llm

PhilipMay · Dec 29, 2023 · be22e35 · be22e35
1 parent b8f53ae
commit be22e35
Showing 1 changed file with 4 additions and 0 deletions.
diff --git a/source/machine-learning/llm.md b/source/machine-learning/llm.md
@@ -2,6 +2,10 @@
 
 ## Base Knowledge
 
+- [HF: The Alignment Handbook](https://github.com/huggingface/alignment-handbook)
+
+## Specific Techniques
+
 - Direct Preference Optimization (DPO)
   - Paper: <https://arxiv.org/abs/2305.18290>
   - <https://plainenglish.io/community/direct-preference-optimization-dpo-a-simplified-approach-to-fine-tuning-large-language-models>