diff --git a/README.md b/README.md
index e9d93daf..798b7bd4 100644
--- a/README.md
+++ b/README.md
@@ -145,7 +145,7 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
 | [BLOOMZ](https://huggingface.co/bigscience)              | 560M/1.1B/1.7B/3B/7.1B/176B      | query_key_value   | -         |
 | [ChatGLM3](https://huggingface.co/THUDM)                 | 6B                               | query_key_value   | chatglm3  |
 | [Command-R](https://huggingface.co/CohereForAI)          | 35B/104B                         | q_proj,v_proj     | cohere    |
-| [DeepSeek (MoE)](https://huggingface.co/deepseek-ai)     | 7B/16B/67B                       | q_proj,v_proj     | deepseek  |
+| [DeepSeek (MoE)](https://huggingface.co/deepseek-ai)     | 7B/16B/67B/236B                  | q_proj,v_proj     | deepseek  |
 | [Falcon](https://huggingface.co/tiiuae)                  | 7B/40B/180B                      | query_key_value   | falcon    |
 | [Gemma/CodeGemma](https://huggingface.co/google)         | 2B/7B                            | q_proj,v_proj     | gemma     |
 | [InternLM2](https://huggingface.co/internlm)             | 7B/20B                           | wqkv              | intern2   |
diff --git a/README_zh.md b/README_zh.md
index 15758ae4..2c5b1aa1 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -145,7 +145,7 @@ https://github.com/hiyouga/LLaMA-Factory/assets/16256802/ec36a9dd-37f4-4f72-81bd
 | [BLOOMZ](https://huggingface.co/bigscience)              | 560M/1.1B/1.7B/3B/7.1B/176B      | query_key_value   | -         |
 | [ChatGLM3](https://huggingface.co/THUDM)                 | 6B                               | query_key_value   | chatglm3  |
 | [Command-R](https://huggingface.co/CohereForAI)          | 35B/104B                         | q_proj,v_proj     | cohere    |
-| [DeepSeek (MoE)](https://huggingface.co/deepseek-ai)     | 7B/16B/67B                       | q_proj,v_proj     | deepseek  |
+| [DeepSeek (MoE)](https://huggingface.co/deepseek-ai)     | 7B/16B/67B/236B                  | q_proj,v_proj     | deepseek  |
 | [Falcon](https://huggingface.co/tiiuae)                  | 7B/40B/180B                      | query_key_value   | falcon    |
 | [Gemma/CodeGemma](https://huggingface.co/google)         | 2B/7B                            | q_proj,v_proj     | gemma     |
 | [InternLM2](https://huggingface.co/internlm)             | 7B/20B                           | wqkv              | intern2   |
diff --git a/assets/wechat.jpg b/assets/wechat.jpg
index 0e17295a..d251f405 100644
Binary files a/assets/wechat.jpg and b/assets/wechat.jpg differ
diff --git a/requirements.txt b/requirements.txt
index f4818ed2..67bd7033 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -13,7 +13,7 @@ uvicorn
 pydantic
 fastapi
 sse-starlette
-matplotlib
+matplotlib>=3.7.0
 fire
 packaging
 pyyaml
diff --git a/setup.py b/setup.py
index 7b849942..ddc3a594 100644
--- a/setup.py
+++ b/setup.py
@@ -21,7 +21,7 @@ def get_requires():
 
 extra_require = {
     "metrics": ["nltk", "jieba", "rouge-chinese"],
-    "deepspeed": ["deepspeed>=0.10.0"],
+    "deepspeed": ["deepspeed>=0.10.0,<=0.14.0"],
     "bitsandbytes": ["bitsandbytes>=0.39.0"],
     "vllm": ["vllm>=0.4.0"],
     "galore": ["galore-torch"],
diff --git a/src/llmtuner/extras/constants.py b/src/llmtuner/extras/constants.py
index bf542e69..e055f1f3 100644
--- a/src/llmtuner/extras/constants.py
+++ b/src/llmtuner/extras/constants.py
@@ -324,6 +324,14 @@ register_model_group(
             DownloadSource.DEFAULT: "deepseek-ai/deepseek-moe-16b-chat",
             DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-moe-16b-chat",
         },
+        "DeepSeek-MoE-236B": {
+            DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-V2",
+            DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-V2",
+        },
+        "DeepSeek-MoE-236B-Chat": {
+            DownloadSource.DEFAULT: "deepseek-ai/DeepSeek-V2-Chat",
+            DownloadSource.MODELSCOPE: "deepseek-ai/DeepSeek-V2-Chat",
+        },
     },
     template="deepseek",
 )
@@ -569,6 +577,10 @@ register_model_group(
             DownloadSource.DEFAULT: "meta-llama/Meta-Llama-3-70B-Instruct",
             DownloadSource.MODELSCOPE: "LLM-Research/Meta-Llama-3-70B-Instruct",
         },
+        "LLaMA3-8B-Chinese-Chat": {
+            DownloadSource.DEFAULT: "shenzhi-wang/Llama3-8B-Chinese-Chat",
+            DownloadSource.MODELSCOPE: "LLM-Research/Llama3-8B-Chinese-Chat",
+        },
     },
     template="llama3",
 )
diff --git a/src/llmtuner/model/utils/valuehead.py b/src/llmtuner/model/utils/valuehead.py
index a192dcfa..a6180753 100644
--- a/src/llmtuner/model/utils/valuehead.py
+++ b/src/llmtuner/model/utils/valuehead.py
@@ -57,3 +57,7 @@ def prepare_valuehead_model(model: "PreTrainedModel") -> None:
     if getattr(model.config, "model_type", None) == "chatglm":
         setattr(model, "lm_head", model.transformer.output_layer)
         setattr(model, "_keys_to_ignore_on_save", ["lm_head.weight"])
+
+    if getattr(model.config, "model_type", None) == "internlm2":
+        setattr(model, "lm_head", model.output)
+        setattr(model, "_keys_to_ignore_on_save", ["lm_head.weight"])