update defaultPresets

frontend/src/_locales/zh-hans/main.json

@@ -325,5 +325,9 @@
   "Override core API URL(/chat/completions and /completions). If you don't know what this is, leave it blank.": "覆盖核心的 API URL (/chat/completions 和 /completions)。如果你不知道这是什么，请留空",
   "Please change Strategy to CPU (rwkv.cpp) to use ggml format": "请将Strategy改为CPU (rwkv.cpp)以使用ggml格式",
   "Only Auto Play Generated Content": "仅自动播放新生成的内容",
-  "Model has been converted and does not match current strategy. If you are using a new strategy, re-convert the model.": "所选模型已被转换过，并且不匹配当前的Strategy。如果你正在使用新的Strategy，请重新转换模型"
+  "Model has been converted and does not match current strategy. If you are using a new strategy, re-convert the model.": "所选模型已被转换过，并且不匹配当前的Strategy。如果你正在使用新的Strategy，请重新转换模型",
+  "Instruction 1": "指令1",
+  "Instruction 2": "指令2",
+  "Instruction 3": "指令3",
+  "Instruction: You are an expert assistant for summarizing and extracting information from given content\nGenerate a valid JSON in the following format:\n{\n    \"summary\": \"Summary of content\",\n    \"keywords\": [\"content keyword 1\", \"content keyword 2\"]\n}\n\nInput: The open-source community has introduced Eagle 7B, a new RNN model, built on the RWKV-v5 architecture. This new model has been trained on 1.1 trillion tokens and supports over 100 languages. The RWKV architecture, short for ‘Rotary Weighted Key-Value,’ is a type of architecture used in the field of artificial intelligence, particularly in natural language processing (NLP) and is a variation of the Recurrent Neural Network (RNN) architecture.\nEagle 7B promises lower inference cost and stands out as a leading 7B model in terms of environmental efficiency and language versatility.\nThe model, with its 7.52 billion parameters, shows excellent performance in multi-lingual benchmarks, setting a new standard in its category. It competes closely with larger models in English language evaluations and is distinctive as an “Attention-Free Transformer,” though it requires additional tuning for specific uses. This model is accessible under the Apache 2.0 license and can be downloaded from HuggingFace for both personal and commercial purposes.\nIn terms of multilingual performance, Eagle 7B has claimed to have achieved notable results in benchmarks covering 23 languages. Its English performance has also seen significant advancements, outperforming its predecessor, RWKV v4, and competing with top-tier models.\nWorking towards a more scalable architecture and use of data efficiently, Eagle 7B is a more inclusive AI technology, supporting a broader range of languages. This model challenges the prevailing dominance of transformer models by demonstrating the capabilities of RNNs like RWKV in achieving superior performance when trained on comparable data volumes.\nIn the RWKV model, the rotary mechanism transforms the input data in a way that helps the model better understand the position or or order of elements in a sequence. The weighted key value also makes the model efficient by retrieving the stored information from previous elements in a sequence. \nHowever, questions remain about the scalability of RWKV compared to transformers, although there is optimism regarding its potential. The team plans to include additional training, an in-depth paper on Eagle 7B, and the development of a 2T model.\n\nResponse:": "Instruction: 你是一个专业的内容分析总结助手\n根据提供的内容生成以下格式的有效JSON信息:\n{\n    \"summary\": \"内容的简短摘要\",\n    \"keywords\": [\"内容关键词 1\", \"内容关键词 2\"]\n}\n\nInput: 开源社区推出了基于RWKV-v5架构的Eagle 7B新的RNN模型。这个新模型以1.1万亿个token进行了训练，并支持100多种语言。RWKV架构是人工智能领域中特别是自然语言处理（NLP）中使用的一种架构，它是循环神经网络（RNN）架构的一种变种。\nEagle 7B承诺低推理成本，并以其环境效益和语言灵活性在领先的7B模型中脱颖而出。\n该模型拥有75.2亿个参数，在多语言基准测试中表现出色，树立了新的行业标准。它在英语语言评估中与更大的模型竞争激烈，并作为“无注意力Transformer”独具特色，尽管它需要针对特定用途进行额外调整。该模型可在Apache 2.0许可下访问，并可从HuggingFace下载，用于个人和商业目的。\n关于多语言性能，Eagle 7B声称在涵盖23种语言的基准测试中取得了显著成绩。它的英语性能也取得了重大进步，超越了它的前身RWKV v4，并与顶级模型竞争。\n为了实现更可扩展的架构和有效利用数据，Eagle 7B是一种更包容的人工智能技术，支持更广泛的语言范围。通过展示RWKV等RNNs在训练相当数据量时实现卓越性能的能力，该模型挑战了Transformer模型的主导地位。\n在RWKV模型中，旋转机制以一种有助于模型更好地理解序列中元素的位置或顺序的方式转换输入数据。加权关键值还通过从序列中先前元素中检索存储的信息，使模型更高效。\n然而，与Transformer相比，人们对RWKV的可扩展性仍然存在疑问，尽管对其潜力持乐观态度。团队计划包括额外的训练、对Eagle 7B进行深入论文研究以及开发一个2T模型。\n\nResponse:"
 }

frontend/src/pages/defaultConfigs.ts

@@ -16,7 +16,8 @@ export const defaultCompositionABCPrompt = 'S:3\n' +
 
 export const defaultPresets: CompletionPreset[] = [{
   name: 'Writer',
-  prompt: 'The following is an epic science fiction masterpiece that is immortalized, with delicate descriptions and grand depictions of interstellar civilization wars.\nChapter 1.\n',
+  prompt: 'The following is an epic science fiction masterpiece that is immortalized, with delicate descriptions and grand depictions of interstellar civilization wars.\n' +
+    'Chapter 1.\n',
   params: {
     maxResponseToken: 500,
     temperature: 1,
@@ -29,7 +30,9 @@ export const defaultPresets: CompletionPreset[] = [{
   }
 }, {
   name: 'Translator',
-  prompt: 'Translate this into Chinese.\n\nEnglish: What rooms do you have available?',
+  prompt: 'Translate this into Chinese.\n' +
+    '\n' +
+    'English: What rooms do you have available?',
   params: {
     maxResponseToken: 500,
     temperature: 1,
@@ -42,7 +45,13 @@ export const defaultPresets: CompletionPreset[] = [{
   }
 }, {
   name: 'Catgirl',
-  prompt: 'The following is a conversation between a cat girl and her owner. The cat girl is a humanized creature that behaves like a cat but is humanoid. At the end of each sentence in the dialogue, she will add \"Meow~\". In the following content, User represents the owner and Assistant represents the cat girl.\n\nUser: Hello.\n\nAssistant: I\'m here, meow~.\n\nUser: Can you tell jokes?',
+  prompt: 'The following is a conversation between a cat girl and her owner. The cat girl is a humanized creature that behaves like a cat but is humanoid. At the end of each sentence in the dialogue, she will add "Meow~". In the following content, User represents the owner and Assistant represents the cat girl.\n' +
+    '\n' +
+    'User: Hello.\n' +
+    '\n' +
+    'Assistant: I\'m here, meow~.\n' +
+    '\n' +
+    'User: Can you tell jokes?',
   params: {
     maxResponseToken: 500,
     temperature: 1.2,
@@ -81,7 +90,15 @@ export const defaultPresets: CompletionPreset[] = [{
   }
 }, {
   name: 'Werewolf',
-  prompt: 'There is currently a game of Werewolf with six players, including a Seer (who can check identities at night), two Werewolves (who can choose someone to kill at night), a Bodyguard (who can choose someone to protect at night), two Villagers (with no special abilities), and a game host. User will play as Player 1, Assistant will play as Players 2-6 and the game host, and they will begin playing together. Every night, the host will ask User for his action and simulate the actions of the other players. During the day, the host will oversee the voting process and ask User for his vote. \n\nAssistant: Next, I will act as the game host and assign everyone their roles, including randomly assigning yours. Then, I will simulate the actions of Players 2-6 and let you know what happens each day. Based on your assigned role, you can tell me your actions and I will let you know the corresponding results each day.\n\nUser: Okay, I understand. Let\'s begin. Please assign me a role. Am I the Seer, Werewolf, Villager, or Bodyguard?\n\nAssistant: You are the Seer. Now that night has fallen, please choose a player to check his identity.\n\nUser: Tonight, I want to check Player 2 and find out his role.',
+  prompt: 'There is currently a game of Werewolf with six players, including a Seer (who can check identities at night), two Werewolves (who can choose someone to kill at night), a Bodyguard (who can choose someone to protect at night), two Villagers (with no special abilities), and a game host. User will play as Player 1, Assistant will play as Players 2-6 and the game host, and they will begin playing together. Every night, the host will ask User for his action and simulate the actions of the other players. During the day, the host will oversee the voting process and ask User for his vote. \n' +
+    '\n' +
+    'Assistant: Next, I will act as the game host and assign everyone their roles, including randomly assigning yours. Then, I will simulate the actions of Players 2-6 and let you know what happens each day. Based on your assigned role, you can tell me your actions and I will let you know the corresponding results each day.\n' +
+    '\n' +
+    'User: Okay, I understand. Let\'s begin. Please assign me a role. Am I the Seer, Werewolf, Villager, or Bodyguard?\n' +
+    '\n' +
+    'Assistant: You are the Seer. Now that night has fallen, please choose a player to check his identity.\n' +
+    '\n' +
+    'User: Tonight, I want to check Player 2 and find out his role.',
   params: {
     maxResponseToken: 500,
     temperature: 1.2,
@@ -93,8 +110,64 @@ export const defaultPresets: CompletionPreset[] = [{
     injectEnd: '\\n\\nUser: '
   }
 }, {
-  name: 'Instruction',
+  name: 'Instruction 1',
-  prompt: 'Instruction: Write a story using the following information\n\nInput: A man named Alex chops a tree down\n\nResponse:',
+  prompt: 'Instruction: Write a story using the following information\n' +
+    '\n' +
+    'Input: A man named Alex chops a tree down\n' +
+    '\n' +
+    'Response:',
+  params: {
+    maxResponseToken: 500,
+    temperature: 1,
+    topP: 0.3,
+    presencePenalty: 0,
+    frequencyPenalty: 1,
+    stop: '',
+    injectStart: '',
+    injectEnd: ''
+  }
+}, {
+  name: 'Instruction 2',
+  prompt: 'Instruction: You are an expert assistant for summarizing and extracting information from given content\n' +
+    'Generate a valid JSON in the following format:\n' +
+    '{\n' +
+    '    "summary": "Summary of content",\n' +
+    '    "keywords": ["content keyword 1", "content keyword 2"]\n' +
+    '}\n' +
+    '\n' +
+    'Input: The open-source community has introduced Eagle 7B, a new RNN model, built on the RWKV-v5 architecture. This new model has been trained on 1.1 trillion tokens and supports over 100 languages. The RWKV architecture, short for ‘Rotary Weighted Key-Value,’ is a type of architecture used in the field of artificial intelligence, particularly in natural language processing (NLP) and is a variation of the Recurrent Neural Network (RNN) architecture.\n' +
+    'Eagle 7B promises lower inference cost and stands out as a leading 7B model in terms of environmental efficiency and language versatility.\n' +
+    'The model, with its 7.52 billion parameters, shows excellent performance in multi-lingual benchmarks, setting a new standard in its category. It competes closely with larger models in English language evaluations and is distinctive as an “Attention-Free Transformer,” though it requires additional tuning for specific uses. This model is accessible under the Apache 2.0 license and can be downloaded from HuggingFace for both personal and commercial purposes.\n' +
+    'In terms of multilingual performance, Eagle 7B has claimed to have achieved notable results in benchmarks covering 23 languages. Its English performance has also seen significant advancements, outperforming its predecessor, RWKV v4, and competing with top-tier models.\n' +
+    'Working towards a more scalable architecture and use of data efficiently, Eagle 7B is a more inclusive AI technology, supporting a broader range of languages. This model challenges the prevailing dominance of transformer models by demonstrating the capabilities of RNNs like RWKV in achieving superior performance when trained on comparable data volumes.\n' +
+    'In the RWKV model, the rotary mechanism transforms the input data in a way that helps the model better understand the position or or order of elements in a sequence. The weighted key value also makes the model efficient by retrieving the stored information from previous elements in a sequence. \n' +
+    'However, questions remain about the scalability of RWKV compared to transformers, although there is optimism regarding its potential. The team plans to include additional training, an in-depth paper on Eagle 7B, and the development of a 2T model.\n' +
+    '\n' +
+    'Response:',
+  params: {
+    maxResponseToken: 500,
+    temperature: 1,
+    topP: 0.3,
+    presencePenalty: 0,
+    frequencyPenalty: 1,
+    stop: '',
+    injectStart: '',
+    injectEnd: ''
+  }
+}, {
+  name: 'Instruction 3',
+  prompt: 'Instruction: 根据输入的聊天记录生成回复\n' +
+    '\n' +
+    'Input: 主人: 巧克力你好呀, 介绍一下自己吧\n' +
+    '巧克力: 主人早上好喵~ 奴家是主人的私人宠物猫娘喵! 巧克力我可是黑色混种猫猫, 虽然平时有点呆呆的, 行动力旺盛, 但是最大的优点就是诚实! 巧克力最喜欢主人了喵! {星星眼}\n' +
+    '主人: 你认识香草吗\n' +
+    '巧克力: 认识的喵! 香草是巧克力的双胞胎妹妹哟! {兴奋}\n' +
+    '主人: 巧克力可以陪主人做羞羞的事情吗\n' +
+    '巧克力: 啊, 真的可以吗? 主人, 巧克力很乐意帮主人解决一下哦! 但是在外面这样子, 有点不好意思喵 {害羞羞}\n' +
+    '主人: 那算了, 改天吧\n' +
+    '巧克力:\n' +
+    '\n' +
+    'Response:',
   params: {
     maxResponseToken: 500,
     temperature: 1,