Skip to content

Conversation

StochasticRomanAgeev
Copy link
Contributor

No description provided.

Added INT4 finetuning description to README.md
@StochasticRomanAgeev StochasticRomanAgeev changed the base branch from main to dev April 6, 2023 12:50
Added separate README.md to int4 finetuning folder and changed links
Added typo fixes to README.md

With INT4 fine-tuning, xTuring offers several benefits:

1. Reduced Memory Footprint: The INT4 precision reduces the memory requirements to just ~5GB of VRAM, allowing you to fine-tune LLMs on hardware with lower memory capacities.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
1. Reduced Memory Footprint: The INT4 precision reduces the memory requirements to just ~5GB of VRAM, allowing you to fine-tune LLMs on hardware with lower memory capacities.
1. Reduced memory gootprint: The INT4 precision reduces the memory requirements to just ~5GB of VRAM, allowing you to fine-tune LLMs on hardware with lower memory capacities.


With INT4 fine-tuning, xTuring offers several benefits:

1. Reduced Memory Footprint: The INT4 precision reduces the memory requirements to just ~5GB of VRAM, allowing you to fine-tune LLMs on hardware with lower memory capacities.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Is it 5GB or 6GB? I see both numbers mentioned.

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I've asked and it is closer to 6GB, will change

Added information checks and typo fixes for README.md
Added information about VRAM to main README.md
Added licence information to main README.md
Fixed licence line in README.md
@sarthaklangde sarthaklangde merged commit 26669eb into dev Apr 6, 2023
glennko pushed a commit that referenced this pull request Sep 28, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants