Update README.md

README.md

@@ -12,9 +12,22 @@ model-index:
   results: []
 ---
 
-Paper: https://huggingface.co/papers/2410.01691.
+# FactAlign-LLaMA-3-8B
+This model is aligned with our **FactAlign** framework for improved long-form factuality, from [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct).
+
+For more information, please refer to our paper: [FactAlign: Long-form Factuality Alignment of Large Language Models](https://huggingface.co/papers/2410.01691).
+
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
 
-# kto-mix-14k-lf-response-llama3-f1_100_0.8-fg0.5-fgudw4.0-kto-fg
 
 This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the trl-lib/kto-mix-14k and the chaoweihuang/lf-response-llama3-f1_100_0.8-fg0.5 datasets.
 It achieves the following results on the evaluation set:
@@ -38,17 +51,6 @@ It achieves the following results on the evaluation set:
 - Fg Kl: nan
 - Fg Loss: 0.7625
 
-## Model description
-
-More information needed
-
-## Intended uses & limitations
-
-More information needed
-
-## Training and evaluation data
-
-More information needed
 
 ## Training procedure