SYMBOL INDEX (30 symbols across 5 files) FILE: bench.py function get_batch (line 37) | def get_batch(split): FILE: data/openwebtext/prepare.py function process (line 43) | def process(example): FILE: data/shakespeare_char/prepare.py function encode (line 32) | def encode(s): function decode (line 34) | def decode(l): FILE: model.py class LayerNorm (line 18) | class LayerNorm(nn.Module): method __init__ (line 21) | def __init__(self, ndim, bias): method forward (line 26) | def forward(self, input): class CausalSelfAttention (line 29) | class CausalSelfAttention(nn.Module): method __init__ (line 31) | def __init__(self, config): method forward (line 52) | def forward(self, x): class MLP (line 78) | class MLP(nn.Module): method __init__ (line 80) | def __init__(self, config): method forward (line 87) | def forward(self, x): class Block (line 94) | class Block(nn.Module): method __init__ (line 96) | def __init__(self, config): method forward (line 103) | def forward(self, x): class GPTConfig (line 109) | class GPTConfig: class GPT (line 118) | class GPT(nn.Module): method __init__ (line 120) | def __init__(self, config): method get_num_params (line 150) | def get_num_params(self, non_embedding=True): method _init_weights (line 162) | def _init_weights(self, module): method forward (line 170) | def forward(self, idx, targets=None): method crop_block_size (line 195) | def crop_block_size(self, block_size): method from_pretrained (line 207) | def from_pretrained(cls, model_type, override_args=None): method configure_optimizers (line 263) | def configure_optimizers(self, weight_decay, learning_rate, betas, dev... method estimate_mfu (line 289) | def estimate_mfu(self, fwdbwd_per_iter, dt): method generate (line 306) | def generate(self, idx, max_new_tokens, temperature=1.0, top_k=None): FILE: train.py function get_batch (line 116) | def get_batch(split): function estimate_loss (line 216) | def estimate_loss(): function get_lr (line 231) | def get_lr(it):