Update README.md

Fix syntax errors

README.md

@@ -4,22 +4,25 @@ license_name: doge
 license_link: LICENSE
 datasets:
 - michaelwzhu/ChatMed_Consult_Dataset
-metrics:
-- code_eval
 base_model:
 - JingzeShi/Doge-197M
 pipeline_tag: question-answering
 library_name: transformers
+language:
+- en
+- zh
+tags:
+- medical
 ---
 
-## **Doge 197M for Medical QA**
+## **Doge-197M for MedicalQA**
 
 This model is a fine-tuned version of [JingzeShi/Doge-197M](https://huggingface.co/JingzeShi/Doge-197M).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 Doge is an ongoing research project where we aim to train a series of small language models to further explore whether the Transformer framework allows for more complex feedforward network structures, enabling the model to have fewer cache states and larger knowledge capacity.
 
-In addition, Doge uses Inner Function Attention with Dynamic Mask as sequence transformation and Cross Domain Mixture of Experts as state transformation. This model is trained by Jingze Shi, it only allows text input and text generation, for detailed algorithm and model architecture, please refer to [Wonderful Matrices](https://arxiv.org/abs/2407.16958), the ongoing research repository is [Doge](https://github.com/LoserCheems/Doge).
+In addition, Doge uses Dynamic Mask Attention as sequence transformation and can use Multi-Layer Perceptron or Cross Domain Mixture of Experts as state transformation. Dynamic Mask Attention allows the Transformer to use self-attention during training and state space during inference, and Cross Domain Mixture of Experts can directly inherit the weights of Multi-Layer Perceptron for further training. This model is trained by Jingze Shi, it only allows text input and text generation, for detailed algorithm and model architecture, please refer to [Wonderful Matrices](https://arxiv.org/abs/2412.11834), the ongoing research repository is [Wonderful Matrices](https://github.com/LoserCheems/WonderfulMatrices).
 
 
 ## Uses
@@ -74,11 +77,11 @@ In addition, Doge uses Inner Function Attention with Dynamic Mask as sequence tr
 ... )
 ```
 
-**Fine-tue Task**:
+**Fine-tune Task**:
 - We selected an open-source Chinese medical question answering dataset for fine-tuning.
 
 
-**Fine-tue Environment**:
+**Fine-tune Environment**:
 - Image: nvcr.io/nvidia/pytorch:24.10-py3
 - Hardware: 1x NVIDIA RTX 3090
 - Software: Transformers
@@ -92,12 +95,12 @@ In addition, Doge uses Inner Function Attention with Dynamic Mask as sequence tr
 
 ```bibtex
 @misc{shi2024wonderfulmatrices,
-      title={Wonderful Matrices: More Efficient and Effective Architecture for Language Modeling Tasks}, 
-      author={Jingze Shi and Bingheng Wu and Lu He and Luchang Jiang},
+      title={Wonderful Matrices: Combining for a More Efficient and Effective Foundation Model Architecture}, 
+      author={Jingze Shi and Bingheng Wu},
       year={2024},
-      eprint={2407.16958},
+      eprint={2412.11834},
       archivePrefix={arXiv},
       primaryClass={cs.LG},
-      url={https://arxiv.org/abs/2407.16958}, 
+      url={https://arxiv.org/abs/2412.11834}, 
 }
 ```