app_1.py

'''from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
import gradio as grad
import ast

#mdl_name = "deepset/roberta-base-squad2"
#my_pipeline = pipeline('question-answering', model=mdl_name, tokenizer=mdl_name)

mdl_name = "distilbert-base-cased-distilled-squad"
my_pipeline = pipeline('question-answering', model=mdl_name,tokenizer=mdl_name)

def answer_question(question,context):
    text= "{"+"'question': '"+question+"','context': '"+context+"'}"
    
    di=ast.literal_eval(text)
    response = my_pipeline(di)
    return response
grad.Interface(answer_question, inputs=["text","text"], outputs="text").launch()
'''
''' 
from transformers import pipeline
import gradio as grad
mdl_name = "VietAI/envit5-translation"
opus_translator = pipeline("translation", model=mdl_name)

def translate(text):
    
    response = opus_translator(text)
    return response
grad.Interface(translate, inputs=["text",], outputs="text").launch()
'''

'''5.11

from transformers import GPT2LMHeadModel,GPT2Tokenizer
import gradio as grad

mdl = GPT2LMHeadModel.from_pretrained('gpt2')
gpt2_tkn=GPT2Tokenizer.from_pretrained('gpt2')

def generate(starting_text):
    tkn_ids = gpt2_tkn.encode(starting_text, return_tensors = 'pt')
    gpt2_tensors = mdl.generate(tkn_ids)
    response = gpt2_tensors
    return response
txt=grad.Textbox(lines=1, label="English", placeholder="English Text here")
out=grad.Textbox(lines=1, label="Generated Tensors")
grad.Interface(generate, inputs=txt, outputs=out).launch()
'''

'''5.12
from transformers import GPT2LMHeadModel,GPT2Tokenizer
import gradio as grad

mdl = GPT2LMHeadModel.from_pretrained('gpt2')
gpt2_tkn=GPT2Tokenizer.from_pretrained('gpt2')


def generate(starting_text):
    tkn_ids = gpt2_tkn.encode(starting_text, return_tensors = 'pt')
    gpt2_tensors = mdl.generate(tkn_ids)
    response=""
    #response = gpt2_tensors
    for i, x in enumerate(gpt2_tensors):
       response=response+f"{i}: {gpt2_tkn.decode(x, skip_special_tokens=True)}"
    return response

txt=grad.Textbox(lines=1, label="English", placeholder="English Text here")
out=grad.Textbox(lines=1, label="Generated Tensors")
grad.Interface(generate, inputs=txt, outputs=out).launch()
'''

'''5.20
from transformers import AutoModelWithLMHead, AutoTokenizer
import gradio as grad

text2text_tkn = AutoTokenizer.from_pretrained("mrm8488/t5-base-finetuned-question-generation-ap")
mdl = AutoModelWithLMHead.from_pretrained("mrm8488/t5-base-finetuned-question-generation-ap")

def text2text(context,answer):
    input_text = "answer: %s  context: %s </s>" % (answer, context)
    features = text2text_tkn ([input_text], return_tensors='pt')

    output = mdl.generate(input_ids=features['input_ids'], 
               attention_mask=features['attention_mask'],
               max_length=64)

    response=text2text_tkn.decode(output[0])    
    return response

context=grad.Textbox(lines=10, label="English", placeholder="Context")
ans=grad.Textbox(lines=1, label="Answer")
out=grad.Textbox(lines=1, label="Genereated Question")
grad.Interface(text2text, inputs=[context,ans], outputs=out).launch()
'''

'''5.21
from transformers import AutoTokenizer, AutoModelWithLMHead
import gradio as grad
text2text_tkn = AutoTokenizer.from_pretrained("deep-learning-analytics/wikihow-t5-small")
mdl = AutoModelWithLMHead.from_pretrained("deep-learning-analytics/wikihow-t5-small")


def text2text_summary(para):
    initial_txt = para.strip().replace("\n","")
    tkn_text = text2text_tkn.encode(initial_txt, return_tensors="pt")

    tkn_ids = mdl.generate(
            tkn_text,
            max_length=250, 
            num_beams=5,
            repetition_penalty=2.5, 
           
            early_stopping=True
        )

    response = text2text_tkn.decode(tkn_ids[0], skip_special_tokens=True)
    return response

para=grad.Textbox(lines=10, label="Paragraph", placeholder="Copy paragraph")
out=grad.Textbox(lines=1, label="Summary")
grad.Interface(text2text_summary, inputs=para, outputs=out).launch()
'''

'''5.28
from transformers import AutoModelForCausalLM, AutoTokenizer,BlenderbotForConditionalGeneration
import torch


chat_tkn = AutoTokenizer.from_pretrained("microsoft/DialoGPT-medium")
mdl = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-medium")


#chat_tkn = AutoTokenizer.from_pretrained("facebook/blenderbot-400M-distill")
#mdl = BlenderbotForConditionalGeneration.from_pretrained("facebook/blenderbot-400M-distill")

def converse(user_input, chat_history=[]):
    
    user_input_ids = chat_tkn(user_input + chat_tkn.eos_token, return_tensors='pt').input_ids

    # keep history in the tensor
    bot_input_ids = torch.cat([torch.LongTensor(chat_history), user_input_ids], dim=-1)

    # get response 
    chat_history = mdl.generate(bot_input_ids, max_length=1000, pad_token_id=chat_tkn.eos_token_id).tolist()
    print (chat_history)

    
    response = chat_tkn.decode(chat_history[0]).split("<|endoftext|>")
    
    print("starting to print response")
    print(response)
    
    # html for display
    html = "<div class='mybot'>"
    for x, mesg in enumerate(response):
        if x%2!=0 :
           mesg="Alicia:"+mesg
           clazz="alicia"
        else :
           clazz="user"
        
        
        print("value of x")
        print(x)
        print("message")
        print (mesg)
        
        html += "<div class='mesg {}'> {}</div>".format(clazz, mesg)
    html += "</div>"
    print(html)
    return html, chat_history

import gradio as grad

css = """
.mychat {display:flex;flex-direction:column}
.mesg {padding:5px;margin-bottom:5px;border-radius:5px;width:75%}
.mesg.user {background-color:lightblue;color:white}
.mesg.alicia {background-color:orange;color:white,align-self:self-end}
.footer {display:none !important}
"""
text=grad.inputs.Textbox(placeholder="Lets chat")
grad.Interface(fn=converse,
             theme="default",
             inputs=[text, "state"],
             outputs=["html", "state"],
             css=css).launch()
'''

from datasets import list_datasets
all_datasets = huggingface_hub.list_datasets()
print(f"There are {len(all_datasets)} datasets currently available on the Hub") 
print(f"The first 10 are: {all_datasets[:10]}")