File size: 1,401 Bytes
f8bd6fe | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 | """Transformers implementation used to package Pollock SwiGLU checkpoints."""
import torch.nn as nn
import torch.nn.functional as F
from transformers import GPT2Config, GPT2LMHeadModel
from transformers.pytorch_utils import Conv1D
class PollockConfig(GPT2Config):
model_type = "pollock"
def __init__(self, mlp_variant="swiglu", **kwargs):
super().__init__(**kwargs)
self.mlp_variant = mlp_variant
class PollockSwiGLU(nn.Module):
def __init__(self, config):
super().__init__()
n_inner = config.n_inner or 4 * config.hidden_size
self.c_fc = Conv1D(2 * n_inner, config.hidden_size)
self.c_proj = Conv1D(config.hidden_size, n_inner)
self.dropout = nn.Dropout(config.resid_pdrop)
def forward(self, hidden_states):
gate, value = self.c_fc(hidden_states).chunk(2, dim=-1)
hidden_states = F.silu(gate) * value
return self.dropout(self.c_proj(hidden_states))
class PollockForCausalLM(GPT2LMHeadModel):
config_class = PollockConfig
def __init__(self, config):
if config.mlp_variant != "swiglu":
raise ValueError(
f"PollockForCausalLM requires SwiGLU, got {config.mlp_variant!r}"
)
super().__init__(config)
for block in self.transformer.h:
block.mlp = PollockSwiGLU(config)
block.mlp.apply(self._init_weights)
|