Spaces:
Runtime error
Runtime error
| """ Script for streamlit demo | |
| @author: AbinayaM02 | |
| """ | |
| # Install necessary libraries | |
| from transformers import AutoTokenizer, AutoModelWithLMHead, pipeline | |
| import streamlit as st | |
| from pprint import pprint | |
| import json | |
| # Read the config | |
| with open("config.json") as f: | |
| config = json.loads(f.read()) | |
| # Set page layout | |
| st.set_page_config( | |
| page_title="Tamil Language Models", | |
| layout="wide", | |
| initial_sidebar_state="expanded" | |
| ) | |
| # Load the model | |
| def load_model(model_name): | |
| with st.spinner('Waiting for the model to load.....'): | |
| model = AutoModelWithLMHead.from_pretrained(model_name) | |
| tokenizer = AutoTokenizer.from_pretrained(model_name) | |
| st.success('Model loaded!!') | |
| return model, tokenizer | |
| # Side bar | |
| img = st.sidebar.image("images/tamil_logo.jpg", width=380) | |
| # Choose the model based on selection | |
| page = st.sidebar.selectbox("Model", config["models"]) | |
| data = st.sidebar.selectbox("Data", config[page]) | |
| # Main page | |
| st.header("Tamil Language Demos") | |
| st.markdown( | |
| "This demo uses [GPT2 trained on Oscar dataset](https://huggingface.co/flax-community/gpt-2-tamil) " | |
| "and [GPT2 trained on Oscar & Indic Corpus dataset] (https://huggingface.co/abinayam/gpt-2-tamil) " | |
| "to show language generation" | |
| ) | |
| if page == 'Text Generation' and data == 'Oscar': | |
| st.title('Tamil text generation with GPT2') | |
| st.markdown('A simple demo using gpt-2-tamil model trained on Oscar data') | |
| model, tokenizer = load_model(config[data]) | |
| # Set default options | |
| seed = st.text_input('Starting text', 'அகர முதல எழுதெல்லம்') | |
| #seq_num = st.number_input('Number of sentences to generate ', 1, 20, 5) | |
| max_len = st.number_input('Length of the sentence', 5, 300, 100) | |
| gen_bt = st.button('Generate') | |
| if gen_bt: | |
| try: | |
| with st.spinner('Generating...'): | |
| generator = pipeline('text-generation', model=model, tokenizer=tokenizer) | |
| seqs = generator(seed, max_length=max_len) # num_return_sequences=seq_num) | |
| st.write(seqs) | |
| except Exception as e: | |
| st.exception(f'Exception: {e}') | |
| elif page == 'Text Generation' and data == "Oscar + Indic Corpus": | |
| st.title('Tamil text generation with GPT2') | |
| st.markdown('A simple demo using gpt-2-tamil model trained on Oscar data') | |
| model, tokenizer = load_model(config[data]) | |
| # Set default options | |
| seed = st.text_input('Starting text', 'அகர முதல எழுதெல்லம்') | |
| #seq_num = st.number_input('Number of sentences to generate ', 1, 20, 5) | |
| max_len = st.number_input('Length of the sentence', 5, 300, 100) | |
| gen_bt = st.button('Generate') | |
| if gen_bt: | |
| try: | |
| with st.spinner('Generating...'): | |
| generator = pipeline('text-generation', model=model, tokenizer=tokenizer) | |
| seqs = generator(seed, max_length=max_len) #num_return_sequences=seq_num) | |
| st.write(seqs) | |
| except Exception as e: | |
| st.exception(f'Exception: {e}') | |
| else: | |
| st.title('Tamil News classification with Finetuned GPT2') | |
| st.markdown('In progress') | |