wassname/alignment-handbook
1
0
Fork 0
mirror of https://github.com/wassname/alignment-handbook.git synced 2026-07-15 11:20:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

🪁 (#129)

Browse Source 
* Add Gemma 7B recipe

* Use Gemma template

* Make it work for dolly lol

* Enable cahce

* Clean up

* DPO to the max

* DPO, DPO, DPO

* Add openhermes

* Add custom configs

* Add kwargs

* Fix config

* Bump deps

* Move old recipes

* Add doc

* Add norte

* Renable cache

* Nuke

* Clean

* Apply suggestions from code review

Co-authored-by: Alvaro Bartolome <alvaro@argilla.io>

* Fix isort

* Update README.md

* Update config_full.yaml

---------

Co-authored-by: Alvaro Bartolome <alvaro@argilla.io>
Co-authored-by: Philipp Schmid <32632186+philschmid@users.noreply.github.com>
This commit is contained in:
lewtun
2024-03-01 17:29:42 +01:00
committed by GitHub
co-authored by Alvaro Bartolome Philipp Schmid
parent d17fd7cd3b
commit ff618a4d13
10 changed files with 150 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/alignment/data.py
+1 -1
View File
@@ -34,7 +34,7 @@ def maybe_insert_system_message(messages, tokenizer):
chat_template = tokenizer.default_chat_template
# confirm the jinja template refers to a system message before inserting
if "system" in chat_template:
if "system" in chat_template or "<|im_start|>" in chat_template:
messages.insert(0, {"role": "system", "content": ""})