Spaces:
Runtime error
Runtime error
| # 1. The RoBERTa base model is used, fine-tuned using the SQuAD 2.0 dataset. | |
| # It’s been trained on question-answer pairs, including unanswerable questions, for the task of question and answering. | |
| # 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) | |
| # 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() | |
| #--------------------------------------------------------------------------------- | |
| # 2. Same task, different model. | |
| # from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline | |
| # import gradio as grad | |
| # import ast | |
| # 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() | |
| #--------------------------------------------------------------------------------- | |
| # 3. Different task: language translation. | |
| # from transformers import pipeline | |
| # import gradio as grad | |
| # First model translates English to German. | |
| # mdl_name = "Helsinki-NLP/opus-mt-en-de" | |
| # opus_translator = pipeline("translation", model=mdl_name) | |
| # def translate(text): | |
| # response = opus_translator(text) | |
| # return response | |
| # grad.Interface(translate, inputs=["text",], outputs="text").launch() | |
| #---------------------------------------------------------------------------------- | |
| # 4. Language translation without pipeline API. | |
| # Second model translates English to French. | |
| # from transformers import AutoModelForSeq2SeqLM, AutoTokenizer | |
| # import gradio as grad | |
| # mdl_name = "Helsinki-NLP/opus-mt-en-fr" | |
| # mdl = AutoModelForSeq2SeqLM.from_pretrained(mdl_name) | |
| # my_tkn = AutoTokenizer.from_pretrained(mdl_name) | |
| # def translate(text): | |
| # inputs = my_tkn(text, return_tensors="pt") | |
| # trans_output = mdl.generate(**inputs) | |
| # response = my_tkn.decode(trans_output[0], skip_special_tokens=True) | |
| # return response | |
| # txt = grad.Textbox(lines=1, label="English", placeholder="English Text here") | |
| # out = grad.Textbox(lines=1, label="French") | |
| # grad.Interface(translate, inputs=txt, outputs=out).launch() | |
| #----------------------------------------------------------------------------------- | |
| # 5. Different task: abstractive summarization | |
| # Abstractive summarization is more difficult than extractive summarization, | |
| # which pulls key sentences from a document and combines them to form a “summary.” | |
| # Because abstractive summarization involves paraphrasing words, it is also more time-consuming; | |
| # however, it has the potential to produce a more polished and coherent summary. | |
| # from transformers import PegasusForConditionalGeneration, PegasusTokenizer | |
| # import gradio as grad | |
| # mdl_name = "google/pegasus-xsum" | |
| # pegasus_tkn = PegasusTokenizer.from_pretrained(mdl_name) | |
| # mdl = PegasusForConditionalGeneration.from_pretrained(mdl_name) | |
| # def summarize(text): | |
| # tokens = pegasus_tkn(text, truncation=True, padding="longest", return_tensors="pt") | |
| # txt_summary = mdl.generate(**tokens) | |
| # response = pegasus_tkn.batch_decode(txt_summary, skip_special_tokens=True) | |
| # return response | |
| # txt = grad.Textbox(lines=10, label="English", placeholder="English Text here") | |
| # out = grad.Textbox(lines=10, label="Summary") | |
| # grad.Interface(summarize, inputs=txt, outputs=out).launch() | |
| #------------------------------------------------------------------------------------------ | |
| # 6. Same model with some tuning with some parameters: num_return_sequences=5, max_length=200, temperature=1.5, num_beams=10 | |
| # from transformers import PegasusForConditionalGeneration, PegasusTokenizer | |
| # import gradio as grad | |
| # mdl_name = "google/pegasus-xsum" | |
| # pegasus_tkn = PegasusTokenizer.from_pretrained(mdl_name) | |
| # mdl = PegasusForConditionalGeneration.from_pretrained(mdl_name) | |
| # def summarize(text): | |
| # tokens = pegasus_tkn(text, truncation=True, padding="longest", return_tensors="pt") | |
| # translated_txt = mdl.generate(**tokens, num_return_sequences=5, max_length=200, temperature=1.5, num_beams=10) | |
| # response = pegasus_tkn.batch_decode(translated_txt, skip_special_tokens=True) | |
| # return response | |
| # txt = grad.Textbox(lines=10, label="English", placeholder="English Text here") | |
| # out = grad.Textbox(lines=10, label="Summary") | |
| # grad.Interface(summarize, inputs=txt, outputs=out).launch() | |
| #----------------------------------------------------------------------------------- | |
| # 7. Zero-Shot Learning: | |
| # Zero-shot learning, as the name implies, is to use a pretrained model , trained on a certain set of data, | |
| # on a different set of data, which it has not seen during training. This would mean, as an example, to take | |
| # some model from huggingface that is trained on a certain dataset and use it for inference on examples it has never seen before. | |
| # The transformers are where the zero-shot classification implementations are most frequently found by us. | |
| # There are more than 60 transformer models that function based on the zero-shot classification that are found in the huggingface library. | |
| # When we discuss zero-shot text classification , there is one additional thing that springs to mind. | |
| # In the same vein as zero-shot classification is few-shot classification, which is very similar to zero-shot classification. | |
| # However, in contrast with zero-shot classification, few-shot classification makes use of very few labeled samples during the training process. | |
| # The implementation of the few-shot classification methods can be found in OpenAI, where the GPT3 classifier is a well-known example of a few-shot classifier. | |
| # Deploying the following code works but comes with a warning: "No model was supplied, defaulted to facebook/bart-large-mnli and revision c626438 (https://huggingface.co/facebook/bart-large-mnli). | |
| # Using a pipeline without specifying a model name and revision in production is not recommended." | |
| # from transformers import pipeline | |
| # import gradio as grad | |
| # zero_shot_classifier = pipeline("zero-shot-classification") | |
| # def classify(text,labels): | |
| # classifer_labels = labels.split(",") | |
| # #["software", "politics", "love", "movies", "emergency", "advertisment","sports"] | |
| # response = zero_shot_classifier(text,classifer_labels) | |
| # return response | |
| # txt=grad.Textbox(lines=1, label="English", placeholder="text to be classified") | |
| # labels=grad.Textbox(lines=1, label="Labels", placeholder="comma separated labels") | |
| # out=grad.Textbox(lines=1, label="Classification") | |
| # grad.Interface(classify, inputs=[txt,labels], outputs=out).launch() | |
| #----------------------------------------------------------------------------------- | |
| # 8. Text Generation Task/Models | |
| # The earliest text generation models were based on Markov chains . Markov chains are like a state machine wherein | |
| # using only the previous state, the next state is predicted. This is similar also to what we studied in bigrams. | |
| # Post the Markov chains, recurrent neural networks (RNNs) , which were capable of retaining a greater context of the text, were introduced. | |
| # They are based on neural network architectures that are recurrent in nature. RNNs are able to retain a greater context of the text that was introduced. | |
| # Nevertheless, the amount of information that these kinds of networks are able to remember is constrained, and it is also difficult to train them, | |
| # which means that they are not effective at generating lengthy texts. To counter this issue with RNNs, LSTM architectures were evolved, | |
| # which could capture long-term dependencies in text. Finally, we came to transformers, whose decoder architecture became popular for generative models | |
| # used for generating text as an example. | |
| 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() | |