meta-llama

/

Meta-Llama-3-8B-Instruct

like 4.36k

Follow

Meta Llama 73.2k

I found the problem, the model I downloaded was incomplete.
I used git clone https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct without installing git lfs first.
So I ran git lfs install and the git clone https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct and it worked

Also had this issue had to do a few more steps from @sbruhat 's solution

1. I had forgotten to install git-lfs

brew install git-lfs

2. I had to init lfs after installing

git install lfs

4. had to delete my model and then redownload, still had to use git lfs clone instead of git clone

rm -rf Meta-Llama-3-8B-Instruct
git lfs clone https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct      

5. then i had a weird issue that was causing the DL to hang: warning: Multiple 'url.*..insteadof' keys with the same alias: "https://github.com/" so had to go into my .gitconfig and delete multiple git url insteadOf redirects.

6. finally i was able to run the convert script

python llama.cpp/convert-hf-to-gguf.py Meta-Llama-3-8B-Instruct/

I had the same problem with another model from the Hub. Thanks for the solution.
However, shouldn't this be more transparent? In my case I was using a VM and had no git lfs installed. Shouldn't it throw an error or warning when downloading the model?

For my fellow linux users:

curl -s https://packagecloud.io/install/repositories/github/git-lfs/script.deb.sh | sudo bash
sudo apt install git-lfs
git-lfs https://huggingface.co/{model name as always}

All good then.