Spaces:
Sleeping
Sleeping
File size: 2,373 Bytes
6f66e5a e8c7621 6f66e5a e8c7621 6f66e5a e8c7621 6f66e5a e8c7621 6f66e5a e8c7621 6f66e5a e8c7621 6619948 6f66e5a 6619948 6f66e5a 3b05c47 |
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 |
import gradio as gr
import os
import requests
from dotenv import load_dotenv
load_dotenv()
API_TOKEN = os.environ.get("API_TOKEN", None)
MODEL_URL = os.environ.get("MODEL_URL", None)
def evaluate(hotel_request: str):
resp = requests.post(
MODEL_URL,
json={"inputs": hotel_request},
headers={"Authorization": f"Bearer {API_TOKEN}"},
cookies=None,
timeout=10,
)
payload = resp.json()
text = payload[0]["generated_text"]
name, location, hotel, date = text.split("|")
return name, hotel, location, date
gr.Interface(
fn=evaluate,
inputs=[
# gr.components.Textbox(
# lines=2,
# label="Instruction",
# placeholder="Tell me about alpacas.",
# ),
gr.components.Textbox(lines=2, label="Input", placeholder="Request for the Hotel"),
# gr.components.Slider(
# minimum=0, maximum=1, value=0.1, label="Temperature"
# ),
# gr.components.Slider(
# minimum=0, maximum=1, value=0.75, label="Top p"
# ),
# gr.components.Slider(
# minimum=0, maximum=100, step=1, value=40, label="Top k"
# ),
# gr.components.Slider(
# minimum=1, maximum=4, step=1, value=4, label="Beams"
# ),
# gr.components.Slider(
# minimum=1, maximum=2000, step=1, value=128, label="Max tokens"
# ),
# gr.components.Checkbox(label="Stream output"),
],
outputs=[
gr.inputs.Textbox(
lines=1,
label="Guest Name",
),
gr.inputs.Textbox(
lines=1,
label="Hotel",
),
gr.inputs.Textbox(
lines=1,
label="Location",
),
gr.inputs.Textbox(
lines=1,
label="Date",
)
],
allow_flagging="never",
title="Falcon-LoRA",
description="Falcon-LoRA is a 1B-parameter LLM finetuned to follow instructions. It is trained on the [Hotel Requests](https://huggingface.co/datasets/MichaelAI23/hotel_requests) dataset.", # noqa: E501
).queue().launch() #server_name="0.0.0.0", server_port=8080) |