llama

llama copied to clipboard

UnicodeEncodeError: 'latin-1' codec can't encode character '\u201c' in position 992: ordinal not in range(256)

2

I keep running into this error. I realise that there are certain characters that can't be encoded properly. I did some digging around and tried changing the codec but it...

AIWithShrey

HTTP request sent, awaiting response... 403 Forbidden

9

I accidentally deleted the tokenizer.model when I started download.sh. When I repeated the download, it had already been 403 forbidden, so it could not be downloaded (maybe the download link...

Minami-su

Update README.md

4

Added alternative torchrun through python.

Inserian

Update download.sh

3

Ameero11

Distributed package doesn't have NCCL built in

21

Got the following error when executing: `torchrun --nproc_per_node 1 example.py --ckpt_dir models/7B --tokenizer_path models/tokenizer.model`  additional info: cuda: 11.4 GPU: NVIDIA GeForce 3090 torch 1.12.1 Ubuntu 20.04.2 LTS Anyone knows...

alescire94

torrent seems not to be working

4

im stuck at downloading metadata for 30 mins now

revolverocelot1

Update download.sh

2

Ameero11

This is how to run it on Shadow PC 😎

8

Hello, I got the 7B model to work on a [Shadow PC](https://shadow.tech/) with just **12GB RAM** and **16GB** P5000 GPU 😲. (This is equivalent to about a Nvidia 1080) If...

pauldog

Attempting to run 7B model on two Nvidia 3090s but getting OOM error with one GPU, and can't use both

13

Hello all, I'm trying to use the 7B model on a machine with two Nvidia 3090s, but am running out of Vram. `$ torchrun --nproc_per_node 1 example2.py --ckpt_dir ../llamafiles/7B --tokenizer_path...

wupgop

Download weights from huggingface to help us save bandwith

17

The torrent seed is extremely slow this should definitely help out

Jainam2130