Update README.md

README.md

@@ -5,22 +5,24 @@ pipeline_tag: text-generation
 # Model Card for Breeze-7B-Instruct-v0.1
 
 
-Breeze-7B is a language model that builds upon the foundation of Mistral-7B, specifically 
-enhanced for Traditional Chinese. This model introduces an expanded vocabulary with additional 30,000 Traditional Chinese tokens, 
-significantly improving its performance in understanding and generating Traditional Chinese text. As a result, 
-the model is twice as efficient in the encoding and decoding of Traditional Chinese compared to Mistral-7B.
+Breeze-7B is a language model that builds upon the foundation of Mistral-7B, specifically enhanced for Traditional Chinese. 
 
+[Breeze-7B-Base-v0.1](https://huggingface.co/MediaTek-Research/Breeze-7B-Base-v0.1) introduces an expanded vocabulary with additional 30,000 Traditional Chinese tokens and 
+is pre-trained on a substantial dataset of 250GB of Traditional Chinese content. 
+With the expanded vocabulary, the base model operates at twice the inference speed for Traditional Chinese characters compared to Mistral-7B. [See Inference Performance.]
+This achievement marks a significant milestone as it is the first instance of vocabulary expansion in a model tailored for Traditional Chinese.
 
-
-[Breeze-7B-Instruct-v0.1](https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-v0.1) derives from the base model [Breeze-7B-Base-v0.1](https://huggingface.co/MediaTek-Research/Breeze-7B-Base-v0.1), which has been continually 
-pre-trained on a substantial dataset of 250GB of Traditional Chinese content. Additionally, it has undergone supervised fine-tuning with over 1 million instances to 
-sharpen its capabilities. Breeze-7B-Instruct-v0.1 demonstrates impressive performance in benchmarks for both English and Traditional Chinese, surpassing the results of 
+[Breeze-7B-Instruct-v0.1](https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-v0.1) derives from the base model [Breeze-7B-Base-v0.1](https://huggingface.co/MediaTek-Research/Breeze-7B-Base-v0.1) 
+and has undergone supervised fine-tuning with over 1 million instances to 
+sharpen its capabilities. This fine-tuned model demonstrates impressive performance in benchmarks for both English and Traditional Chinese, surpassing the results of 
 Taiwan-LLM-7B-v2.1-chat, Taiwan-LLM-13B-v2.0-chat and Qwen-7B-chat in Traditional Chinese assessments. It also excels in some benchmarks against Yi-6B-Chat. 
-In English evaluations, Breeze-7B-Instruct-v0.1 shows comparable results to Mistral-7B-Instruct-v0.1 on the MMLU and MT-Bench benchmarks. 
-
+In English evaluations, Breeze-7B-Instruct-v0.1 shows comparable results to Mistral-7B-Instruct-v0.1 on the MMLU and MT-Bench benchmarks. [See Chat Model Performance.]
 
 
-[Breeze-7B-Instruct-64k-v0.1](https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-64k-v0.1) is an extension to the Breeze-7B-v-0.1 model to enable 64k context length, which is equivalent to 88k Traditional Chinese characters.
+[Breeze-7B-Instruct-64k-v0.1](https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-64k-v0.1) is an extension to [Breeze-7B-Instruct-v0.1](https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-v0.1) 
+to enable 64k 
+context length, which is equivalent to 88k Traditional Chinese characters. With minimal sacrifice in the performance of the regular benchmarks, 
+Breeze-7B-Instruct-64k-v0.1 can solve tasks such as question answering and summarization on document-level inputs. [See Long-context Performance.]
 
 
 *A project by the members (in alphabetical order): Chan-Jan Hsu 許湛然, Chang-Le Liu 劉昶樂, Feng-Ting Liao 廖峰挺, Po-Chun Hsu 許博竣, Yi-Chang Chen 陳宜昌, and the supervisor Da-Shan Shiu 許大山.*
@@ -110,6 +112,10 @@ All inferences run on 2 RTX A6000 GPUs (using `vllm`, with a tensor-parallel siz
 | Taiwan-LLM-13B-v2.0-base                                |   36.80          |    2.2k                  |
 | Yi-34B                                                       |  43.71   |    4.5k                  |
 
+## Long-context Performance
+
+
+
 ## Examples