Impact of Fine-Tuning Data
We trained the TinyLLaMA-1.1B and LLaMA2-7B models using the GitHub dataset. The figures below illustrate the perplexity changes as the training data volume increases from 4 million to 104 million tokens (0.1 billion).
-
Notifications
You must be signed in to change notification settings - Fork 0
JjjFangg/ex
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
No description, website, or topics provided.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published