Update README.md

README.md

@@ -7,31 +7,41 @@ language:
 - en
 ---
 
-This is a beta release of a QLoRa adapter model to [Falcon-40b](https://huggingface.co/tiiuae/falcon-40b). 
-Please read the instruction carefully before downloading the model.
+This is a QLoRa adapter model to [Falcon-40b](https://huggingface.co/tiiuae/falcon-40b). 
 
 Though Falcon is not specifically trained on Chinese corpus, it exhibits strong performance in Chinese Language Understanding in our experiment. We would like to explore out of curiosity whether a 
-small amount of Chinese instruction data can push it further and make it better at speaking.
+small amount of Chinese instruction data can push it further and make it better at speaking.The LoRa model is trained with the [QLoRa repo](https://github.com/artidoro/qlora) on a subset of bilingual instruction data from [Alpaca-CoT dataset](https://huggingface.co/datasets/QingyiSi/Alpaca-CoT).
 
-The LoRa model is trained with the [QLoRa code](https://github.com/artidoro/qlora) on a subset of bilingual instruction data from [Alpaca-CoT dataset](https://huggingface.co/datasets/QingyiSi/Alpaca-CoT) for a mere 5k steps.
-The finetune model is not as good as the carefully continue-trained-and-finetuned LLaMA-models such as [OpenBuddy](https://huggingface.co/OpenBuddy) and [Ziya](https://huggingface.co/IDEA-CCNL/Ziya-LLaMA-13B-v1) in Chinese generation, 
-still it quickly adapts to the new langauge and generate superisingly good result. We call for more research on applying Falcon-40b to the Chinese domain.
+The result is suprisingly good considering the number of Chinese tokens it has ever seen, though it shows clear limitions. Please check the examples below.
 
-## Evalutions
+```
+Question: 序列1,4,9,16的后一个数是什么？
+Answer: 序列1,4,9,16的后一个数是25。因为序列中的每个数字都是前一个数字加上一个递增的差值，第一个差值是3，第二个差值是5，第三个差值是7，第四个差值是9，所以最后一个数字应该是第四个数字16加上第四个差值9，即16+9=25。因此，序列1,4,9,16的后一个数是25。
 
-We evaluate on two Chinese language understanding benchmarks, [C-Eval](https://cevalbenchmark.com/) and Gaokao subset of [AGIEval](https://github.com/microsoft/AGIEval).
+Question: 已知全班所有同学的姓名存储于列表names中，所有同学的身高存储于列表heights中，它们的关系是一一对应的。请写一段Python代码，将所有同学的姓名按身高由低到高排序。
+Answer: names = ['小明', '小红', '小张', '小李']
+heights = [170, 165, 175, 180]
 
-* C-Eval made breaking change in 2023/06/08 from few-shot to zero-shot, 
+# 使用zip函数将姓名和身高对应起来，然后根据身高排序
+sorted_names = sorted(names, key=lambda x: heights[names.index(x)])
 
-Result on C-Eval test set with 5-shot and no CoT
+# 输出排序后的姓名列表
+print(sorted_names)
 
-| Average | Avg(Hard) | STEM | Social Science | Humanities | Others |
-| - | - | - | - | - | - |
-| 40.4 | 30.1 | 35.8 | 47.6 | 42.0 | 40.6 |
+Question: 中国的“东北三省”指的是哪里？
+Answer: 中国的东北三省指的是吉林省、黑龙江省和辽宁省。这些省份位于中国东北地区，北临俄罗斯和乌克兰，东临日本海。它们是中国最大的省份之一，占中国陆地面积的七分之一。东北三省以其自然风光、丰富的民族文化和历史遗产而闻名。它们是中国旅游业的重要目的地之一。您还有其他问题吗？
 
+Question: “但愿人长久，千里共婵娟”，其中婵娟指的是什么？ A、月亮 B、姻缘
+Answer:  这道题目考察的是对于古诗词的理解和文化常识。这句话出自唐代诗人杜甫的《月夜》一诗，其中婵娟是指月亮。这句话的意思是希望人和月亮能够长久存在，共同见证世间美好的事物。婵娟是古代诗词中常用的一个词语，指的是月亮的光辉、美丽和媚态。因此，答案是A，月亮。
+```
 
-Result on GaoKao subset of C-Eval with 0-shot
 
-| Average | GK-chinese | GK-English | GK-geography | GK-history | GK-biology | GK-chemistry | GK-physics | GK-mathqa | GK-mathcloze
-| - | - | - | - | - | - | - | - | - | - |
-| 33.6 | 26.4 | 69.0 | 46.7 | 47.8 | 27.1 | 32.4 | 24.5 | 26.8 | 1.7 |
+## Evalutions
+
+We evaluate on [C-Eval](https://cevalbenchmark.com/). More results will be added later.
+
+Result on C-Eval test set with 5-shot and no CoT, which is better than LLaMA-series models.
+
+| Average | Avg(Hard) | STEM | Social Science | Humanities | Others |
+| - | - | - | - | - | - |
+| 42.0 | 32.4 | 38.5 | 50.3 | 42.5 | 40.5 |