Update README.md

README.md

@@ -15,12 +15,13 @@ language:
 <em>[Paper][Code][🤗] (would be released soon)</em>
 </p>
 
-Infinity-Instruct-3M-0613-Mistral-7B is an opensource supervised instruction tuning model without reinforcement learning from human feedback (RLHF). This model is just finetuned on Infinity-Instruct-3M and Infinity-Instruct-0613 (https://huggingface.co/datasets/BAAI/Infinity-Instruct) and beats SOTA language models such as Mixtral 8x7B v0.1, Gemini Pro and GPT3.5 on AlpacaEval 2.0！
+Infinity-Instruct-3M-0613-Mistral-7B is an opensource supervised instruction tuning model without reinforcement learning from human feedback (RLHF). This model is just finetuned on [Infinity-Instruct-3M and Infinity-Instruct-0613](https://huggingface.co/datasets/BAAI/Infinity-Instruct) and it beats SOTA language models such as Mixtral 8x7B v0.1, Gemini Pro and GPT3.5 on AlpacaEval 2.0！
 
 ## **Training Details**
 <p align="center">
 <img src="fig/trainingflow.png">
 </p>
+
 Infinity-Instruct-3M-0613-Mistral-7B is tuned on Million-level instruction dataset [Infinity-Instruct](https://huggingface.co/datasets/BAAI/Infinity-Instruct). First, we apply the foundational dataset Infinity-Instruct-3M to improve the foundational ability (math & code) of Mistral-7B-v0.1, and get the foundational instruct model Infinity-Instruct-3M-Mistral-7B. Then we finetune the Infinity-Instruct-3M-Mistral-7B to get the stronger chat model Infinity-Instruct-3M-0613-Mistral-7B. Here is the training hyperparamers. 
 
 ```bash