Update README.md

README.md

@@ -11,6 +11,8 @@ base_model: meta-llama/Llama-2-13b-hf
 
 # Model Card for Deita Llama2 13B V1.0 SFT
 
+[GitHub](https://github.com/hkust-nlp/deita) | [Paper](https://arxiv.org/abs/2312.15685)
+
 Deita is an open-sourced project designed to facilitate **Automatic Data Selection** for instruction tuning in Large Language Models (LLMs). 
 Deita Llama2 13B V1.0 SFT is a fine-tuned version of Llama 2 that was trained on 10k automatically selected lightweight, high-quality alignment SFT data: [Deita 10K V0](https://huggingface.co/datasets/hkust-nlp/deita-10k-v0).
 
@@ -30,8 +32,7 @@ Deita Llama2 13B V1.0 SFT is a fine-tuned version of Llama 2 that was trained on
 ## Performance
 
 
-<details>
-  <summary>See full evaluations</summary>
+
 
 | Model                                          | Align     | Data Size  | MT-Bench | AlpacaEval(%) | OpenLLM (Avg.) |
 |------------------------------------------------|-----------|------------|----------|---------------|----------------|
@@ -66,7 +67,7 @@ Deita Llama2 13B V1.0 SFT is a fine-tuned version of Llama 2 that was trained on
 | DEITA-7B-v1.0             | SFT + DPO | 6K SFT + 10K DPO   | 7.55     | 90.06         | 69.86          |
 
 
-</details>
+