diff --git a/docs/source/en/model_doc/minimax.md b/docs/source/en/model_doc/minimax.md
index a8c5ee1b236..7ae1ca67003 100644
--- a/docs/source/en/model_doc/minimax.md
+++ b/docs/source/en/model_doc/minimax.md
@@ -18,7 +18,7 @@ rendered properly in your Markdown viewer.
 
 ## Overview
 
-The DepthPro model was proposed in [MiniMax-01: Scaling Foundation Models with Lightning Attention](https://arxiv.org/abs/2501.08313) by MiniMax, Aonian Li, Bangwei Gong, Bo Yang, Boji Shan, Chang Liu, Cheng Zhu, Chunhao Zhang, Congchao Guo, Da Chen, Dong Li, Enwei Jiao, Gengxin Li, Guojun Zhang, Haohai Sun, Houze Dong, Jiadai Zhu, Jiaqi Zhuang, Jiayuan Song, Jin Zhu, Jingtao Han, Jingyang Li, Junbin Xie, Junhao Xu, Junjie Yan, Kaishun Zhang, Kecheng Xiao, Kexi Kang, Le Han, Leyang Wang, Lianfei Yu, Liheng Feng, Lin Zheng, Linbo Chai, Long Xing, Meizhi Ju, Mingyuan Chi, Mozhi Zhang, Peikai Huang, Pengcheng Niu, Pengfei Li, Pengyu Zhao, Qi Yang, Qidi Xu, Qiexiang Wang, Qin Wang, Qiuhui Li, Ruitao Leng, Shengmin Shi, Shuqi Yu, Sichen Li, Songquan Zhu, Tao Huang, Tianrun Liang, Weigao Sun, Weixuan Sun, Weiyu Cheng, Wenkai Li, Xiangjun Song, Xiao Su, Xiaodong Han, Xinjie Zhang, Xinzhu Hou, Xu Min, Xun Zou, Xuyang Shen, Yan Gong, Yingjie Zhu, Yipeng Zhou, Yiran Zhong, Yongyi Hu, Yuanxiang Fan, Yue Yu, Yufeng Yang, Yuhao Li, Yunan Huang, Yunji Li, Yunpeng Huang, Yunzhi Xu, Yuxin Mao, Zehan Li, Zekang Li, Zewei Tao, Zewen Ying, Zhaoyang Cong, Zhen Qin, Zhenhua Fan, Zhihang Yu, Zhuo Jiang, Zijia Wu.
+The MiniMax-Text-01 model was proposed in [MiniMax-01: Scaling Foundation Models with Lightning Attention](https://arxiv.org/abs/2501.08313) by MiniMax, Aonian Li, Bangwei Gong, Bo Yang, Boji Shan, Chang Liu, Cheng Zhu, Chunhao Zhang, Congchao Guo, Da Chen, Dong Li, Enwei Jiao, Gengxin Li, Guojun Zhang, Haohai Sun, Houze Dong, Jiadai Zhu, Jiaqi Zhuang, Jiayuan Song, Jin Zhu, Jingtao Han, Jingyang Li, Junbin Xie, Junhao Xu, Junjie Yan, Kaishun Zhang, Kecheng Xiao, Kexi Kang, Le Han, Leyang Wang, Lianfei Yu, Liheng Feng, Lin Zheng, Linbo Chai, Long Xing, Meizhi Ju, Mingyuan Chi, Mozhi Zhang, Peikai Huang, Pengcheng Niu, Pengfei Li, Pengyu Zhao, Qi Yang, Qidi Xu, Qiexiang Wang, Qin Wang, Qiuhui Li, Ruitao Leng, Shengmin Shi, Shuqi Yu, Sichen Li, Songquan Zhu, Tao Huang, Tianrun Liang, Weigao Sun, Weixuan Sun, Weiyu Cheng, Wenkai Li, Xiangjun Song, Xiao Su, Xiaodong Han, Xinjie Zhang, Xinzhu Hou, Xu Min, Xun Zou, Xuyang Shen, Yan Gong, Yingjie Zhu, Yipeng Zhou, Yiran Zhong, Yongyi Hu, Yuanxiang Fan, Yue Yu, Yufeng Yang, Yuhao Li, Yunan Huang, Yunji Li, Yunpeng Huang, Yunzhi Xu, Yuxin Mao, Zehan Li, Zekang Li, Zewei Tao, Zewen Ying, Zhaoyang Cong, Zhen Qin, Zhenhua Fan, Zhihang Yu, Zhuo Jiang, Zijia Wu.
 
 The abstract from the paper is the following:
 
@@ -148,8 +148,8 @@ Quantizing a model is as simple as passing a `quantization_config` to the model.
 "The expected output"
 ```
 
-This model was contributed by [geetu040](https://github.com/geetu040).
-The original code can be found [here](https://huggingface.co/MiniMaxAI/MiniMax-Text-01-hf/blob/main/modeling_minimax.py).
+This model was contributed by [geetu040](https://github.com/geetu040) and [Shakib-IO](https://github.com/Shakib-IO).
+The original code can be found [here](https://huggingface.co/MiniMaxAI/MiniMax-Text-01/blob/main/modeling_minimax_text_01.py).
 
 ## Resources
 
diff --git a/tests/models/minimax/test_modeling_minimax.py b/tests/models/minimax/test_modeling_minimax.py
index 2d03b01f736..eee66461279 100644
--- a/tests/models/minimax/test_modeling_minimax.py
+++ b/tests/models/minimax/test_modeling_minimax.py
@@ -243,7 +243,7 @@ class MiniMaxModelTest(CausalLMModelTest, unittest.TestCase):
 @slow
 class MiniMaxIntegrationTest(unittest.TestCase):
     def test_small_model_logits(self):
-        model_id = "geetu040/MiniMax-tiny"
+        model_id = "hf-internal-testing/MiniMax-tiny"
         dummy_input = torch.LongTensor([[0, 1, 0], [0, 1, 0]]).to(torch_device)
 
         model = MiniMaxForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, low_cpu_mem_usage=True).to(
@@ -262,7 +262,7 @@ class MiniMaxIntegrationTest(unittest.TestCase):
         torch.testing.assert_close(logits[1, :3, :3], expected_slice, atol=1e-3, rtol=1e-3)
 
     def test_small_model_generation(self):
-        model_id = "geetu040/MiniMax-tiny"
+        model_id = "hf-internal-testing/MiniMax-tiny"
         dummy_input = torch.LongTensor([[0, 1, 0], [0, 1, 0]]).to(torch_device)
 
         model = MiniMaxForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16, low_cpu_mem_usage=True).to(