From 7be801ff8d9359115179d57adaa0c050ee4238fa Mon Sep 17 00:00:00 2001
From: Daniel Han-Chen <danielhanchen@gmail.com>
Date: Sun, 21 Jan 2024 19:10:48 +1100
Subject: [PATCH] Update llama.py

---
 unsloth/models/llama.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py
index 6f9006474f..fab0689fa6 100644
--- a/unsloth/models/llama.py
+++ b/unsloth/models/llama.py
@@ -105,7 +105,6 @@ def LlamaAttention_fast_forward_inference(
     Xn = hidden_states
     bsz, _, _ = hidden_states.size()
     K1, V1 = past_key_value
-    print(1)
 
     n_heads    = self.num_heads
     n_groups   = self.num_key_value_groups
@@ -305,9 +304,9 @@ 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()
+    print(hidden_states.size())
 
     if (past_key_value is not None and q_len == 1):
-        print(1)
         # Self Attention
         residual = hidden_states
         hidden_states = fast_rms_layernorm_inference(self.input_layernorm, hidden_states)