ros/LLaMA-Factory
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

improve KTO impl., replace datasets

Browse Source 
Former-commit-id: e56a57ddcf061de6e4acc8679f7dbf0b68364986
This commit is contained in:
hiyouga
2024-05-18 03:44:56 +08:00
parent e4570e28a8
commit 2bff90719b
53 changed files with 448 additions and 330 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
examples/extras/llama_pro/llama3_freeze_sft.yaml
View File

@@ -10,7 +10,7 @@ freeze_trainable_modules: all
use_llama_pro: true
### dataset
dataset: identity,alpaca_gpt4_en
dataset: identity,alpaca_en_demo
template: llama3
cutoff_len: 1024
max_samples: 1000