60行代码就能构建GPT！网友：比之前的教程都要清晰

def generate(inputs, n_tokens_to_generate):
    for _ in range(n_tokens_to_generate): # auto-regressive decode loop
        output = gpt(inputs) # model forward pass
        next_id = np.argmax(output[-1]) # greedy sampling
        inputs = np.append(out, [next_id]) # append prediction to input
    return list(inputs[len(inputs) - n_tokens_to_generate :])  # only return generated ids

input_ids = [1, 0] # "not" "all"
output_ids = generate(input_ids, 3) # output_ids = [2, 4, 6]
output_tokens = [vocab[i] for i in output_ids] # "heroes" "wear" "capes"

import numpy as np


def gpt2(inputs, wte, wpe, blocks, ln_f, n_head):
    pass # TODO: implement this


def generate(inputs, params, n_head, n_tokens_to_generate):
    from tqdm import tqdm

    for _ in tqdm(range(n_tokens_to_generate), "generating"):  # auto-regressive decode loop
        logits = gpt2(inputs, **params, n_head=n_head)  # model forward pass
        next_id = np.argmax(logits[-1])  # greedy sampling
        inputs = np.append(inputs, [next_id])  # append prediction to input

    return list(inputs[len(inputs) - n_tokens_to_generate :])  # only return generated ids


def main(prompt: str, n_tokens_to_generate: int = 40, model_size: str = "124M", models_dir: str = "models"):
    from utils import load_encoder_hparams_and_params

    # load encoder, hparams, and params from the released open-ai gpt-2 files
    encoder, hparams, params = load_encoder_hparams_and_params(model_size, models_dir)

    # encode the input string using the BPE tokenizer
    input_ids = encoder.encode(prompt)

    # make sure we are not surpassing the max sequence length of our model
    assert len(input_ids) + n_tokens_to_generate < hparams["n_ctx"]

    # generate output ids
    output_ids = generate(input_ids, params, hparams["n_head"], n_tokens_to_generate)

    # decode the ids back into a string
    output_text = encoder.decode(output_ids)

    return output_text


if name == "__main__":
    import fire

    fire.Fire(main)

from utils import load_encoder_hparams_and_params
encoder, hparams, params = load_encoder_hparams_and_params("124M", "models")

def gpt2(inputs, wte, wpe, blocks, ln_f, n_head):  # [n_seq] -> [n_seq, n_vocab]
    # token + positional embeddings
    x = wte[inputs] + wpe[range(len(inputs))]  # [n_seq] -> [n_seq, n_embd]

    # forward pass through n_layer transformer blocks
    for block in blocks:
        x = transformer_block(x, block, n_head=n_head)  # [n_seq, n_embd] -> [n_seq, n_embd]

    # projection to vocab
    x = layer_norm(x, ln_f)  # [n_seq, n_embd] -> [n_seq, n_embd]
    return x @ wte.T  # [n_seq, n_embd] -> [n_seq, n_vocab]

python gpt2.py \
    "Alan Turing theorized that computers would one day become" \
    --n_tokens_to_generate 8

the most powerful machines on the planet.