Update README.md

README.md

@@ -25,6 +25,16 @@ tags:
 
 We present AmberChat, an instruction following model finetuned from [LLM360/Amber](https://huggingface.co/LLM360/Amber).
 
+# Evaluation
+
+| Model                                                | MT-Bench                                                  | 
+|------------------------------------------------------|------------------------------------------------------------|
+| **LLM360/AmberChat** | **5.428125** |
+| [LLM360/Amber](https://huggingface.co/LLM360/Amber) | 2.48750 |
+| [Falcon-40B-Instruct](https://huggingface.co/tiiuae/falcon-40b-instruct) | 5.17 |
+| [MPT-7B-Chat](https://huggingface.co/mosaicml/mpt-7b-chat) | 5.42 |
+| [Nous-Hermes-13B](https://huggingface.co/NousResearch/Nous-Hermes-13b) | 5.51 |
+
 ## Model Description
 
 - **Model type:** Language model with the same architecture as LLaMA-7B
@@ -92,15 +102,6 @@ python3 -m fastchat.serve.cli --model-path LLM360/AmberChat
 | model_max_length | 2048     |
 
 
-# Evaluation
-
-| Model                                                | MT-Bench                                                  | 
-|------------------------------------------------------|------------------------------------------------------------|
-| **LLM360/AmberChat** | **5.428125** |
-| [LLM360/Amber](https://huggingface.co/LLM360/Amber) | 2.48750 |
-| [Falcon-40B-Instruct](https://huggingface.co/tiiuae/falcon-40b-instruct) | 5.17 |
-| [MPT-7B-Chat](https://huggingface.co/mosaicml/mpt-7b-chat) | 5.42 |
-| [Nous-Hermes-13B](https://huggingface.co/NousResearch/Nous-Hermes-13b) | 5.51 |
 
 # Using Quantized Models with Ollama