ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update README.md

Browse source
This commit is contained in:
Daniel Han 2023-12-01 14:38:03 +11:00 • committed by GitHub
commit d9743a3089
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 2 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

3
README.md
View file

@ -6,7 +6,8 @@
* All kernels written in OpenAI's Triton language.
* 0% loss in accuracy.
* No change of hardware necessary. Supports Tesla T4, RTX 20, 30, 40 series, A100, H100s
* Flash Attention
* Flash Attention support
* Supports 4bit and 16bit LoRA finetuning.
* Train Slim Orca **fully locally in 260 hours from 1301 hours (5x faster).**
* Check out [Unsloth Pro and Max](https://unsloth.ai/) codepaths for **30x faster training**!