generated_from_trainer

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

GPT-Neo za Generiranje Fiktivnih Priča/ GPT-Neo for Fiction Story Generation

Ovaj model je fino podešena verzija EleutherAI-jevog GPT-Neo-125M modela, optimiziran za generiranje fikcijskih priča. Obučen je na skupu podataka dostupnom na https://github.com/facebookresearch/fairseq/tree/main/examples/stories.

Opis modela

Upotrebe i ograničenja

Model je dizajniran za generiranje kreativnih fiktivnih priča. Može se koristiti u razne svrhe, uključujući, ali ne ograničavajući se na:

Performanse Modela

Ograničenja

Upotreba

from transformers import GPTNeoForCausalLM, GPT2Tokenizer

tokenizer = GPT2Tokenizer.from_pretrained(Tincando/fiction_story_generator)
model = GPTNeoForCausalLM.from_pretrained(Tincando/fiction_story_generator)

# Generate a fiction story
input_prompt = "[WP] I can't believe I died the same way twice."
input_ids = tokenizer(input_prompt, add_special_tokens=False, return_tensors="pt").input_ids

output = model.generate(input_ids,
        max_length=300,
        temperature=0.9,
        top_k=2,
        top_p=0.9,
        repetition_penalty=1.2,
        do_sample=True,
        num_return_sequences=2
)

generated_story = tokenizer.batch_decode(output,clean_up_tokenization_spaces=True)[0]
print(generated_story)

Etika

Prilikom korištenja ovog modela, razmotrite sljedeće etičke smjernice:

Citiranje

Ako koristite GPT-Neo-Fiction u svojem radu, molimo razmislite o citiranju originalnog GPT-Neo modela i skupa podataka koji su korišteni za fino podešavanje:

Training hyperparameters

The following hyperparameters were used during training:

Training results

Training Loss Epoch Step Validation Loss
3.0842 1.0 34075 3.1408
3.0026 2.0 68150 3.1275
2.9344 3.0 102225 3.1270
2.8932 4.0 136300 3.1306
2.8517 5.0 170375 3.1357

Framework versions