반응형
updates : 2024.04.23
contents : Run the open source code of Llama3 without using huggingface but original model.
Go to the Llama official website and request access of Llama3
https://llama.meta.com/
click "Download models"
Fill the form and accept all and continue.
Then, we can get URL code (not using it as URL, it is the key for downloading tokens of the model).
Let's go to Meta's github.
Run Llama3.
https://github.com/meta-llama/llama3
# CLI Command (terminal)
git clone https://github.com/meta-llama/llama3
cd llama3
pip install -e .
bash download.sh
# put the URL code after the comment said put on it!
# after download, run it
# example
torchrun --nproc_per_node 1 example_chat_completion.py \
--ckpt_dir llama-2-7b-chat/ \
--tokenizer_path tokenizer.model \
--max_seq_len 512 --max_batch_size 6
반응형
'Programming > AI, LLM' 카테고리의 다른 글
[Llama] 라마3 다운로드 및 실행 방법 (Kor) (0) | 2024.04.27 |
---|