Closed
Description
Hi, I have encounter the above problem when running the alpaca model. I download the model from the link "https://gateway.estuary.tech/gw/ipfs/QmQ1bf2BTnYxq73MFJWu1B7bQ2UD6qG7D7YDCxhTndVkPC" which is one of the three options from the readme. Should I download the model from somewhere else?
Metadata
Metadata
Assignees
Type
Projects
Milestone
Relationships
Development
No branches or pull requests
Activity
nsarrazin commentedon Mar 20, 2023
You need to convert your weights using the script provided here.
You will also need the tokenizer from here.
Then you can run
python convert.py your/models/folder/ path/to/tokenizer.model
And the outputted
*.bin.tmp
files are the new models.nsarrazin commentedon Mar 20, 2023
I have uploaded the converted weights here for the 7B alpaca model. I also have the 13B version but not sure where to upload it, it's a bit big.
TonyHanzhiSU commentedon Mar 20, 2023
thank you so much ! It has fixed my problem and the model is up and running.
Zer0- commentedon Mar 20, 2023
Can you just make a torrent of it for now?
tkafka commentedon Mar 23, 2023
@nsarrazin You should be able to publish them to https://huggingface.co, right?
l29ah commentedon Mar 24, 2023
Downloaded one from https://huggingface.co/Pi3141/alpaca-13B-ggml/ and it's "too old" as well.
l29ah commentedon Mar 24, 2023
magnet:?xt=urn:btih:e5322ab4676e24632a907fd9846234bb40265c4f&dn=ggml-q4 should have the proper models.