Update README.md

README.md

@@ -1,11 +1,14 @@
 ---
-license: apache-2.0
 inference: false
 ---
 
+**NOTE: New version available**  
+Please check out a newer version of the weights [here](https://huggingface.co/lmsys/vicuna-13b-v1.3).  
+If you still want to use this old version, please see the compatibility and difference between different versions [here](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md).
+
 **NOTE: This "delta model" cannot be used directly.**  
-Users have to apply it on top of the original LLaMA weights to get actual Vicuna weights.  
-See https://github.com/lm-sys/FastChat#vicuna-weights for instructions.
+Users have to apply it on top of the original LLaMA weights to get actual Vicuna weights. See [instructions](https://github.com/lm-sys/FastChat/blob/main/docs/vicuna_weights_version.md#how-to-apply-delta-weights-for-weights-v11-and-v0).
+
 <br>
 <br>
 
@@ -24,14 +27,12 @@ Vicuna was trained between March 2023 and April 2023.
 The Vicuna team with members from UC Berkeley, CMU, Stanford, and UC San Diego.
 
 **Paper or resources for more information:**
-https://vicuna.lmsys.org/
-
-**License:**
-Apache License 2.0
+https://lmsys.org/blog/2023-03-30-vicuna/
 
 **Where to send questions or comments about the model:**
 https://github.com/lm-sys/FastChat/issues
 
+
 ## Intended use
 **Primary intended uses:**
 The primary use of Vicuna is research on large language models and chatbots.
@@ -43,8 +44,5 @@ The primary intended users of the model are researchers and hobbyists in natural
 70K conversations collected from ShareGPT.com.
 
 ## Evaluation dataset
-A preliminary evaluation of the model quality is conducted by creating a set of 80 diverse questions and utilizing GPT-4 to judge the model outputs. See https://vicuna.lmsys.org/ for more details.
-
-## Major updates of weights v1.1
-- Refactor the tokenization and separator. In Vicuna v1.1, the separator has been changed from `"###"` to the EOS token `"</s>"`. This change makes it easier to determine the generation stop criteria and enables better compatibility with other libraries.
-- Fix the supervised fine-tuning loss computation for better model quality.
+A preliminary evaluation of the model quality is conducted by creating a set of 80 diverse questions and utilizing GPT-4 to judge the model outputs.
+See https://lmsys.org/blog/2023-03-30-vicuna/ for more details.