Haruhi Dialogue Speaker Extract Qwen18

🚀 Chat涼宮春日的對話抽取模型

本模型旨在從小說的chunk中批量提取摘要和對話，為小說內容的分析和處理提供便利。它使用了約30k的中文小說數據和20k的英文小說數據進行訓練，並在qwen - 1.8上進行了3個epoch的finetune，原則上支持中文和英文小說的抽取。

🚀 快速開始

推理代碼

你可以通過以下代碼進行推理：

from transformers import AutoTokenizer, AutoModel, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("silk-road/Haruhi-Dialogue-Speaker-Extract_qwen18", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("silk-road/Haruhi-Dialogue-Speaker-Extract_qwen18", device_map="auto", trust_remote_code=True)

sys_prompt = "給定input paragraph，抽取其中的對話，並輸出為json格式 Let's think it step by step 1. summarize input paragraph into bullet format，存儲在summary字段 2. 抽取每一句對話的內容 dialogue，判斷每一句話的說話人 said by, 存儲在conversations中"

text = "Your novel text"
response_str, history = model.chat(tokenizer, text, history=[], system=sys_prompt)

推理代碼鏈接：Dialogue_Speaker_Extract_Test.ipynb

✨ 主要特性

• 多語言支持：模型使用中文和英文小說數據進行訓練，支持對中文和英文小說的對話和摘要抽取。
• 批量抽取：能夠從小說的chunk中批量提取摘要和對話。

📦 模型信息

📚 詳細文檔

官方提示

中文

給定input paragraph，抽取其中的對話，並輸出為json格式 Let's think it step by step 1. summarize input paragraph into bullet format，存儲在summary字段 2. 抽取每一句對話的內容 dialogue，判斷每一句話的說話人 said by, 存儲在conversations中

英文

Given an input paragraph, extract the dialogues within it, and output them in JSON format.

Let's think about it step by step:
- Summarize the input paragraph into bullet points and store it in the 'summary' field.
- Extract the content of each dialogue ('dialogue'), identify the speaker for each sentence ('said by'), and store these in 'conversations'.

輸出示例

中文輸出示例

{'summary': '- 彭蠡不在家中，老刀感到擔憂並等待著彭蠡回家的時間，同時觀察周圍環境和人們的消費行為，表現出內心的飢餓感和焦慮情緒。', 'conversations': [{'dialogue': '哎，你們知道那兒一盤迴鍋肉多少錢嗎？', 'said_by': '小李'}, {'dialogue': '靠，菜裡有沙子。', 'said_by': '小丁'}, {'dialogue': '人家那兒一盤迴鍋肉，就三百四。', 'said_by': '小李'}, {'dialogue': '什麼玩意？這麼貴。', 'said_by': '小丁'}, {'dialogue': '你吃不了這麼多。', 'said_by': '小李'}]}
{'summary': '- 彭蠡在家等待彭蠡回家，表現出內心的飢餓感和焦慮情緒，同時對彭蠡的行為表示不滿和失望。彭蠡則對老刀的行為表現出冷漠和不屑的態度。', 'conversations': [{'dialogue': '我沒時間和你解釋。我需要去第一空間，你告訴我怎麼走。', 'said_by': '老刀'}, {'dialogue': '回我家說，要走也從那兒走。', 'said_by': '彭蠡'}, {'dialogue': '回家啦，回家啦。轉換馬上開始了。', 'said_by': '車上的人'}, {'dialogue': '你不告訴我為什麼，我就不告訴你怎麼走。', 'said_by': '彭蠡'}, {'dialogue': '你躲在垃圾道里？去第二空間？那你得等24小時啊。', 'said_by': '彭蠡'}, {'dialogue': '二十萬塊。等一禮拜也值啊。', 'said_by': '老刀'}, {'dialogue': '你就這麼缺錢花？', 'said_by': '彭蠡'}, {'dialogue': '糖糖還有一年多該去幼兒園了。我來不及了。', 'said_by': '老刀'}, {'dialogue': '你別說了。', 'said_by': '彭蠡'}]}
{'summary': '- 彭蠡對彭蠡的行為表現出不滿和失望，同時對老刀的行為表現出冷漠和不屑的態度。', 'conversations': [{'dialogue': '你真是作死，她又不是你閨女，犯得著嗎。', 'said_by': '彭蠡'}, {'dialogue': '別說這些了。快告我怎麼走。', 'said_by': '老刀'}, {'dialogue': '你可得知道，萬一被抓著，可不只是罰款，得關上好幾個月。', 'said_by': '彭蠡'}, {'dialogue': '你不是去過好多次嗎？', 'said_by': '老刀'}, {'dialogue': '只有四次。第五次就被抓了。', 'said_by': '彭蠡'}, {'dialogue': '那也夠了。我要是能去四次，抓一次也無所謂。', 'said_by': '老刀'}, {'dialogue': '別說了。你要是真想讓我帶你去，我就帶你去。', 'said_by': '彭蠡'}]}

- 彭蠡不在家中，老刀感到擔憂並等待著彭蠡回家的時間，同時觀察周圍環境和人們的消費行為，表現出內心的飢餓感和焦慮情緒。
小李 : 哎，你們知道那兒一盤迴鍋肉多少錢嗎？
小丁 : 靠，菜裡有沙子。
小李 : 人家那兒一盤迴鍋肉，就三百四。
小丁 : 什麼玩意？這麼貴。
小李 : 你吃不了這麼多。
- 彭蠡在家等待彭蠡回家，表現出內心的飢餓感和焦慮情緒，同時對彭蠡的行為表示不滿和失望。彭蠡則對老刀的行為表現出冷漠和不屑的態度。
老刀 : 我沒時間和你解釋。我需要去第一空間，你告訴我怎麼走。
彭蠡 : 回我家說，要走也從那兒走。
車上的人 : 回家啦，回家啦。轉換馬上開始了。
彭蠡 : 你不告訴我為什麼，我就不告訴你怎麼走。
彭蠡 : 你躲在垃圾道里？去第二空間？那你得等24小時啊。
老刀 : 二十萬塊。等一禮拜也值啊。
彭蠡 : 你就這麼缺錢花？
老刀 : 糖糖還有一年多該去幼兒園了。我來不及了。
彭蠡 : 你別說了。
- 彭蠡對彭蠡的行為表現出不滿和失望，同時對老刀的行為表現出冷漠和不屑的態度。
彭蠡 : 你真是作死，她又不是你閨女，犯得著嗎。
老刀 : 別說這些了。快告我怎麼走。
彭蠡 : 你可得知道，萬一被抓著，可不只是罰款，得關上好幾個月。
老刀 : 你不是去過好多次嗎？
彭蠡 : 只有四次。第五次就被抓了。
老刀 : 那也夠了。我要是能去四次，抓一次也無所謂。
彭蠡 : 別說了。你要是真想讓我帶你去，我就帶你去。

英文輸出示例

{'summary': "Snow-covered Paris, Kimura's workshop, artist and viewer engaging in conversation.", 'conversations': [{'dialogue': 'You should hear the stories they tell of you at the café. If Émile is to be believed, you arrived here as an ukiyo-e courtesan, nothing more than paper wrapped around a porcelain bowl. A painter—he will not say which of us it was, of course—bought the bowl and the print along with it.', 'said_by': 'Artist'}, {'dialogue': 'And the painter pulled me from the print with the sheer force of his imagination, I’m sure. Émile is a novelist and can hardly be trusted to give an accurate account. The reality of my conception is vastly more mundane, I assure you…though it does involve a courtesan.', 'said_by': 'Woman'}, {'dialogue': 'A grain of truth makes for the best fiction. nude, but leave the jewelry and the shoes. I’ll paint you on the chaise. We’ll have three hours in the proper light, and I will pay you four francs.', 'said_by': 'Artist'}, {'dialogue': 'Victorine gets five!', 'said_by': 'Woman'}, {'dialogue': 'Victorine is a redhead.', 'said_by': 'Artist'}, {'dialogue': 'My name is Mariko, by the way, but everyone calls me Mari.', 'said_by': 'Mariko'}]}
{'summary': "Snow-covered Paris, Kimura's workshop, artist and viewer engaged in conversation. Artist and viewer engage in intimate conversation and interaction.", 'conversations': [{'dialogue': 'I’m on the chaise', 'said_by': 'Artist'}, {'dialogue': 'Bring your left hip forward. No, not that far. Bend the leg a bit more, yes. Turn your head to face the canvas.', 'said_by': 'Artist'}, {'dialogue': 'Like a Manet', 'said_by': 'Artist'}, {'dialogue': 'Don’t like a model that talks while you work, huh?', 'said_by': 'Artist'}, {'dialogue': 'I don’t like being compared to other artists.', 'said_by': 'Artist'}, {'dialogue': 'Then you must paint me so well that I forget about the others.', 'said_by': 'Artist'}, {'dialogue': 'Tilt your head into the light. And look at me intently. Intently. As though I were the one naked on the chaise.', 'said_by': 'Artist'}, {'dialogue': 'You did better than I would have expected.', 'said_by': 'Artist'}, {'dialogue': 'There are other poses I could show you, if you like?', 'said_by': 'Artist'}, {'dialogue': 'But the sooner I get started on this portrait, the better.', 'said_by': 'Artist'}]}
{'summary': "Kimura's workshop, artist and viewer engaging in intimate conversation and interaction. Kimura responds with a strong, cold embrace, leading to a passionate physical exchange. Afterward, the artist falls asleep, leaving the narrator feeling incomplete and longing.", 'num': 14, 'conversations': [{'dialogue': 'I could show you other poses.', 'said_by': 'Kimura'}, {'dialogue': 'Yes.', 'said_by': 'Kimura'}, {'dialogue': 'See you tomorrow?', 'said_by': 'Artist'}]}

Snow-covered Paris, Kimura's workshop, artist and viewer engaging in conversation.
Artist : You should hear the stories they tell of you at the café. If Émile is to be believed, you arrived here as an ukiyo-e courtesan, nothing more than paper wrapped around a porcelain bowl. A painter—he will not say which of us it was, of course—bought the bowl and the print along with it.
Woman : And the painter pulled me from the print with the sheer force of his imagination, I’m sure. Émile is a novelist and can hardly be trusted to give an accurate account. The reality of my conception is vastly more mundane, I assure you…though it does involve a courtesan.
Artist : A grain of truth makes for the best fiction. nude, but leave the jewelry and the shoes. I’ll paint you on the chaise. We’ll have three hours in the proper light, and I will pay you four francs.
Woman : Victorine gets five!
Artist : Victorine is a redhead.
Mariko : My name is Mariko, by the way, but everyone calls me Mari.
Snow-covered Paris, Kimura's workshop, artist and viewer engaged in conversation. Artist and viewer engage in intimate conversation and interaction.
Artist : I’m on the chaise
Artist : Bring your left hip forward. No, not that far. Bend the leg a bit more, yes. Turn your head to face the canvas.
Artist : Like a Manet
Artist : Don’t like a model that talks while you work, huh?
Artist : I don’t like being compared to other artists.
Artist : Then you must paint me so well that I forget about the others.
Artist : Tilt your head into the light. And look at me intently. Intently. As though I were the one naked on the chaise.
Artist : You did better than I would have expected.
Artist : There are other poses I could show you, if you like?
Artist : But the sooner I get started on this portrait, the better.
Kimura's workshop, artist and viewer engaging in intimate conversation and interaction. Kimura responds with a strong, cold embrace, leading to a passionate physical exchange. Afterward, the artist falls asleep, leaving the narrator feeling incomplete and longing.
Kimura : I could show you other poses.
Kimura : Yes.
Artist : See you tomorrow?

🔜 待辦事項

中文

• [x] 拓展到多chunks的inference
• [x] 提供英語的例子
• [ ] 提供一個多章節並行inference的例子
• [ ] 在json解析失敗的時候嘗試直接從raw字符串提取summary
• [ ] 在失敗的時候額外嘗試調用openai進行推理

英文

• [x] Expand to multi - chunk inference
• [x] Provide an English example
• [ ] Provide an example of multi - chapter parallel inference
• [ ] Try extracting summary directly from raw strings when JSON parsing fails
• [ ] Additionally attempt to use OpenAI for inference when failing

👥 貢獻者

• 李魯魯：完成了數據的收集，以及進一步將inference程序擴展到連續的chunks
• 劉崇寒：完成了模型的訓練
• 米唯實：測試並上傳模型到hugging face

📄 許可證

本項目採用Apache - 2.0許可證。

🔗 主項目鏈接

Chat-Haruhi-Suzumiya