from transformers import GPTNeoXForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained(
    "afterless/reverse-pythia-160m"
)
model = GPTNeoXForCausalLM.from_pretrained(
    "afterless/reverse-pythia-160m"
)

inputs = tokenizer(
    "but I told him, the cheese was the best",
    return_token_type_ids=False,
    return_tensors="pt"
)
inputs['input_ids'] = t.flip(inputs.input_ids, (1,))
tokens = t.flip(model.generate(**inputs), (1,))
tokenizer.decode(tokens[0])

Downloads last month: 1,106

Inference Examples

Text Generation

This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

afterless
/

reverse-pythia-160m

Dataset used to train afterless/reverse-pythia-160m