Update README.md

README.md

@@ -1,10 +1,15 @@
 ---
 license: apache-2.0
+datasets:
+- hkust-nlp/deita-10k-v0
+language:
+- en
 ---
 
 # Model Card for Deita Llama2 13B V1.0 SFT
 
-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).
+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).
 
 ## Model description
 
@@ -37,4 +42,4 @@ The following hyperparameters were used during fine tuning:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 3.0
+- num_epochs: 3.0