def get_model(rebuild=False):
set_seed(42)
if not rebuild:
try:
model = torch.load(MODEL_PATH)
print(f"resuming from existing model at {MODEL_PATH}")
return model
except FileNotFoundError:
pass
print("constructing new model")
conf = GPTConfig(VOCAB_SIZE, BLOCK_SIZE, n_layer=2, n_head=4, n_embd=128)
model = GPT(conf)
return model
#!/usr/bin/env python
# set up logging
import logging
logging.basicConfig(
format="%(asctime)s - %(levelname)s - %(name)s - %(message)s",
datefmt="%m/%d/%Y %H:%M:%S",
level=logging.INFO,
)
# make deterministic
from mingpt.utils import set_seed
set_seed(42)
import numpy as np
import torch
import torch.nn as nn
from torch.nn import functional as F
import math
from torch.utils.data import Dataset
class CharDataset(Dataset):
def __init__(self, data, block_size):
chars = sorted(list(set(data)))
data_size, vocab_size = len(data), len(chars)
print('data has %d characters, %d unique.' % (data_size, vocab_size))
self.stoi = {ch: i for i, ch in enumerate(chars)}
self.itos = {i: ch for i, ch in enumerate(chars)}
self.block_size = block_size
from torch.utils.data import Dataset
from mingpt.utils import set_seed, sample
from mingpt.model import GPT, GPTConfig
from mingpt.trainer import Trainer, TrainerConfig
import os
logging.basicConfig(
format='%(asctime)s|%(levelname)s|%(name)s|%(message)s',
datefmt='%Y-%d-%d %H:%M:%S',
level=logging.INFO,
)
set_seed(42) # make deterministic
GPT_S = dict(
embd_pdrop=0.0,
resid_pdrop=0.0,
attn_pdrop=0.0,
n_layer=24,
n_head=8,
n_embd=512,
)
def now_utc(): # unix time
seconds = round(time.time())
millis = seconds * 1000
unix = int(millis)
