- Joined
- Apr 16, 2023
- Messages
- 11
- Reaction score
- 0
- Points
- 1
So, you want to create your own AI like ChatGPT? Well, test it and let me know if it works. Worked great for me but I know there's way more to coding an AI than just this little bit of sample code.
COPIED CODE:
import tensorflow as tf
from transformers import GPT2Tokenizer, TFGPT2LMHeadModel
tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
model = TFGPT2LMHeadModel.from_pretrained("gpt2", pad_token_id=tokenizer.eos_token_id)
def generate_text(prompt):
input_ids = tokenizer.encode(prompt, return_tensors='tf')
output = model.generate(input_ids, max_length=1024, num_return_sequences=1, no_repeat_ngram_size=2)
return tokenizer.decode(output[0], skip_special_tokens=True)
PROMPT TEST CODE:
output_text = generate_text("Hello, how are you today?")
print(output_text)
Courtesy: Brennan Jeremy
√
COPIED CODE:
import tensorflow as tf
from transformers import GPT2Tokenizer, TFGPT2LMHeadModel
tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
model = TFGPT2LMHeadModel.from_pretrained("gpt2", pad_token_id=tokenizer.eos_token_id)
def generate_text(prompt):
input_ids = tokenizer.encode(prompt, return_tensors='tf')
output = model.generate(input_ids, max_length=1024, num_return_sequences=1, no_repeat_ngram_size=2)
return tokenizer.decode(output[0], skip_special_tokens=True)
PROMPT TEST CODE:
output_text = generate_text("Hello, how are you today?")
print(output_text)
Courtesy: Brennan Jeremy
√
