import gradio as gr
import timm
from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
import transformers


title = "Finetuning [BERT] on A Financial News Sentiment Dataset"
description = """
The LLM was finetuned on a Financial News Tweet Sentiment Dataset. The documents have 3 different labels:
 "LABEL_0": "Bearish",
  "LABEL_1": "Bullish",
  "LABEL_2": "Neutral"
<img src="https://huggingface.co./spaces/course-demos/Rick_and_Morty_QA/resolve/main/rick.png" width=200px>
"""

article = "Check out the model card [here](https://huggingface.co./at2507/finetuned_model)!"

def sentiment_analyzer(financial_news_headline):
  tokenizer = AutoTokenizer.from_pretrained("at2507/finetuned_model")
  model = AutoModelForSequenceClassification.from_pretrained("at2507/finetuned_model")
  zeroshotsent_model = pipeline("text-classification", model = model.to('cpu:0'), tokenizer=tokenizer)
  return zeroshotsent_model(financial_news_headline)

gr.Interface(
    fn=sentiment_analyzer,
    inputs="textbox",
    outputs="text",
    title=title,
    description=description,
    article=article,
    examples=[["CLNE, TRXC, TGE and ADMS among midday movers"],
     ["CRISPR Therapeutics among healthcare gainers; Plus Therapeutics leads the losers"], 
    ["Firsthand Technology Value Fund and Itau CorpBanca among Financial gainers; Mmtec and Jupai among losers"], 
    ["Canopy Growth up 6% as BofA buys the dip"]],
).launch()