wassname/alignment-handbook
1
0
Fork 0
mirror of https://github.com/wassname/alignment-handbook.git synced 2026-08-20 12:10:13 +08:00
Code Issues Packages Projects Releases Wiki Activity

DPO/IPO/KTO ablations (#104)

Browse Source 
* adds configs and readme

* cleaning config files

* fix typos and removes things from config

* updates text to use comparisons rather ablations

* fix readme and adds launch script

* fix launch script, adds blogpost link

* bump release version, added missing dep, fixes configs

* updates main readme file
This commit is contained in:
Edward Beeching
2024-01-18 14:55:00 +01:00
committed by GitHub
parent c74ed11171
commit cbcb3f60fb
6 changed files with 157 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files
README.md
+1 -1
View File
@@ -19,7 +19,7 @@ However, we know from the [InstructGPT](https://huggingface.co/papers/2203.02155
The Alignment Handbook aims to fill that gap by providing the community with a series of robust training recipes that span the whole pipeline.
## News 🗞️
* **January 18, 2024:** We release a suite of Evalutions of DPO vs KTO vs IPO, see the [recipe](recipes/pref_align_scan/README.md) and the [blogpost](https://huggingface.co/blog/pref-tuning)
* **November 10, 2023:** We release all the training code to replicate Zephyr-7b-β 🪁! We also release [No Robots](https://huggingface.co/datasets/HuggingFaceH4/no_robots), a brand new dataset of 10,000 instructions and demonstrations written entirely by skilled human annotators.
## Links 🔗