One CPU

 I have solved it with a cpu installation by installing this : https://github.com/krychu/llama instead of https://github.com/facebookresearch/llama

Complete process to install :

  1. download the original version of Llama from : https://github.com/facebookresearch/llama and extract it to a llama-main folder
  2. download th cpu version from : https://github.com/krychu/llama and extract it and replace files in the llama-main folder
  3. run the download.sh script in a terminal, passing the URL provided when prompted to start the download
  4. go to the llama-main folder
  5. cretate an Python3 env : python3 -m venv env and activate it : source env/bin/activate
  6. install the cpu version of pytorch : python3 -m pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu #pour la version cpu
  7. install dependencies off llama : python3 -m pip install -e .
  8. run if you have downloaded llama-2-7b :
torchrun --nproc_per_node 1 example_text_completion.py \
    --ckpt_dir llama-2-7b/ \
    --tokenizer_path tokenizer.model \
    --max_seq_len 128 --max_batch_size 1 #(instead of 4)

Comments

Popular posts from this blog

Flutter for Single-Page Scrollable Websites with Navigator 2.0

A Data Science Portfolio is More Valuable than a Resume

Better File Storage in Oracle Cloud