ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update gemma.py

Browse source
This commit is contained in:
Daniel Han-Chen 2024-02-25 03:19:34 +11:00
commit 20da5547f5
1 changed files with 6 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

11
unsloth/models/gemma.py
View file

@ -93,10 +93,8 @@ class FastGemmaRotaryEmbedding(torch.nn.Module):
if length > self.max_seq_len_cached:
self._set_cos_sin_cache(seq_len=length, device=x.device, dtype=x.dtype)
return (
self.cos_cached[:seq_len].to(dtype=x.dtype),
self.sin_cached[:seq_len].to(dtype=x.dtype),
)
old_cos = self.cos_cached[:seq_len].to(dtype=x.dtype)
old_sin = self.sin_cached[:seq_len].to(dtype=x.dtype)
# x: [bs, num_attention_heads, seq_len, head_size]
if self.inv_freq is None:
@ -111,7 +109,10 @@ class FastGemmaRotaryEmbedding(torch.nn.Module):
emb = torch.cat((freqs, freqs), dim=-1)
seq_len = position_ids.shape[1]
return emb.cos().to(dtype=x.dtype)[:seq_len], emb.sin().to(dtype=x.dtype)[:seq_len]
new_cos = emb.cos().to(dtype=x.dtype)[:seq_len]
new_sin = emb.sin().to(dtype=x.dtype)[:seq_len]
logger.warning_once(str(torch.dist(new_cos, old_cos)))
pass