INX-TEXT
/

Bailong-orpo-7B

@@ -22,7 +22,7 @@ This model card contains the information and the results of our released Bailong
 - **Bailong-instruct 7B:** Bailong-instruct 7B is the fine-tuned version of Bailong 7B optimized for multi-turn dialogue use cases. Similar to secondary pretraining stage, we use QLoRA to fine-tune the model. To facilitate the development and communication within the research community in Traditional Chinese NLP, we decide to release this model on Hugging Face.
 - **Bailong-bench:** Most existing language models claiming to support Traditional Chinese are adapted from continuously pre-trained open-source models, primarily trained on English data. In certain cases, models fine-tuned with instructions using this approach may respond to Traditional Chinese instructions in English and vice versa. This could pose a significant problem when deploying the model for real-world applications. Consequently, it is essential to have a benchmark dataset specifically designed to assess a model's proficiency in following both English and Traditional Chinese instructions. To address this issue, we propose Bailong-bench, a benchmark dataset crafted not only to evaluate the model's performance in various real-world application scenarios but also to assess its ability to maintain language consistency.
 - **Technical report:** In our [technical report](https://arxiv.org/abs/2404.00862), we document the model training process and the details regarding the sources of training data.
-- **Bailong-orpo 7B:** Leveraging monolithic odds ratio preference optimization
 algorithm, [ORPO](https://arxiv.org/abs/2403.07691), we further fine-tune Bailong-instruct 7B with 180k preference pair data to derive Bailong-orpo 7B. We also provide f16 GGUF version of Bailong-orpo 7B for efficient inference and storage purposes.
 ## Model information

 - **Bailong-instruct 7B:** Bailong-instruct 7B is the fine-tuned version of Bailong 7B optimized for multi-turn dialogue use cases. Similar to secondary pretraining stage, we use QLoRA to fine-tune the model. To facilitate the development and communication within the research community in Traditional Chinese NLP, we decide to release this model on Hugging Face.
 - **Bailong-bench:** Most existing language models claiming to support Traditional Chinese are adapted from continuously pre-trained open-source models, primarily trained on English data. In certain cases, models fine-tuned with instructions using this approach may respond to Traditional Chinese instructions in English and vice versa. This could pose a significant problem when deploying the model for real-world applications. Consequently, it is essential to have a benchmark dataset specifically designed to assess a model's proficiency in following both English and Traditional Chinese instructions. To address this issue, we propose Bailong-bench, a benchmark dataset crafted not only to evaluate the model's performance in various real-world application scenarios but also to assess its ability to maintain language consistency.
 - **Technical report:** In our [technical report](https://arxiv.org/abs/2404.00862), we document the model training process and the details regarding the sources of training data.
+- **Bailong-orpo 7B:** By leveraging monolithic odds ratio preference optimization
 algorithm, [ORPO](https://arxiv.org/abs/2403.07691), we further fine-tune Bailong-instruct 7B with 180k preference pair data to derive Bailong-orpo 7B. We also provide f16 GGUF version of Bailong-orpo 7B for efficient inference and storage purposes.
 ## Model information