stanford_alpaca
stanford_alpaca copied to clipboard
tatsu-lab
Code and documentation to train Stanford's Alpaca models, and generate the data.
så i downloaded and installed the requirements. i noticed utils.py is not written in normal python or at least im getting syntax error. when i run the code i get...
I'm just curious
The idea is to maximize the new tokens, and a first step to adjust to users that change the prompt.txt. #47 I dont know whether the code is correct, please...
As the PR has been merged with the main branch, you can update the instructions. Sorry for formatting the text 😅
I would love to recrate this experiment in German and maybe also Esperanto and it looks easy enough, I bascially just have to adapt [prompt.txt](https://github.com/tatsu-lab/stanford_alpaca/blob/main/prompt.txt) to another language and follow...
Hi, @percyliang , thanks for your sharing! But when I try to regenerate instruction by script `generate_instruction.py`, the cost of time seems so long, even if I reduce the number...
We have released "ChatDoctor: A Medical Chat Model Fine-tuned on LLaMA Model using Medical Domain Knowledge". Please feel free to try our code and training data. https://github.com/Kent0n-Li/ChatDoctor
So that we can communicate with each other faster and easier about the issues we encountered during the setup and training stages. Reason: I noticed many of the issues are...
I tried to train LLaMA 13B with the exact same configuration as 7B (except using deepspeed ZeRO stage 3) and found that the 13B model had an unusually high training...
Traceback (most recent call last): File "/root/train.py", line 231, in train() File "/root/train.py", line 225, in train trainer.train() File "/root/anaconda3/envs/test/lib/python3.10/site-packages/transformers/trainer.py", line 1628, in train return inner_training_loop( File "/root/anaconda3/envs/test/lib/python3.10/site-packages/transformers/trainer.py", line 1715,...
