venu12345/venu2004
收藏Hugging Face2023-02-25 更新2024-03-04 收录
下载链接:
https://hf-mirror.com/datasets/venu12345/venu2004
下载链接
链接失效反馈官方服务:
资源简介:
--import os
import openai
import gradio as gr
# if you have OpenAI API key as an environment variable, enable the below
# openai.api_key = os.getenv("OPENAI_API_KEY")
# if you have OpenAI API key as a string, enable the below
openai.api_key = "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"
start_sequence = "\nVenu:"
restart_sequence = "\nHuman: "
prompt ="The following is a conversation with Venu. The assistant is helpful, creative,clever, and very friendly. \n\nHuman: Hello, who are you?\nVenu: I am Venu . How can I help you " \
"today?\nHuman: "
def openai_create(prompt):
response = openai.Completion.create(
model="text-davinci-003",
prompt=prompt,
temperature=0.9,
max_tokens=150,
top_p=1,
frequency_penalty=2,
presence_penalty= 2,
stop=[" Human:", " AI:"]
)
return response.choices[0].text
def chatgpt_clone(input, history):
history = history or []
s = list(sum(history, ()))
s.append(input)
inp = ' '.join(s)
output = openai_create(inp)
history.append((input, output))
return history, history
block = gr.Blocks()
with block:
gr.Markdown("""<h1><center>Venu</center></h1>
""")
chatbot = gr.Chatbot()
message = gr.Textbox(placeholder=prompt)
state = gr.State()
submit = gr.Button("Enter")
submit.click(chatgpt_clone, inputs=[message, state], outputs=[chatbot, state])
block.launch(share=True)
-
license: afl-3.0
---
提供机构:
venu12345
原始信息汇总
数据集概述
数据集名称
- Venu
数据集描述
- 该数据集用于模拟与名为Venu的AI助手的对话。Venu被描述为帮助性、创造性、聪明且非常友好。
数据集使用的技术
- 使用OpenAI的
text-davinci-003模型进行对话生成。 - 对话生成过程中,设置了温度参数为0.9,最大令牌数为150,频率惩罚为2,存在惩罚为2。
数据集交互界面
- 通过Gradio构建了一个交互式聊天机器人界面,用户可以通过文本输入与Venu进行对话。
许可证
- 该数据集遵循afl-3.0许可证。



