From 2c8997bc99ddfc65022c215952679620c788564a Mon Sep 17 00:00:00 2001
From: Nagico2 <nagico@qq.com>
Date: Thu, 25 Jul 2024 17:55:24 +0800
Subject: [PATCH] Add the position_imbeddings param to LlamaAttention.forward
 (#105)

* fix: add position_embeddings args to LlamaAttention

a new arg here: https://github.com/huggingface/transformers/blame/main/src/transformers/models/llama/modeling_llama.py#L316

* feat: update transformers version

* style: fix incorrect style

---------

Co-authored-by: Alessandro Palla <alessandro.palla@intel.com>
---
 requirements.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/requirements.txt b/requirements.txt
index d22de26..14609e2 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,4 +1,4 @@
 numpy
 torch
-transformers>=4.39.3
+transformers>=4.43.0
 neural-compressor
\ No newline at end of file