How to train a little dataset ? What format to use and how to call train_gpt2 executable to generate the LLM ? Then, how to test it ? #683
Unanswered
FiveTechSoft
asked this question in
Q&A
Replies: 1 comment 2 replies
-
|
As far as I understand it, "gpt2_124M.bin" is the base model that we are going to fine tune with tiny_shakespeare if available or with tiny_stories. How are they built ? How to provide ours ? |
Beta Was this translation helpful? Give feedback.
2 replies
-
|
tinyshakespeare.py and tinystories.py are the python files that prepare the bin files |
Beta Was this translation helpful? Give feedback.
-
|
Instead of the provided tiny_shakespeare.txt we can provide our dataset renamed as tiny_shakespeare.txt. Is it correct ? |
Beta Was this translation helpful? Give feedback.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
as the title explains, many thanks
Beta Was this translation helpful? Give feedback.
All reactions