Spaces:
Sleeping
Sleeping
import gradio as gr | |
from huggingface_hub import InferenceClient | |
""" | |
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference | |
""" | |
DESCRIPTION = ''' | |
<div> | |
<h1 style="text-align: center;">zephyr-7b-beta</h1> | |
<p>This Space demonstrates the instruction-tuned model<b>zephyr-7b-beta by Hugging face</b></a>. zephyr-7b-beta is the new open 7B parameter GPT-like model fine-tuned on a mix of publicly available, synthetic datasets. Feel free to play with it, or duplicate to run privately!</p> | |
<p>π Zephyr is a series of language models that are trained to act as helpful assistants. Zephyr-7B-Ξ² is the second model in the series, and is a fine-tuned version of mistralai/Mistral-7B-v0.1 that was trained on on a mix of publicly available, synthetic datasets using Direct Preference Optimization (DPO). We found that removing the in-built alignment of these datasets boosted performance on MT Bench and made the model more helpful..</p> | |
<p>π¦ Looking for an even more powerful model? Check out the <a href="https://huggingface.co/chat/"><b>Hugging Chat</b></a> integration for Meta Llama 3 70b</p> | |
</div> | |
''' | |
LICENSE = """ | |
<p/> | |
--- | |
Built with zephyr-7b-beta | |
""" | |
PLACEHOLDER = """ | |
<div style="padding: 30px; text-align: center; display: flex; flex-direction: column; align-items: center;"> | |
<img src="https://ysharma-dummy-chat-app.hf.space/file=/tmp/gradio/8e75e61cc9bab22b7ce3dec85ab0e6db1da5d107/Meta_lockup_positive%20primary_RGB.jpg" style="width: 80%; max-width: 550px; height: auto; opacity: 0.55; "> | |
<h1 style="font-size: 28px; margin-bottom: 2px; opacity: 0.55;">zephyr-7b-beta</h1> | |
<p style="font-size: 18px; margin-bottom: 2px; opacity: 0.65;">Ask me anything...</p> | |
</div> | |
""" | |
css = """ | |
h1 { | |
text-align: center; | |
display: block; | |
} | |
#duplicate-button { | |
margin: auto; | |
color: white; | |
background: #1565c0; | |
border-radius: 100vh; | |
}""" | |
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta") | |
def respond( | |
message, | |
history: list[tuple[str, str]], | |
system_message, | |
max_tokens, | |
temperature, | |
top_p, | |
): | |
messages = [{"role": "system", "content": system_message}] | |
for val in history: | |
if val[0]: | |
messages.append({"role": "user", "content": val[0]}) | |
if val[1]: | |
messages.append({"role": "assistant", "content": val[1]}) | |
messages.append({"role": "user", "content": message}) | |
response = "" | |
for message in client.chat_completion( | |
messages, | |
max_tokens=max_tokens, | |
stream=True, | |
temperature=temperature, | |
top_p=top_p, | |
): | |
token = message.choices[0].delta.content | |
response += token | |
yield response | |
""" | |
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface | |
""" | |
demo = gr.ChatInterface( | |
respond, | |
additional_inputs=[ | |
gr.Textbox(value="You are a friendly Chatbot.", label="System message"), | |
gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"), | |
gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"), | |
gr.Slider( | |
minimum=0.1, | |
maximum=1.0, | |
value=0.95, | |
step=0.05, | |
label="Top-p (nucleus sampling)", | |
), | |
], | |
) | |
if __name__ == "__main__": | |
demo.launch() |