Spaces:
Sleeping
Sleeping
File size: 2,644 Bytes
2e0f8aa 06daacc 2e0f8aa 06daacc 0783741 2e0f8aa bb316b0 2e0f8aa bb316b0 9f85689 0783741 06daacc a27ae3d 06daacc 9f85689 06daacc 253665d 06daacc 4208c01 06daacc 9f85689 2e0f8aa 9f85689 2e0f8aa bb316b0 2e0f8aa 06daacc |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 |
import gradio as gr
from huggingface_hub import InferenceClient
from transformers import pipeline
"""
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
"""
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
modelpath = "distilgpt2"
pipe = pipeline(
"text-generation",
model=modelpath
)
#messages = [
# {"role": "system", "content": "You are a customer applying for a housing loan in India. Provide dummy details about your application and negotiate the terms."},
# {"role": "user", "content": "Hi!Welcome to Hero Housing Finance!"},
# {"role": "assistant", "content": "Hello, I would like to apply for a loan."},
#]
#outputs = pipe(
# messages,
# max_new_tokens=256,
#)
#print(outputs[0]["generated_text"][-1])
system_message = "You are a Technical Support Assistant. Read the Context and generate only the summary of the answer to the Query based on your understanding of the <Question> <Answer> pairs in the context."
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 Technical Support Assistant. Read the Context and generate only the summary of the answer to the Query based on your understanding of the <Question> <Answer> pairs in the context.", 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() |