jackdoczy/Generating_Messages_Assignment

#This prompt is from message 2. #The goal is to generate 100 messages per prompt.

prompt2 = "Vaping is risky"

#Below, we specify to use pytorch machine learning framework. #You can also choose Tensorflow, but we use Pytorch here.

inputs = tokenizer(prompt2, return_tensors="pt")

#We generate 50 messages each time due to restrictions in Ram storage.

sample_outputs = bloom.generate(inputs["input_ids"], temperature = 0.7, max_new_tokens = 60, do_sample=True, top_k=40, top_p=0.9, num_return_sequences=50 )

print("Output:\n" + 100 * '-') messages = [] for i, sample_output in enumerate(sample_outputs): generated_messages = tokenizer.decode(sample_output, skip_special_tokens=True) print("{}: {}".format(i, generated_messages)) messages.append(generated_messages)

print(messages)

#We save the AI-generated messages to google drive.

AI_messages = pd.DataFrame(messages, columns = ['tweet']) AI_messages.to_csv('Vaping is risky1.csv', index = False)

#Then generate another 50 messages with prompt1 and then save to google drive.

AI_messages = pd.DataFrame(messages, columns = ['tweet']) AI_messages.to_csv('Vaping is risky2.csv', index = False)

#This prompt is from message 3. #The goal is to generate 100 messages per prompt.

prompt3 = "Vapes and e-cigarettes increase your risk"

#Below, we specify to use pytorch machine learning framework. #You can also choose Tensorflow, but we use Pytorch here.

inputs = tokenizer(prompt3, return_tensors="pt")

#We generate 50 messages each time due to restrictions in Ram storage.

sample_outputs = bloom.generate(inputs["input_ids"], temperature = 0.7, max_new_tokens = 60, do_sample=True, top_k=40, top_p=0.9, num_return_sequences=50 )

print("Output:\n" + 100 * '-') messages = [] for i, sample_output in enumerate(sample_outputs): generated_messages = tokenizer.decode(sample_output, skip_special_tokens=True) print("{}: {}".format(i, generated_messages)) messages.append(generated_messages)

print(messages)

#We save the AI-generated messages to google drive.

AI_messages = pd.DataFrame(messages, columns = ['tweet']) AI_messages.to_csv('Vapes and e-cigarettes increase your risk1.csv', index = False)