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

Update llama.py

Browse source
This commit is contained in:
Daniel Han-Chen 2024-01-27 04:47:42 +11:00
commit bd2ff90817
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
unsloth/models/llama.py
View file

@ -234,7 +234,7 @@ def LlamaAttention_fast_forward(
bsz, q_len, _ = hidden_states.size()
# Check for inference
if False:#past_key_value is not None and q_len == 1 and bsz == 1:
if past_key_value is not None and q_len == 1 and bsz == 1:
A, past_key_value = LlamaAttention_fast_forward_inference(
self,
hidden_states,
@ -350,7 +350,7 @@ def LlamaDecoderLayer_fast_forward(
past_key_value (`Tuple(torch.FloatTensor)`, *optional*): cached past key and value projection states
"""
bsz, q_len, hd = hidden_states.size()
if False:#(past_key_value is not None and q_len == 1 and bsz == 1):
if (past_key_value is not None and q_len == 1 and bsz == 1):
# Self Attention
residual = hidden_states
hidden_states = fast_rms_layernorm_inference(self.input_layernorm, hidden_states)