Merge pull request #1 from Dianababaei/feat/gpt-add-kvcache-import

Update GPT model configuration and initialization parameters in GPTConfig class
This commit is contained in:
Dianababaei 2025-11-03 13:26:17 +03:30 committed by GitHub
commit d44a3e090f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -22,6 +22,7 @@ import torch.nn.functional as F
from nanochat.common import get_dist_info, print0
from nanochat.muon import Muon, DistMuon
from nanochat.adamw import DistAdamW
from nanochat.engine import KVCache
@dataclass
class GPTConfig: