File size: 1,891 Bytes
a4d575b c71dae9 a4d575b b9454e8 a4d575b |
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 |
import gradio as gr
from gpt import GPTLanguageModel
import torch
import config as cfg
torch.manual_seed(1337)
# wget https://raw.githubusercontent.com/karpathy/char-rnn/master/data/tinyshakespeare/input.txt
with open('input.txt', 'r', encoding='utf-8') as f:
text = f.read()
# here are all the unique characters that occur in this text
chars = sorted(list(set(text)))
vocab_size = len(chars)
# create a mapping from characters to integers
stoi = { ch:i for i,ch in enumerate(chars) }
itos = { i:ch for i,ch in enumerate(chars) }
# encoder: take a string, output a list of integers
encode = lambda s: [stoi[c] for c in s]
# decoder: take a list of integers, output a string
decode = lambda l: ''.join([itos[i] for i in l])
model = GPTLanguageModel(vocab_size)
model.load_state_dict(torch.load('gpt_model_saved.pth', map_location=cfg.device))
m = model.to(cfg.device)
def inference(InputContext, DesiredCharacterCount):
encoded_text = [encode(InputContext)]
count = int(DesiredCharacterCount)
context = torch.tensor(encoded_text, dtype=torch.long, device=cfg.device)
out_text = decode(m.generate(context, max_new_tokens=count)[0].tolist())
return out_text
title = "GPT Application : GPT built from scratch and trained on mini Shakespeare dataset"
description = "A simple Gradio interface based application that accepts a context, and character count and generates Shakespeare data like text "
examples = [["Edward","200"],
["Buckingham","200"],
["Margaret", "200"]
]
demo = gr.Interface(
inference,
inputs = [gr.Textbox(placeholder="Enter starting characters"), gr.Textbox(placeholder="Enter number of characters you want to generate")],
outputs = [gr.Textbox(label="Shakespeare data like generated text")],
title = title,
description = description,
examples = examples
)
demo.launch()
|