tacit/nanochat
1
0
Fork 0
mirror of https://github.com/karpathy/nanochat.git synced 2026-01-20 18:34:14 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

remove spurious cast, gets compiled away anyway but it's confusing people

Browse Source
This commit is contained in:
Andrej Karpathy 2025-12-27 23:07:48 +00:00
parent 49389ecaa8
commit e1770a3061
1 changed files with 2 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
nanochat/gpt.py
View File

@ -41,12 +41,10 @@ def norm(x):
def apply_rotary_emb(x, cos, sin):
assert x.ndim == 4 # multihead attention
d = x.shape[3] // 2
x1, x2 = x[..., :d], x[..., d:] # split up last time into two halves
x1, x2 = x[..., :d], x[..., d:] # split up last dim into two halves
y1 = x1 * cos + x2 * sin # rotate pairs of dims
y2 = x1 * (-sin) + x2 * cos
out = torch.cat([y1, y2], 3) # re-assemble
out = out.to(x.dtype) # ensure input/output dtypes match
return out
return torch.cat([y1, y2], 3)
class CausalSelfAttention(nn.Module):
def __init__(self, config, layer_idx):