llama-dl icon indicating copy to clipboard operation
llama-dl copied to clipboard

High-speed download of LLaMA, Facebook's 65B parameter GPT model

Results 23 llama-dl issues
Sort by recently updated
recently updated
newest added

Anyone have a list of checksums for the original models?

bash won't suffice since script does rely on 'wget', more clean way implemented for users to run on mac.

Use aria2c to for parallel downloading and continuation

Hi, could someone shed some light on how this model can be loaded and used for inference? I know this is early and everybody might be a little vague on...

All of the models are on huggingface already. https://huggingface.co/decapoda-research there's even an open, working pr to add support to the transformers lib.

Translated the download script to python.

After downloading this, how can I use it Like how can I ask it a question I am a noob 🫠

![image](https://user-images.githubusercontent.com/12760587/224312994-eddc3b47-8d9b-4852-9207-8091f0e6a5ec.png) I didn't install md5sum, I got error above.

Added -c switch to large file downloads with wget

from your readme: >I doubt it. This is using the download link that was leaked in the original torrent. (i.e. the leaker accidentally leaked their own unique download link that...