carlos gemmell

Hi, I am wondering if it is possible to set dependencies for issues such that they could appear after others only if the ones they depend on are completed. If...

Able to load 13B model on 2x3090 24Gb! But not inference... :(

15

I am able to get sensible output by running 7B on 1x24Gb GPU with MP 1. ``` (llama) user@e9242bd8ac2c:~/llama$ CUDA_VISIBLE_DEVICES="0,1" torchrun --nproc_per_node 1 example.py --ckpt_dir checkpoints/7B --tokenizer_path checkpoints/tokenizer.model > initializing...

Hi @sweetpeach I'm trying to reproduce the results from your paper. I cannot see however where to find the trained weights for the model you got the results for. Could...

Reproducing results

1

Hi I am trying to reproduce the numbers stated in the paper for appropriate comparisons to a paper I am writing. But when I run the following command I get...