From b8f53ae80ca065604be957a76316184b3fc3f0c0 Mon Sep 17 00:00:00 2001
From: PhilipMay <philip@may.la>
Date: Fri, 29 Dec 2023 15:09:47 +0100
Subject: [PATCH] llm

---
 source/machine-learning/llm.md | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/source/machine-learning/llm.md b/source/machine-learning/llm.md
index 9d05473..6107792 100644
--- a/source/machine-learning/llm.md
+++ b/source/machine-learning/llm.md
@@ -1,7 +1,16 @@
 # LLM
 
 ## Base Knowledge
+
 - 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>
   - <https://huggingface.co/blog/dpo-trl>
+
+## Specific Models
+
+- Argilla Notux
+  - based on Mixtral
+  - HF Model: <https://huggingface.co/argilla/notux-8x7b-v1>
+  - Dataset: <https://huggingface.co/datasets/argilla/ultrafeedback-binarized-preferences-cleaned>
+  - Code: <https://github.com/argilla-io/notus>