stanford_alpaca
stanford_alpaca copied to clipboard
tatsu-lab
Code and documentation to train Stanford's Alpaca models, and generate the data.
I encountered the CUDA OOM on a single core A100 80G using your training code? Can i fix this by changing anything?
Dear @all Due to OOM as mentioned in previous issues, who can finetune LLaMA using bitsandbytes for an 8-bit setting on a single 3090? If yes, please share your experiments...
Environment: 6xA6000 48GB with Ubuntu 22.04, Pytorch 1.13.0 I ran into a generation problem after following your instruction to convert LLaMA-7B weight using your attached script. I simply used the...
As the name implies, can you share the training log?
I am currently training the model, and I am hoping to compare it with others. I am only using only 2 A100-80G. Here is my wanb log: https://wandb.ai/charliezjw/huggingface/runs/hil1q6lt
Hi, What is the steps to train it with this specific Bible content? Example: https://raw.githubusercontent.com/tushortz/variety-bible-text/master/bibles/kjv.txt Can you show me the steps to train it? And the other question is: The...
LLaMA-13B (HF) Fails with OOM on a dual A100-80GB. For those who managed to run alpaca against the 13b model, what specs and torchun setting did you use? `torchrun --nproc_per_node=2...
1. write the new requiremens for train only: `requires.train.txt` 2. split the old utils.py into utils.py and openai_utils.py 3. apply changes on generate_instruction.py and README
