diff --git a/README.md b/README.md
index 144908c1..e62a9d47 100644
--- a/README.md
+++ b/README.md
@@ -162,34 +162,36 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
 
 ## Supported Models
 
-| Model                                                             | Model size                       | Template  |
-| ----------------------------------------------------------------- | -------------------------------- | --------- |
-| [Baichuan 2](https://huggingface.co/baichuan-inc)                 | 7B/13B                           | baichuan2 |
-| [BLOOM/BLOOMZ](https://huggingface.co/bigscience)                 | 560M/1.1B/1.7B/3B/7.1B/176B      | -         |
-| [ChatGLM3](https://huggingface.co/THUDM)                          | 6B                               | chatglm3  |
-| [Command R](https://huggingface.co/CohereForAI)                   | 35B/104B                         | cohere    |
-| [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai)         | 7B/16B/67B/236B                  | deepseek  |
-| [Falcon](https://huggingface.co/tiiuae)                           | 7B/11B/40B/180B                  | falcon    |
-| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google)          | 2B/7B/9B/27B                     | gemma     |
-| [GLM-4](https://huggingface.co/THUDM)                             | 9B                               | glm4      |
-| [InternLM2/InternLM2.5](https://huggingface.co/internlm)          | 7B/20B                           | intern2   |
-| [Llama](https://github.com/facebookresearch/llama)                | 7B/13B/33B/65B                   | -         |
-| [Llama 2](https://huggingface.co/meta-llama)                      | 7B/13B/70B                       | llama2    |
-| [Llama 3-3.2](https://huggingface.co/meta-llama)                  | 1B/3B/8B/70B                     | llama3    |
-| [LLaVA-1.5](https://huggingface.co/llava-hf)                      | 7B/13B                           | llava     |
-| [MiniCPM](https://huggingface.co/openbmb)                         | 1B/2B/4B                         | cpm/cpm3  |
-| [Mistral/Mixtral](https://huggingface.co/mistralai)               | 7B/8x7B/8x22B                    | mistral   |
-| [OLMo](https://huggingface.co/allenai)                            | 1B/7B                            | -         |
-| [PaliGemma](https://huggingface.co/google)                        | 3B                               | paligemma |
-| [Phi-1.5/Phi-2](https://huggingface.co/microsoft)                 | 1.3B/2.7B                        | -         |
-| [Phi-3](https://huggingface.co/microsoft)                         | 4B/7B/14B                        | phi       |
-| [Qwen (1-2.5) (Code/Math/MoE)](https://huggingface.co/Qwen)       | 0.5B/1.5B/3B/7B/14B/32B/72B/110B | qwen      |
-| [Qwen2-VL](https://huggingface.co/Qwen)                           | 2B/7B/72B                        | qwen2_vl  |
-| [StarCoder 2](https://huggingface.co/bigcode)                     | 3B/7B/15B                        | -         |
-| [XVERSE](https://huggingface.co/xverse)                           | 7B/13B/65B                       | xverse    |
-| [Yi/Yi-1.5 (Code)](https://huggingface.co/01-ai)                  | 1.5B/6B/9B/34B                   | yi        |
-| [Yi-VL](https://huggingface.co/01-ai)                             | 6B/34B                           | yi_vl     |
-| [Yuan 2](https://huggingface.co/IEITYuan)                         | 2B/51B/102B                      | yuan      |
+| Model                                                             | Model size                       | Template         |
+| ----------------------------------------------------------------- | -------------------------------- | ---------------- |
+| [Baichuan 2](https://huggingface.co/baichuan-inc)                 | 7B/13B                           | baichuan2        |
+| [BLOOM/BLOOMZ](https://huggingface.co/bigscience)                 | 560M/1.1B/1.7B/3B/7.1B/176B      | -                |
+| [ChatGLM3](https://huggingface.co/THUDM)                          | 6B                               | chatglm3         |
+| [Command R](https://huggingface.co/CohereForAI)                   | 35B/104B                         | cohere           |
+| [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai)         | 7B/16B/67B/236B                  | deepseek         |
+| [Falcon](https://huggingface.co/tiiuae)                           | 7B/11B/40B/180B                  | falcon           |
+| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google)          | 2B/7B/9B/27B                     | gemma            |
+| [GLM-4](https://huggingface.co/THUDM)                             | 9B                               | glm4             |
+| [InternLM2/InternLM2.5](https://huggingface.co/internlm)          | 7B/20B                           | intern2          |
+| [Llama](https://github.com/facebookresearch/llama)                | 7B/13B/33B/65B                   | -                |
+| [Llama 2](https://huggingface.co/meta-llama)                      | 7B/13B/70B                       | llama2           |
+| [Llama 3-3.2](https://huggingface.co/meta-llama)                  | 1B/3B/8B/70B                     | llama3           |
+| [LLaVA-1.5](https://huggingface.co/llava-hf)                      | 7B/13B                           | llava            |
+| [LLaVA-NeXT](https://huggingface.co/llava-hf)                     | 7B/8B/13B/34B/72B/110B           | llava_next       |
+| [LLaVA-NeXT-Video](https://huggingface.co/llava-hf)               | 7B/34B                           | llava_next_video |
+| [MiniCPM](https://huggingface.co/openbmb)                         | 1B/2B/4B                         | cpm/cpm3         |
+| [Mistral/Mixtral](https://huggingface.co/mistralai)               | 7B/8x7B/8x22B                    | mistral          |
+| [OLMo](https://huggingface.co/allenai)                            | 1B/7B                            | -                |
+| [PaliGemma](https://huggingface.co/google)                        | 3B                               | paligemma        |
+| [Phi-1.5/Phi-2](https://huggingface.co/microsoft)                 | 1.3B/2.7B                        | -                |
+| [Phi-3](https://huggingface.co/microsoft)                         | 4B/7B/14B                        | phi              |
+| [Qwen (1-2.5) (Code/Math/MoE)](https://huggingface.co/Qwen)       | 0.5B/1.5B/3B/7B/14B/32B/72B/110B | qwen             |
+| [Qwen2-VL](https://huggingface.co/Qwen)                           | 2B/7B/72B                        | qwen2_vl         |
+| [StarCoder 2](https://huggingface.co/bigcode)                     | 3B/7B/15B                        | -                |
+| [XVERSE](https://huggingface.co/xverse)                           | 7B/13B/65B                       | xverse           |
+| [Yi/Yi-1.5 (Code)](https://huggingface.co/01-ai)                  | 1.5B/6B/9B/34B                   | yi               |
+| [Yi-VL](https://huggingface.co/01-ai)                             | 6B/34B                           | yi_vl            |
+| [Yuan 2](https://huggingface.co/IEITYuan)                         | 2B/51B/102B                      | yuan             |
 
 > [!NOTE]
 > For the "base" models, the `template` argument can be chosen from `default`, `alpaca`, `vicuna` etc. But make sure to use the **corresponding template** for the "instruct/chat" models.
diff --git a/README_zh.md b/README_zh.md
index 60ac8ee2..b5da9785 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -163,34 +163,36 @@ https://github.com/user-attachments/assets/e6ce34b0-52d5-4f3e-a830-592106c4c272
 
 ## 模型
 
-| 模型名                                                            | 模型大小                          | Template  |
-| ----------------------------------------------------------------- | -------------------------------- | --------- |
-| [Baichuan 2](https://huggingface.co/baichuan-inc)                 | 7B/13B                           | baichuan2 |
-| [BLOOM/BLOOMZ](https://huggingface.co/bigscience)                 | 560M/1.1B/1.7B/3B/7.1B/176B      | -         |
-| [ChatGLM3](https://huggingface.co/THUDM)                          | 6B                               | chatglm3  |
-| [Command R](https://huggingface.co/CohereForAI)                   | 35B/104B                         | cohere    |
-| [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai)         | 7B/16B/67B/236B                  | deepseek  |
-| [Falcon](https://huggingface.co/tiiuae)                           | 7B/11B/40B/180B                  | falcon    |
-| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google)          | 2B/7B/9B/27B                     | gemma     |
-| [GLM-4](https://huggingface.co/THUDM)                             | 9B                               | glm4      |
-| [InternLM2/InternLM2.5](https://huggingface.co/internlm)          | 7B/20B                           | intern2   |
-| [Llama](https://github.com/facebookresearch/llama)                | 7B/13B/33B/65B                   | -         |
-| [Llama 2](https://huggingface.co/meta-llama)                      | 7B/13B/70B                       | llama2    |
-| [Llama 3-3.2](https://huggingface.co/meta-llama)                  | 1B/3B/8B/70B                     | llama3    |
-| [LLaVA-1.5](https://huggingface.co/llava-hf)                      | 7B/13B                           | llava     |
-| [MiniCPM](https://huggingface.co/openbmb)                         | 1B/2B/4B                         | cpm/cpm3  |
-| [Mistral/Mixtral](https://huggingface.co/mistralai)               | 7B/8x7B/8x22B                    | mistral   |
-| [OLMo](https://huggingface.co/allenai)                            | 1B/7B                            | -         |
-| [PaliGemma](https://huggingface.co/google)                        | 3B                               | paligemma |
-| [Phi-1.5/Phi-2](https://huggingface.co/microsoft)                 | 1.3B/2.7B                        | -         |
-| [Phi-3](https://huggingface.co/microsoft)                         | 4B/7B/14B                        | phi       |
-| [Qwen (1-2.5) (Code/Math/MoE)](https://huggingface.co/Qwen)       | 0.5B/1.5B/3B/7B/14B/32B/72B/110B | qwen      |
-| [Qwen2-VL](https://huggingface.co/Qwen)                           | 2B/7B/72B                        | qwen2_vl  |
-| [StarCoder 2](https://huggingface.co/bigcode)                     | 3B/7B/15B                        | -         |
-| [XVERSE](https://huggingface.co/xverse)                           | 7B/13B/65B                       | xverse    |
-| [Yi/Yi-1.5 (Code)](https://huggingface.co/01-ai)                  | 1.5B/6B/9B/34B                   | yi        |
-| [Yi-VL](https://huggingface.co/01-ai)                             | 6B/34B                           | yi_vl     |
-| [Yuan 2](https://huggingface.co/IEITYuan)                         | 2B/51B/102B                      | yuan      |
+| 模型名                                                            | 模型大小                          | Template         |
+| ----------------------------------------------------------------- | -------------------------------- | ---------------- |
+| [Baichuan 2](https://huggingface.co/baichuan-inc)                 | 7B/13B                           | baichuan2        |
+| [BLOOM/BLOOMZ](https://huggingface.co/bigscience)                 | 560M/1.1B/1.7B/3B/7.1B/176B      | -                |
+| [ChatGLM3](https://huggingface.co/THUDM)                          | 6B                               | chatglm3         |
+| [Command R](https://huggingface.co/CohereForAI)                   | 35B/104B                         | cohere           |
+| [DeepSeek (Code/MoE)](https://huggingface.co/deepseek-ai)         | 7B/16B/67B/236B                  | deepseek         |
+| [Falcon](https://huggingface.co/tiiuae)                           | 7B/11B/40B/180B                  | falcon           |
+| [Gemma/Gemma 2/CodeGemma](https://huggingface.co/google)          | 2B/7B/9B/27B                     | gemma            |
+| [GLM-4](https://huggingface.co/THUDM)                             | 9B                               | glm4             |
+| [InternLM2/InternLM2.5](https://huggingface.co/internlm)          | 7B/20B                           | intern2          |
+| [Llama](https://github.com/facebookresearch/llama)                | 7B/13B/33B/65B                   | -                |
+| [Llama 2](https://huggingface.co/meta-llama)                      | 7B/13B/70B                       | llama2           |
+| [Llama 3-3.2](https://huggingface.co/meta-llama)                  | 1B/3B/8B/70B                     | llama3           |
+| [LLaVA-1.5](https://huggingface.co/llava-hf)                      | 7B/13B                           | llava            |
+| [LLaVA-NeXT](https://huggingface.co/llava-hf)                     | 7B/8B/13B/34B/72B/110B           | llava_next       |
+| [LLaVA-NeXT-Video](https://huggingface.co/llava-hf)               | 7B/34B                           | llava_next_video |
+| [MiniCPM](https://huggingface.co/openbmb)                         | 1B/2B/4B                         | cpm/cpm3         |
+| [Mistral/Mixtral](https://huggingface.co/mistralai)               | 7B/8x7B/8x22B                    | mistral          |
+| [OLMo](https://huggingface.co/allenai)                            | 1B/7B                            | -                |
+| [PaliGemma](https://huggingface.co/google)                        | 3B                               | paligemma        |
+| [Phi-1.5/Phi-2](https://huggingface.co/microsoft)                 | 1.3B/2.7B                        | -                |
+| [Phi-3](https://huggingface.co/microsoft)                         | 4B/7B/14B                        | phi              |
+| [Qwen (1-2.5) (Code/Math/MoE)](https://huggingface.co/Qwen)       | 0.5B/1.5B/3B/7B/14B/32B/72B/110B | qwen             |
+| [Qwen2-VL](https://huggingface.co/Qwen)                           | 2B/7B/72B                        | qwen2_vl         |
+| [StarCoder 2](https://huggingface.co/bigcode)                     | 3B/7B/15B                        | -                |
+| [XVERSE](https://huggingface.co/xverse)                           | 7B/13B/65B                       | xverse           |
+| [Yi/Yi-1.5 (Code)](https://huggingface.co/01-ai)                  | 1.5B/6B/9B/34B                   | yi               |
+| [Yi-VL](https://huggingface.co/01-ai)                             | 6B/34B                           | yi_vl            |
+| [Yuan 2](https://huggingface.co/IEITYuan)                         | 2B/51B/102B                      | yuan             |
 
 > [!NOTE]
 > 对于所有“基座”（Base）模型，`template` 参数可以是 `default`, `alpaca`, `vicuna` 等任意值。但“对话”（Instruct/Chat）模型请务必使用**对应的模板**。
diff --git a/requirements.txt b/requirements.txt
index 5f158eef..e913c58d 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -19,3 +19,4 @@ fire
 packaging
 pyyaml
 numpy<2.0.0
+av
diff --git a/src/llamafactory/data/mm_plugin.py b/src/llamafactory/data/mm_plugin.py
index e22e2760..3684495b 100644
--- a/src/llamafactory/data/mm_plugin.py
+++ b/src/llamafactory/data/mm_plugin.py
@@ -4,6 +4,7 @@ from io import BytesIO
 from typing import TYPE_CHECKING, Dict, List, Optional, Sequence, Tuple, TypedDict, Union
 
 import numpy as np
+from transformers.image_utils import get_image_size, to_numpy_array
 from typing_extensions import override
 
 from ..extras.constants import IGNORE_INDEX, IMAGE_PLACEHOLDER, VIDEO_PLACEHOLDER
@@ -157,6 +158,7 @@ class BasePlugin:
         It holds num_patches == torch.prod(image_grid_thw)
         """
         image_processor: "BaseImageProcessor" = getattr(processor, "image_processor")
+        video_processor: "BaseImageProcessor" = getattr(processor, "video_processor", image_processor)
         input_dict = {"images": None}  # default key
         if len(images) != 0:
             images = self._regularize_images(
@@ -174,10 +176,16 @@ class BasePlugin:
             )
             input_dict["videos"] = videos
 
-        if input_dict.get("images", None) is not None or input_dict.get("videos", None) is not None:
-            return image_processor(**input_dict, return_tensors="pt")
-        else:
-            return {}
+        mm_inputs = {}
+        if image_processor != video_processor:
+            if input_dict.get("images") is not None:
+                mm_inputs.update(image_processor(input_dict["images"], return_tensors="pt"))
+            if input_dict.get("videos") is not None:
+                mm_inputs.update(video_processor(input_dict["videos"], return_tensors="pt"))
+        elif input_dict.get("images") is not None or input_dict.get("videos") is not None:  # same processor (qwen2-vl)
+            mm_inputs.update(image_processor(**input_dict, return_tensors="pt"))
+
+        return mm_inputs
 
     def process_messages(
         self,
@@ -263,6 +271,122 @@ class LlavaPlugin(BasePlugin):
         return self._get_mm_inputs(images, videos, processor)
 
 
+class LlavaNextPlugin(BasePlugin):
+    @override
+    def process_messages(
+        self,
+        messages: Sequence[Dict[str, str]],
+        images: Sequence["ImageInput"],
+        videos: Sequence["VideoInput"],
+        processor: Optional["ProcessorMixin"],
+    ) -> List[Dict[str, str]]:
+        self._validate_input(images, videos)
+        num_image_tokens = 0
+        messages = deepcopy(messages)
+        mm_inputs = self._get_mm_inputs(images, videos, processor)
+        if "image_sizes" in mm_inputs:
+            image_sizes = iter(mm_inputs["image_sizes"])
+        if "pixel_values" in mm_inputs:
+            height, width = get_image_size(to_numpy_array(mm_inputs["pixel_values"][0][0]))
+        for message in messages:
+            content = message["content"]
+            while self.image_token in content:
+                image_size = next(image_sizes)
+                orig_height, orig_width = image_size
+                image_seqlen = processor._get_number_of_features(orig_height, orig_width, height, width)
+                if processor.vision_feature_select_strategy == "default":
+                    image_seqlen -= 1
+                num_image_tokens += 1
+                content = content.replace(self.image_token, "{{image}}" * image_seqlen, 1)
+
+            message["content"] = content.replace("{{image}}", self.image_token)
+
+        if len(images) != num_image_tokens:
+            raise ValueError("The number of images does not match the number of {} tokens".format(IMAGE_PLACEHOLDER))
+        return messages
+
+    @override
+    def get_mm_inputs(
+        self,
+        images: Sequence["ImageInput"],
+        videos: Sequence["VideoInput"],
+        imglens: Sequence[int],
+        vidlens: Sequence[int],
+        seqlens: Sequence[int],
+        processor: Optional["ProcessorMixin"],
+    ) -> Dict[str, Union[List[int], "torch.Tensor"]]:
+        self._validate_input(images, videos)
+        res = self._get_mm_inputs(images, videos, processor)
+        return res
+
+
+class LlavaNextVideoPlugin(BasePlugin):
+    @override
+    def process_messages(
+        self,
+        messages: Sequence[Dict[str, str]],
+        images: Sequence["ImageInput"],
+        videos: Sequence["VideoInput"],
+        processor: Optional["ProcessorMixin"],
+    ) -> List[Dict[str, str]]:
+        self._validate_input(images, videos)
+        num_image_tokens = 0
+        num_video_tokens = 0
+        messages = deepcopy(messages)
+        mm_inputs = self._get_mm_inputs(images, videos, processor)
+        if "pixel_values" in mm_inputs:
+            image_sizes = iter(mm_inputs["image_sizes"])
+            height, width = get_image_size(to_numpy_array(mm_inputs["pixel_values"][0][0]))
+            for message in messages:
+                content = message["content"]
+
+                while self.image_token in content:
+                    image_size = next(image_sizes)
+                    orig_height, orig_width = image_size
+                    image_seqlen = processor._get_number_of_features(orig_height, orig_width, height, width)
+                    if processor.vision_feature_select_strategy == "default":
+                        image_seqlen -= 1
+                    num_image_tokens += 1
+                    content = content.replace(self.image_token, "{{image}}" * image_seqlen, 1)
+
+                message["content"] = content.replace("{{image}}", self.image_token)
+
+        if "pixel_values_videos" in mm_inputs:
+            pixel_values_video = to_numpy_array(mm_inputs.get("pixel_values_videos")[0])
+            height, width = get_image_size(pixel_values_video[0])
+            num_frames = pixel_values_video.shape[0]  # frame dim is always after batch dim
+            image_seqlen = (height // processor.patch_size) * (width // processor.patch_size)
+            video_seqlen = image_seqlen // 4 * num_frames  # divide by 4 needed for avg pooling layer
+
+            for message in messages:
+                content = message["content"]
+                while self.video_token in content:
+                    num_video_tokens += 1
+                    content = content.replace(self.video_token, "{{video}}", 1)
+                message["content"] = content.replace("{{video}}", self.video_token * video_seqlen)
+
+        if len(images) != num_image_tokens:
+            raise ValueError("The number of images does not match the number of {} tokens".format(IMAGE_PLACEHOLDER))
+
+        if len(videos) != num_video_tokens:
+            raise ValueError("The number of videos does not match the number of {} tokens".format(IMAGE_PLACEHOLDER))
+
+        return messages
+
+    @override
+    def get_mm_inputs(
+        self,
+        images: Sequence["ImageInput"],
+        videos: Sequence["VideoInput"],
+        imglens: Sequence[int],
+        vidlens: Sequence[int],
+        seqlens: Sequence[int],
+        processor: Optional["ProcessorMixin"],
+    ) -> Dict[str, Union[List[int], "torch.Tensor"]]:
+        self._validate_input(images, videos)
+        return self._get_mm_inputs(images, videos, processor)
+
+
 class PaliGemmaPlugin(BasePlugin):
     @override
     def process_messages(
@@ -417,11 +541,77 @@ class Qwen2vlPlugin(BasePlugin):
         return self._get_mm_inputs(images, videos, processor)
 
 
+class VideoLlavaPlugin(BasePlugin):
+    @override
+    def process_messages(
+        self,
+        messages: Sequence[Dict[str, str]],
+        images: Sequence["ImageInput"],
+        videos: Sequence["VideoInput"],
+        processor: Optional["ProcessorMixin"],
+    ) -> List[Dict[str, str]]:
+        self._validate_input(images, videos)
+        num_image_tokens = 0
+        num_video_tokens = 0
+        messages = deepcopy(messages)
+        mm_inputs = self._get_mm_inputs(images, videos, processor)
+        num_frames = 0
+        exist_images = "pixel_values_images" in mm_inputs
+        exist_videos = "pixel_values_videos" in mm_inputs
+        if exist_videos or exist_images:
+            if exist_images:
+                height, width = get_image_size(to_numpy_array(mm_inputs.get("pixel_values_images")[0]))
+                num_frames = 1
+            if exist_videos:
+                pixel_values_video = to_numpy_array(mm_inputs.get("pixel_values_videos")[0])
+                height, width = get_image_size(pixel_values_video[0])
+                num_frames = pixel_values_video.shape[0]  # frame dim is always after batch dim
+            image_seqlen = (height // processor.patch_size) * (width // processor.patch_size) + 1
+            video_seqlen = image_seqlen * num_frames
+            if processor.vision_feature_select_strategy == "default":
+                image_seqlen -= 1
+            for message in messages:
+                content = message["content"]
+                while self.image_token in content:
+                    num_image_tokens += 1
+                    content = content.replace(self.image_token, "{{image}}", 1)
+                while self.video_token in content:
+                    num_video_tokens += 1
+                    content = content.replace(self.video_token, "{{video}}", 1)
+
+                content = content.replace("{{image}}", self.image_token * image_seqlen)
+                message["content"] = content.replace("{{video}}", self.video_token * video_seqlen)
+
+        if len(images) != num_image_tokens:
+            raise ValueError("The number of images does not match the number of {} tokens".format(self.image_token))
+
+        if len(videos) != num_video_tokens:
+            raise ValueError("The number of videos does not match the number of {} tokens".format(self.video_token))
+
+        return messages
+
+    @override
+    def get_mm_inputs(
+        self,
+        images: Sequence["ImageInput"],
+        videos: Sequence["VideoInput"],
+        imglens: Sequence[int],
+        vidlens: Sequence[int],
+        seqlens: Sequence[int],
+        processor: Optional["ProcessorMixin"],
+    ) -> Dict[str, Union[List[int], "torch.Tensor"]]:
+        self._validate_input(images, videos)
+        return self._get_mm_inputs(images, videos, processor)
+
+
 PLUGINS = {
     "base": BasePlugin,
     "llava": LlavaPlugin,
+    "llava_next": LlavaNextPlugin,
+    "llava_next_video": LlavaNextVideoPlugin,
     "paligemma": PaliGemmaPlugin,
     "qwen2_vl": Qwen2vlPlugin,
+    "video_llava": VideoLlavaPlugin,
 }
 
 
diff --git a/src/llamafactory/data/template.py b/src/llamafactory/data/template.py
index c7d47ebc..7a10a0e3 100644
--- a/src/llamafactory/data/template.py
+++ b/src/llamafactory/data/template.py
@@ -760,6 +760,107 @@ _register_template(
 )
 
 
+_register_template(
+    name="llava_next",
+    format_user=StringFormatter(slots=["USER: {{content}} ASSISTANT:"]),
+    default_system=(
+        "A chat between a curious user and an artificial intelligence assistant. "
+        "The assistant gives helpful, detailed, and polite answers to the user's questions."
+    ),
+    mm_plugin=get_mm_plugin(name="llava_next", image_token="<image>"),
+)
+
+
+_register_template(
+    name="llava_next_llama3",
+    format_user=StringFormatter(
+        slots=[
+            (
+                "<|start_header_id|>user<|end_header_id|>\n\n{{content}}<|eot_id|>"
+                "<|start_header_id|>assistant<|end_header_id|>\n\n"
+            )
+        ]
+    ),
+    format_system=StringFormatter(slots=["<|start_header_id|>system<|end_header_id|>\n\n{{content}}<|eot_id|>"]),
+    format_observation=StringFormatter(
+        slots=[
+            (
+                "<|start_header_id|>tool<|end_header_id|>\n\n{{content}}<|eot_id|>"
+                "<|start_header_id|>assistant<|end_header_id|>\n\n"
+            )
+        ]
+    ),
+    format_prefix=EmptyFormatter(slots=[{"bos_token"}]),
+    stop_words=["<|eot_id|>"],
+    replace_eos=True,
+    replace_jinja_template=False,
+    mm_plugin=get_mm_plugin(name="llava_next", image_token="<image>"),
+)
+
+
+_register_template(
+    name="llava_next_mistral",
+    format_user=StringFormatter(slots=["[INST] {{content}} [/INST]"]),
+    format_prefix=EmptyFormatter(slots=[{"bos_token"}]),
+    mm_plugin=get_mm_plugin(name="llava_next", image_token="<image>"),
+)
+
+
+_register_template(
+    name="llava_next_qwen",
+    format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]),
+    format_system=StringFormatter(slots=["<|im_start|>system\n{{content}}<|im_end|>\n"]),
+    format_observation=StringFormatter(slots=["<|im_start|>tool\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]),
+    format_separator=EmptyFormatter(slots=["\n"]),
+    default_system="You are a helpful assistant.",
+    stop_words=["<|im_end|>"],
+    replace_eos=True,
+    replace_jinja_template=False,
+    mm_plugin=get_mm_plugin(name="llava_next", image_token="<image>"),
+)
+
+
+_register_template(
+    name="llava_next_yi",
+    format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]),
+    format_system=StringFormatter(slots=["<|im_start|>system\n{{content}}<|im_end|>\n"]),
+    format_separator=EmptyFormatter(slots=["\n"]),
+    stop_words=["<|im_end|>"],
+    replace_eos=True,
+    mm_plugin=get_mm_plugin(name="llava_next", image_token="<image>"),
+)
+
+
+_register_template(
+    name="llava_next_video",
+    format_user=StringFormatter(slots=["USER: {{content}} ASSISTANT:"]),
+    default_system=(
+        "A chat between a curious user and an artificial intelligence assistant. "
+        "The assistant gives helpful, detailed, and polite answers to the user's questions."
+    ),
+    mm_plugin=get_mm_plugin(name="llava_next_video", image_token="<image>", video_token="<video>"),
+)
+
+
+_register_template(
+    name="llava_next_video_mistral",
+    format_user=StringFormatter(slots=["[INST] {{content}} [/INST]"]),
+    format_prefix=EmptyFormatter(slots=[{"bos_token"}]),
+    mm_plugin=get_mm_plugin(name="llava_next_video", image_token="<image>", video_token="<video>"),
+)
+
+
+_register_template(
+    name="llava_next_video_yi",
+    format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]),
+    format_system=StringFormatter(slots=["<|im_start|>system\n{{content}}<|im_end|>\n"]),
+    format_separator=EmptyFormatter(slots=["\n"]),
+    stop_words=["<|im_end|>"],
+    replace_eos=True,
+    mm_plugin=get_mm_plugin(name="llava_next_video", image_token="<image>", video_token="<video>"),
+)
+
+
 _register_template(
     name="mistral",
     format_user=StringFormatter(slots=["[INST] {{content}} [/INST]"]),
@@ -906,6 +1007,17 @@ _register_template(
 )
 
 
+_register_template(
+    name="video_llava",
+    format_user=StringFormatter(slots=["USER: {{content}} ASSISTANT:"]),
+    default_system=(
+        "A chat between a curious user and an artificial intelligence assistant. "
+        "The assistant gives helpful, detailed, and polite answers to the user's questions."
+    ),
+    mm_plugin=get_mm_plugin(name="video_llava", image_token="<image>", video_token="<video>"),
+)
+
+
 _register_template(
     name="xuanyuan",
     format_user=StringFormatter(slots=["Human: {{content}} Assistant:"]),
diff --git a/src/llamafactory/extras/constants.py b/src/llamafactory/extras/constants.py
index 4ff0ce18..87436bc7 100644
--- a/src/llamafactory/extras/constants.py
+++ b/src/llamafactory/extras/constants.py
@@ -114,17 +114,12 @@ def register_model_group(
     template: Optional[str] = None,
     vision: bool = False,
 ) -> None:
-    prefix = None
     for name, path in models.items():
-        if prefix is None:
-            prefix = name.split("-")[0]
-        else:
-            assert prefix == name.split("-")[0], "prefix should be identical."
         SUPPORTED_MODELS[name] = path
-    if template is not None:
-        DEFAULT_TEMPLATE[prefix] = template
-    if vision:
-        VISION_MODELS.add(prefix)
+        if template is not None and any(suffix in name for suffix in ("-Chat", "-Instruct")):
+            DEFAULT_TEMPLATE[name] = template
+        if vision:
+            VISION_MODELS.add(name)
 
 
 register_model_group(
@@ -274,27 +269,27 @@ register_model_group(
 
 register_model_group(
     models={
-        "ChineseLLaMA2-1.3B": {
+        "Chinese-Llama-2-1.3B": {
             DownloadSource.DEFAULT: "hfl/chinese-llama-2-1.3b",
             DownloadSource.MODELSCOPE: "AI-ModelScope/chinese-llama-2-1.3b",
         },
-        "ChineseLLaMA2-7B": {
+        "Chinese-Llama-2-7B": {
             DownloadSource.DEFAULT: "hfl/chinese-llama-2-7b",
             DownloadSource.MODELSCOPE: "AI-ModelScope/chinese-llama-2-7b",
         },
-        "ChineseLLaMA2-13B": {
+        "Chinese-Llama-2-13B": {
             DownloadSource.DEFAULT: "hfl/chinese-llama-2-13b",
             DownloadSource.MODELSCOPE: "AI-ModelScope/chinese-llama-2-13b",
         },
-        "ChineseLLaMA2-1.3B-Chat": {
+        "Chinese-Alpaca-2-1.3B-Chat": {
             DownloadSource.DEFAULT: "hfl/chinese-alpaca-2-1.3b",
             DownloadSource.MODELSCOPE: "AI-ModelScope/chinese-alpaca-2-1.3b",
         },
-        "ChineseLLaMA2-7B-Chat": {
+        "Chinese-Alpaca-2-7B-Chat": {
             DownloadSource.DEFAULT: "hfl/chinese-alpaca-2-7b",
             DownloadSource.MODELSCOPE: "AI-ModelScope/chinese-alpaca-2-7b",
         },
-        "ChineseLLaMA2-13B-Chat": {
+        "Chinese-Alpaca-2-13B-Chat": {
             DownloadSource.DEFAULT: "hfl/chinese-alpaca-2-13b",
             DownloadSource.MODELSCOPE: "AI-ModelScope/chinese-alpaca-2-13b",
         },
@@ -450,25 +445,25 @@ register_model_group(
 
 register_model_group(
     models={
-        "DeepSeekCoder-6.7B-Base": {
+        "DeepSeek-Coder-6.7B-Base": {
             DownloadSource.DEFAULT: "deepseek-ai/deepseek-coder-6.7b-base",
             DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-coder-6.7b-base",
         },
-        "DeepSeekCoder-7B-Base": {
+        "DeepSeek-Coder-7B-Base": {
             DownloadSource.DEFAULT: "deepseek-ai/deepseek-coder-7b-base-v1.5",
         },
-        "DeepSeekCoder-33B-Base": {
+        "DeepSeek-Coder-33B-Base": {
             DownloadSource.DEFAULT: "deepseek-ai/deepseek-coder-33b-base",
             DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-coder-33b-base",
         },
-        "DeepSeekCoder-6.7B-Instruct": {
+        "DeepSeek-Coder-6.7B-Instruct": {
             DownloadSource.DEFAULT: "deepseek-ai/deepseek-coder-6.7b-instruct",
             DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-coder-6.7b-instruct",
         },
-        "DeepSeekCoder-7B-Instruct": {
+        "DeepSeek-Coder-7B-Instruct": {
             DownloadSource.DEFAULT: "deepseek-ai/deepseek-coder-7b-instruct-v1.5",
         },
-        "DeepSeekCoder-33B-Instruct": {
+        "DeepSeek-Coder-33B-Instruct": {
             DownloadSource.DEFAULT: "deepseek-ai/deepseek-coder-33b-instruct",
             DownloadSource.MODELSCOPE: "deepseek-ai/deepseek-coder-33b-instruct",
         },
@@ -624,13 +619,6 @@ register_model_group(
             DownloadSource.DEFAULT: "internlm/internlm2-chat-20b",
             DownloadSource.MODELSCOPE: "Shanghai_AI_Laboratory/internlm2-chat-20b",
         },
-    },
-    template="intern2",
-)
-
-
-register_model_group(
-    models={
         "InternLM2.5-1.8B": {
             DownloadSource.DEFAULT: "internlm/internlm2_5-1_8b",
             DownloadSource.MODELSCOPE: "Shanghai_AI_Laboratory/internlm2_5-1_8b",
@@ -686,19 +674,19 @@ register_model_group(
 
 register_model_group(
     models={
-        "LLaMA-7B": {
+        "Llama-7B": {
             DownloadSource.DEFAULT: "huggyllama/llama-7b",
             DownloadSource.MODELSCOPE: "skyline2006/llama-7b",
         },
-        "LLaMA-13B": {
+        "Llama-13B": {
             DownloadSource.DEFAULT: "huggyllama/llama-13b",
             DownloadSource.MODELSCOPE: "skyline2006/llama-13b",
         },
-        "LLaMA-30B": {
+        "Llama-30B": {
             DownloadSource.DEFAULT: "huggyllama/llama-30b",
             DownloadSource.MODELSCOPE: "skyline2006/llama-30b",
         },
-        "LLaMA-65B": {
+        "Llama-65B": {
             DownloadSource.DEFAULT: "huggyllama/llama-65b",
             DownloadSource.MODELSCOPE: "skyline2006/llama-65b",
         },
@@ -708,27 +696,27 @@ register_model_group(
 
 register_model_group(
     models={
-        "LLaMA2-7B": {
+        "Llama-2-7B": {
             DownloadSource.DEFAULT: "meta-llama/Llama-2-7b-hf",
             DownloadSource.MODELSCOPE: "modelscope/Llama-2-7b-ms",
         },
-        "LLaMA2-13B": {
+        "Llama-2-13B": {
             DownloadSource.DEFAULT: "meta-llama/Llama-2-13b-hf",
             DownloadSource.MODELSCOPE: "modelscope/Llama-2-13b-ms",
         },
-        "LLaMA2-70B": {
+        "Llama-2-70B": {
             DownloadSource.DEFAULT: "meta-llama/Llama-2-70b-hf",
             DownloadSource.MODELSCOPE: "modelscope/Llama-2-70b-ms",
         },
-        "LLaMA2-7B-Chat": {
+        "Llama-2-7B-Chat": {
             DownloadSource.DEFAULT: "meta-llama/Llama-2-7b-chat-hf",
             DownloadSource.MODELSCOPE: "modelscope/Llama-2-7b-chat-ms",
         },
-        "LLaMA2-13B-Chat": {
+        "Llama-2-13B-Chat": {
             DownloadSource.DEFAULT: "meta-llama/Llama-2-13b-chat-hf",
             DownloadSource.MODELSCOPE: "modelscope/Llama-2-13b-chat-ms",
         },
-        "LLaMA2-70B-Chat": {
+        "Llama-2-70B-Chat": {
             DownloadSource.DEFAULT: "meta-llama/Llama-2-70b-chat-hf",
             DownloadSource.MODELSCOPE: "modelscope/Llama-2-70b-chat-ms",
         },
@@ -739,80 +727,74 @@ register_model_group(
 
 register_model_group(
     models={
-        "LLaMA3-8B": {
+        "Llama-3-8B": {
             DownloadSource.DEFAULT: "meta-llama/Meta-Llama-3-8B",
             DownloadSource.MODELSCOPE: "LLM-Research/Meta-Llama-3-8B",
         },
-        "LLaMA3-70B": {
+        "Llama-3-70B": {
             DownloadSource.DEFAULT: "meta-llama/Meta-Llama-3-70B",
             DownloadSource.MODELSCOPE: "LLM-Research/Meta-Llama-3-70B",
         },
-        "LLaMA3-8B-Instruct": {
+        "Llama-3-8B-Instruct": {
             DownloadSource.DEFAULT: "meta-llama/Meta-Llama-3-8B-Instruct",
             DownloadSource.MODELSCOPE: "LLM-Research/Meta-Llama-3-8B-Instruct",
         },
-        "LLaMA3-70B-Instruct": {
+        "Llama-3-70B-Instruct": {
             DownloadSource.DEFAULT: "meta-llama/Meta-Llama-3-70B-Instruct",
             DownloadSource.MODELSCOPE: "LLM-Research/Meta-Llama-3-70B-Instruct",
         },
-        "LLaMA3-8B-Chinese-Chat": {
+        "Llama-3-8B-Chinese-Chat": {
             DownloadSource.DEFAULT: "shenzhi-wang/Llama3-8B-Chinese-Chat",
             DownloadSource.MODELSCOPE: "LLM-Research/Llama3-8B-Chinese-Chat",
         },
-        "LLaMA3-70B-Chinese-Chat": {
+        "Llama-3-70B-Chinese-Chat": {
             DownloadSource.DEFAULT: "shenzhi-wang/Llama3-70B-Chinese-Chat",
         },
-    },
-    template="llama3",
-)
-
-
-register_model_group(
-    models={
-        "LLaMA3.1-8B": {
+        "Llama-3.1-8B": {
             DownloadSource.DEFAULT: "meta-llama/Meta-Llama-3.1-8B",
             DownloadSource.MODELSCOPE: "LLM-Research/Meta-Llama-3.1-8B",
         },
-        "LLaMA3.1-70B": {
+        "Llama-3.1-70B": {
             DownloadSource.DEFAULT: "meta-llama/Meta-Llama-3.1-70B",
             DownloadSource.MODELSCOPE: "LLM-Research/Meta-Llama-3.1-70B",
         },
-        "LLaMA3.1-405B": {
+        "Llama-3.1-405B": {
             DownloadSource.DEFAULT: "meta-llama/Meta-Llama-3.1-405B",
             DownloadSource.MODELSCOPE: "LLM-Research/Meta-Llama-3.1-405B",
         },
-        "LLaMA3.1-8B-Instruct": {
+        "Llama-3.1-8B-Instruct": {
             DownloadSource.DEFAULT: "meta-llama/Meta-Llama-3.1-8B-Instruct",
             DownloadSource.MODELSCOPE: "LLM-Research/Meta-Llama-3.1-8B-Instruct",
         },
-        "LLaMA3.1-70B-Instruct": {
+        "Llama-3.1-70B-Instruct": {
             DownloadSource.DEFAULT: "meta-llama/Meta-Llama-3.1-70B-Instruct",
             DownloadSource.MODELSCOPE: "LLM-Research/Meta-Llama-3.1-70B-Instruct",
         },
-        "LLaMA3.1-405B-Instruct": {
+        "Llama-3.1-405B-Instruct": {
             DownloadSource.DEFAULT: "meta-llama/Meta-Llama-3.1-405B-Instruct",
             DownloadSource.MODELSCOPE: "LLM-Research/Meta-Llama-3.1-405B-Instruct",
         },
-    },
-    template="llama3",
-)
-
-
-register_model_group(
-    models={
-        "LLaMA3.2-1B": {
+        "Llama-3.1-8B-Chinese-Chat": {
+            DownloadSource.DEFAULT: "shenzhi-wang/Llama3.1-8B-Chinese-Chat",
+            DownloadSource.MODELSCOPE: "XD_AI/Llama3.1-8B-Chinese-Chat",
+        },
+        "Llama-3.1-70B-Chinese-Chat": {
+            DownloadSource.DEFAULT: "shenzhi-wang/Llama3.1-70B-Chinese-Chat",
+            DownloadSource.MODELSCOPE: "XD_AI/Llama3.1-70B-Chinese-Chat",
+        },
+        "Llama-3.2-1B": {
             DownloadSource.DEFAULT: "meta-llama/Llama-3.2-1B",
             DownloadSource.MODELSCOPE: "LLM-Research/Llama-3.2-1B",
         },
-        "LLaMA3.2-3B": {
+        "Llama-3.2-3B": {
             DownloadSource.DEFAULT: "meta-llama/Llama-3.2-3B",
             DownloadSource.MODELSCOPE: "LLM-Research/Llama-3.2-3B",
         },
-        "LLaMA3.2-1B-Instruct": {
+        "Llama-3.2-1B-Instruct": {
             DownloadSource.DEFAULT: "meta-llama/Llama-3.2-1B-Instruct",
             DownloadSource.MODELSCOPE: "LLM-Research/Llama-3.2-1B-Instruct",
         },
-        "LLaMA3.2-3B-Instruct": {
+        "Llama-3.2-3B-Instruct": {
             DownloadSource.DEFAULT: "meta-llama/Llama-3.2-3B-Instruct",
             DownloadSource.MODELSCOPE: "LLM-Research/Llama-3.2-3B-Instruct",
         },
@@ -823,11 +805,13 @@ register_model_group(
 
 register_model_group(
     models={
-        "LLaVA1.5-7B-Chat": {
+        "LLaVA-1.5-7B-Chat": {
             DownloadSource.DEFAULT: "llava-hf/llava-1.5-7b-hf",
+            DownloadSource.MODELSCOPE: "swift/llava-1.5-7b-hf",
         },
-        "LLaVA1.5-13B-Chat": {
+        "LLaVA-1.5-13B-Chat": {
             DownloadSource.DEFAULT: "llava-hf/llava-1.5-13b-hf",
+            DownloadSource.MODELSCOPE: "swift/llava-1.5-13b-hf",
         },
     },
     template="llava",
@@ -835,6 +819,117 @@ register_model_group(
 )
 
 
+register_model_group(
+    models={
+        "LLaVA-NeXT-7B-Chat": {
+            DownloadSource.DEFAULT: "llava-hf/llava-v1.6-vicuna-7b-hf",
+            DownloadSource.MODELSCOPE: "swift/llava-v1.6-vicuna-7b-hf",
+        },
+        "LLaVA-NeXT-13B-Chat": {
+            DownloadSource.DEFAULT: "llava-hf/llava-v1.6-vicuna-13b-hf",
+            DownloadSource.MODELSCOPE: "swift/llava-v1.6-vicuna-13b-hf",
+        },
+    },
+    template="llava_next",
+    vision=True,
+)
+
+
+register_model_group(
+    models={
+        "LLaVA-NeXT-Mistral-7B-Chat": {
+            DownloadSource.DEFAULT: "llava-hf/llava-v1.6-mistral-7b-hf",
+            DownloadSource.MODELSCOPE: "swift/llava-v1.6-mistral-7b-hf",
+        },
+    },
+    template="llava_next_mistral",
+    vision=True,
+)
+
+
+register_model_group(
+    models={
+        "LLaVA-NeXT-Llama3-8B-Chat": {
+            DownloadSource.DEFAULT: "llava-hf/llama3-llava-next-8b-hf",
+            DownloadSource.MODELSCOPE: "swift/llama3-llava-next-8b-hf",
+        },
+    },
+    template="llava_next_llama3",
+    vision=True,
+)
+
+
+register_model_group(
+    models={
+        "LLaVA-NeXT-34B-Chat": {
+            DownloadSource.DEFAULT: "llava-hf/llava-v1.6-34b-hf",
+            DownloadSource.MODELSCOPE: "LLM-Research/llava-v1.6-34b-hf",
+        },
+    },
+    template="llava_next_yi",
+    vision=True,
+)
+
+
+register_model_group(
+    models={
+        "LLaVA-NeXT-72B-Chat": {
+            DownloadSource.DEFAULT: "llava-hf/llava-next-72b-hf",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/llava-next-72b-hf",
+        },
+        "LLaVA-NeXT-110B-Chat": {
+            DownloadSource.DEFAULT: "llava-hf/llava-next-110b-hf",
+            DownloadSource.MODELSCOPE: "AI-ModelScope/llava-next-110b-hf",
+        },
+    },
+    template="llava_next_qwen",
+    vision=True,
+)
+
+
+register_model_group(
+    models={
+        "LLaVA-NeXT-Video-7B-Chat": {
+            DownloadSource.DEFAULT: "llava-hf/LLaVA-NeXT-Video-7B-hf",
+            DownloadSource.MODELSCOPE: "swift/LLaVA-NeXT-Video-7B-hf",
+        },
+        "LLaVA-NeXT-Video-7B-DPO-Chat": {
+            DownloadSource.DEFAULT: "llava-hf/LLaVA-NeXT-Video-7B-DPO-hf",
+            DownloadSource.MODELSCOPE: "swift/LLaVA-NeXT-Video-7B-DPO-hf",
+        },
+    },
+    template="llava_next_video",
+    vision=True,
+)
+
+
+register_model_group(
+    models={
+        "LLaVA-NeXT-Video-7B-32k-Chat": {
+            DownloadSource.DEFAULT: "llava-hf/LLaVA-NeXT-Video-7B-32K-hf",
+            DownloadSource.MODELSCOPE: "swift/LLaVA-NeXT-Video-7B-32K-hf",
+        },
+    },
+    template="llava_next_video_mistral",
+    vision=True,
+)
+
+
+register_model_group(
+    models={
+        "LLaVA-NeXT-Video-34B-Chat": {
+            DownloadSource.DEFAULT: "llava-hf/LLaVA-NeXT-Video-34B-hf",
+            DownloadSource.MODELSCOPE: "swift/LLaVA-NeXT-Video-34B-hf",
+        },
+        "LLaVA-NeXT-Video-34B-DPO-Chat": {
+            DownloadSource.DEFAULT: "llava-hf/LLaVA-NeXT-Video-34B-DPO-hf",
+        },
+    },
+    template="llava_next_video_yi",
+    vision=True,
+)
+
+
 register_model_group(
     models={
         "MiniCPM-2B-SFT-Chat": {
@@ -1028,27 +1123,27 @@ register_model_group(
 
 register_model_group(
     models={
-        "Phi3-4B-4k-Instruct": {
+        "Phi-3-4B-4k-Instruct": {
             DownloadSource.DEFAULT: "microsoft/Phi-3-mini-4k-instruct",
             DownloadSource.MODELSCOPE: "LLM-Research/Phi-3-mini-4k-instruct",
         },
-        "Phi3-4B-128k-Instruct": {
+        "Phi-3-4B-128k-Instruct": {
             DownloadSource.DEFAULT: "microsoft/Phi-3-mini-128k-instruct",
             DownloadSource.MODELSCOPE: "LLM-Research/Phi-3-mini-128k-instruct",
         },
-        "Phi3-7B-8k-Instruct": {
+        "Phi-3-7B-8k-Instruct": {
             DownloadSource.DEFAULT: "microsoft/Phi-3-small-8k-instruct",
             DownloadSource.MODELSCOPE: "LLM-Research/Phi-3-small-8k-instruct",
         },
-        "Phi3-7B-128k-Instruct": {
+        "Phi-3-7B-128k-Instruct": {
             DownloadSource.DEFAULT: "microsoft/Phi-3-small-128k-instruct",
             DownloadSource.MODELSCOPE: "LLM-Research/Phi-3-small-128k-instruct",
         },
-        "Phi3-14B-8k-Instruct": {
+        "Phi-3-14B-8k-Instruct": {
             DownloadSource.DEFAULT: "microsoft/Phi-3-medium-4k-instruct",
             DownloadSource.MODELSCOPE: "LLM-Research/Phi-3-medium-4k-instruct",
         },
-        "Phi3-14B-128k-Instruct": {
+        "Phi-3-14B-128k-Instruct": {
             DownloadSource.DEFAULT: "microsoft/Phi-3-medium-128k-instruct",
             DownloadSource.MODELSCOPE: "LLM-Research/Phi-3-medium-128k-instruct",
         },
@@ -1091,35 +1186,35 @@ register_model_group(
             DownloadSource.DEFAULT: "Qwen/Qwen-72B-Chat",
             DownloadSource.MODELSCOPE: "qwen/Qwen-72B-Chat",
         },
-        "Qwen-1.8B-int8-Chat": {
+        "Qwen-1.8B-Chat-Int8": {
             DownloadSource.DEFAULT: "Qwen/Qwen-1_8B-Chat-Int8",
             DownloadSource.MODELSCOPE: "qwen/Qwen-1_8B-Chat-Int8",
         },
-        "Qwen-1.8B-int4-Chat": {
+        "Qwen-1.8B-Chat-Int4": {
             DownloadSource.DEFAULT: "Qwen/Qwen-1_8B-Chat-Int4",
             DownloadSource.MODELSCOPE: "qwen/Qwen-1_8B-Chat-Int4",
         },
-        "Qwen-7B-int8-Chat": {
+        "Qwen-7B-Chat-Int8": {
             DownloadSource.DEFAULT: "Qwen/Qwen-7B-Chat-Int8",
             DownloadSource.MODELSCOPE: "qwen/Qwen-7B-Chat-Int8",
         },
-        "Qwen-7B-int4-Chat": {
+        "Qwen-7B-Chat-Int4": {
             DownloadSource.DEFAULT: "Qwen/Qwen-7B-Chat-Int4",
             DownloadSource.MODELSCOPE: "qwen/Qwen-7B-Chat-Int4",
         },
-        "Qwen-14B-int8-Chat": {
+        "Qwen-14B-Chat-Int8": {
             DownloadSource.DEFAULT: "Qwen/Qwen-14B-Chat-Int8",
             DownloadSource.MODELSCOPE: "qwen/Qwen-14B-Chat-Int8",
         },
-        "Qwen-14B-int4-Chat": {
+        "Qwen-14B-Chat-Int4": {
             DownloadSource.DEFAULT: "Qwen/Qwen-14B-Chat-Int4",
             DownloadSource.MODELSCOPE: "qwen/Qwen-14B-Chat-Int4",
         },
-        "Qwen-72B-int8-Chat": {
+        "Qwen-72B-Chat-Int8": {
             DownloadSource.DEFAULT: "Qwen/Qwen-72B-Chat-Int8",
             DownloadSource.MODELSCOPE: "qwen/Qwen-72B-Chat-Int8",
         },
-        "Qwen-72B-int4-Chat": {
+        "Qwen-72B-Chat-Int4": {
             DownloadSource.DEFAULT: "Qwen/Qwen-72B-Chat-Int4",
             DownloadSource.MODELSCOPE: "qwen/Qwen-72B-Chat-Int4",
         },
@@ -1202,75 +1297,75 @@ register_model_group(
             DownloadSource.DEFAULT: "Qwen/Qwen1.5-MoE-A2.7B-Chat",
             DownloadSource.MODELSCOPE: "qwen/Qwen1.5-MoE-A2.7B-Chat",
         },
-        "Qwen1.5-0.5B-int8-Chat": {
+        "Qwen1.5-0.5B-Chat-GPTQ-Int8": {
             DownloadSource.DEFAULT: "Qwen/Qwen1.5-0.5B-Chat-GPTQ-Int8",
             DownloadSource.MODELSCOPE: "qwen/Qwen1.5-0.5B-Chat-GPTQ-Int8",
         },
-        "Qwen1.5-0.5B-int4-Chat": {
+        "Qwen1.5-0.5B-Chat-AWQ": {
             DownloadSource.DEFAULT: "Qwen/Qwen1.5-0.5B-Chat-AWQ",
             DownloadSource.MODELSCOPE: "qwen/Qwen1.5-0.5B-Chat-AWQ",
         },
-        "Qwen1.5-1.8B-int8-Chat": {
+        "Qwen1.5-1.8B-Chat-GPTQ-Int8": {
             DownloadSource.DEFAULT: "Qwen/Qwen1.5-1.8B-Chat-GPTQ-Int8",
             DownloadSource.MODELSCOPE: "qwen/Qwen1.5-1.8B-Chat-GPTQ-Int8",
         },
-        "Qwen1.5-1.8B-int4-Chat": {
+        "Qwen1.5-1.8B-Chat-AWQ": {
             DownloadSource.DEFAULT: "Qwen/Qwen1.5-1.8B-Chat-AWQ",
             DownloadSource.MODELSCOPE: "qwen/Qwen1.5-1.8B-Chat-AWQ",
         },
-        "Qwen1.5-4B-int8-Chat": {
+        "Qwen1.5-4B-Chat-GPTQ-Int8": {
             DownloadSource.DEFAULT: "Qwen/Qwen1.5-4B-Chat-GPTQ-Int8",
             DownloadSource.MODELSCOPE: "qwen/Qwen1.5-4B-Chat-GPTQ-Int8",
         },
-        "Qwen1.5-4B-int4-Chat": {
+        "Qwen1.5-4B-Chat-AWQ": {
             DownloadSource.DEFAULT: "Qwen/Qwen1.5-4B-Chat-AWQ",
             DownloadSource.MODELSCOPE: "qwen/Qwen1.5-4B-Chat-AWQ",
         },
-        "Qwen1.5-7B-int8-Chat": {
+        "Qwen1.5-7B-Chat-GPTQ-Int8": {
             DownloadSource.DEFAULT: "Qwen/Qwen1.5-7B-Chat-GPTQ-Int8",
             DownloadSource.MODELSCOPE: "qwen/Qwen1.5-7B-Chat-GPTQ-Int8",
         },
-        "Qwen1.5-7B-int4-Chat": {
+        "Qwen1.5-7B-Chat-AWQ": {
             DownloadSource.DEFAULT: "Qwen/Qwen1.5-7B-Chat-AWQ",
             DownloadSource.MODELSCOPE: "qwen/Qwen1.5-7B-Chat-AWQ",
         },
-        "Qwen1.5-14B-int8-Chat": {
+        "Qwen1.5-14B-Chat-GPTQ-Int8": {
             DownloadSource.DEFAULT: "Qwen/Qwen1.5-14B-Chat-GPTQ-Int8",
             DownloadSource.MODELSCOPE: "qwen/Qwen1.5-14B-Chat-GPTQ-Int8",
         },
-        "Qwen1.5-14B-int4-Chat": {
+        "Qwen1.5-14B-Chat-AWQ": {
             DownloadSource.DEFAULT: "Qwen/Qwen1.5-14B-Chat-AWQ",
             DownloadSource.MODELSCOPE: "qwen/Qwen1.5-14B-Chat-AWQ",
         },
-        "Qwen1.5-32B-int4-Chat": {
+        "Qwen1.5-32B-Chat-AWQ": {
             DownloadSource.DEFAULT: "Qwen/Qwen1.5-32B-Chat-AWQ",
             DownloadSource.MODELSCOPE: "qwen/Qwen1.5-32B-Chat-AWQ",
         },
-        "Qwen1.5-72B-int8-Chat": {
+        "Qwen1.5-72B-Chat-GPTQ-Int8": {
             DownloadSource.DEFAULT: "Qwen/Qwen1.5-72B-Chat-GPTQ-Int8",
             DownloadSource.MODELSCOPE: "qwen/Qwen1.5-72B-Chat-GPTQ-Int8",
         },
-        "Qwen1.5-72B-int4-Chat": {
+        "Qwen1.5-72B-Chat-AWQ": {
             DownloadSource.DEFAULT: "Qwen/Qwen1.5-72B-Chat-AWQ",
             DownloadSource.MODELSCOPE: "qwen/Qwen1.5-72B-Chat-AWQ",
         },
-        "Qwen1.5-110B-int4-Chat": {
+        "Qwen1.5-110B-Chat-AWQ": {
             DownloadSource.DEFAULT: "Qwen/Qwen1.5-110B-Chat-AWQ",
             DownloadSource.MODELSCOPE: "qwen/Qwen1.5-110B-Chat-AWQ",
         },
-        "Qwen1.5-MoE-A2.7B-int4-Chat": {
+        "Qwen1.5-MoE-A2.7B-Chat-GPTQ-Int4": {
             DownloadSource.DEFAULT: "Qwen/Qwen1.5-MoE-A2.7B-Chat-GPTQ-Int4",
             DownloadSource.MODELSCOPE: "qwen/Qwen1.5-MoE-A2.7B-Chat-GPTQ-Int4",
         },
-        "Qwen1.5-Code-7B": {
+        "CodeQwen1.5-7B": {
             DownloadSource.DEFAULT: "Qwen/CodeQwen1.5-7B",
             DownloadSource.MODELSCOPE: "qwen/CodeQwen1.5-7B",
         },
-        "Qwen1.5-Code-7B-Chat": {
+        "CodeQwen1.5-7B-Chat": {
             DownloadSource.DEFAULT: "Qwen/CodeQwen1.5-7B-Chat",
             DownloadSource.MODELSCOPE: "qwen/CodeQwen1.5-7B-Chat",
         },
-        "Qwen1.5-Code-7B-int4-Chat": {
+        "CodeQwen1.5-7B-Chat-AWQ": {
             DownloadSource.DEFAULT: "Qwen/CodeQwen1.5-7B-Chat-AWQ",
             DownloadSource.MODELSCOPE: "qwen/CodeQwen1.5-7B-Chat-AWQ",
         },
@@ -1591,51 +1686,51 @@ register_model_group(
 
 register_model_group(
     models={
-        "Qwen2VL-2B-Instruct": {
+        "Qwen2-VL-2B-Instruct": {
             DownloadSource.DEFAULT: "Qwen/Qwen2-VL-2B-Instruct",
             DownloadSource.MODELSCOPE: "qwen/Qwen2-VL-2B-Instruct",
         },
-        "Qwen2VL-7B-Instruct": {
+        "Qwen2-VL-7B-Instruct": {
             DownloadSource.DEFAULT: "Qwen/Qwen2-VL-7B-Instruct",
             DownloadSource.MODELSCOPE: "qwen/Qwen2-VL-7B-Instruct",
         },
-        "Qwen2VL-72B-Instruct": {
+        "Qwen2-VL-72B-Instruct": {
             DownloadSource.DEFAULT: "Qwen/Qwen2-VL-72B-Instruct",
             DownloadSource.MODELSCOPE: "qwen/Qwen2-VL-72B-Instruct",
         },
-        "Qwen2VL-2B-Instruct-GPTQ-Int8": {
+        "Qwen2-VL-2B-Instruct-GPTQ-Int8": {
             DownloadSource.DEFAULT: "Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int8",
             DownloadSource.MODELSCOPE: "qwen/Qwen2-VL-2B-Instruct-GPTQ-Int8",
         },
-        "Qwen2VL-2B-Instruct-GPTQ-Int4": {
+        "Qwen2-VL-2B-Instruct-GPTQ-Int4": {
             DownloadSource.DEFAULT: "Qwen/Qwen2-VL-2B-Instruct-GPTQ-Int4",
             DownloadSource.MODELSCOPE: "qwen/Qwen2-VL-2B-Instruct-GPTQ-Int4",
         },
-        "Qwen2VL-2B-Instruct-AWQ": {
+        "Qwen2-VL-2B-Instruct-AWQ": {
             DownloadSource.DEFAULT: "Qwen/Qwen2-VL-2B-Instruct-AWQ",
             DownloadSource.MODELSCOPE: "qwen/Qwen2-VL-2B-Instruct-AWQ",
         },
-        "Qwen2VL-7B-Instruct-GPTQ-Int8": {
+        "Qwen2-VL-7B-Instruct-GPTQ-Int8": {
             DownloadSource.DEFAULT: "Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int8",
             DownloadSource.MODELSCOPE: "qwen/Qwen2-VL-7B-Instruct-GPTQ-Int8",
         },
-        "Qwen2VL-7B-Instruct-GPTQ-Int4": {
+        "Qwen2-VL-7B-Instruct-GPTQ-Int4": {
             DownloadSource.DEFAULT: "Qwen/Qwen2-VL-7B-Instruct-GPTQ-Int4",
             DownloadSource.MODELSCOPE: "qwen/Qwen2-VL-7B-Instruct-GPTQ-Int4",
         },
-        "Qwen2VL-7B-Instruct-AWQ": {
+        "Qwen2-VL-7B-Instruct-AWQ": {
             DownloadSource.DEFAULT: "Qwen/Qwen2-VL-7B-Instruct-AWQ",
             DownloadSource.MODELSCOPE: "qwen/Qwen2-VL-7B-Instruct-AWQ",
         },
-        "Qwen2VL-72B-Instruct-GPTQ-Int8": {
+        "Qwen2-VL-72B-Instruct-GPTQ-Int8": {
             DownloadSource.DEFAULT: "Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int8",
             DownloadSource.MODELSCOPE: "qwen/Qwen2-VL-72B-Instruct-GPTQ-Int8",
         },
-        "Qwen2VL-72B-Instruct-GPTQ-Int4": {
+        "Qwen2-VL-72B-Instruct-GPTQ-Int4": {
             DownloadSource.DEFAULT: "Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int4",
             DownloadSource.MODELSCOPE: "qwen/Qwen2-VL-72B-Instruct-GPTQ-Int4",
         },
-        "Qwen2VL-72B-Instruct-AWQ": {
+        "Qwen2-VL-72B-Instruct-AWQ": {
             DownloadSource.DEFAULT: "Qwen/Qwen2-VL-72B-Instruct-AWQ",
             DownloadSource.MODELSCOPE: "qwen/Qwen2-VL-72B-Instruct-AWQ",
         },
@@ -1712,11 +1807,11 @@ register_model_group(
 
 register_model_group(
     models={
-        "Vicuna1.5-7B-Chat": {
+        "Vicuna-v1.5-7B-Chat": {
             DownloadSource.DEFAULT: "lmsys/vicuna-7b-v1.5",
             DownloadSource.MODELSCOPE: "Xorbits/vicuna-7b-v1.5",
         },
-        "Vicuna1.5-13B-Chat": {
+        "Vicuna-v1.5-13B-Chat": {
             DownloadSource.DEFAULT: "lmsys/vicuna-13b-v1.5",
             DownloadSource.MODELSCOPE: "Xorbits/vicuna-13b-v1.5",
         },
@@ -1725,6 +1820,17 @@ register_model_group(
 )
 
 
+register_model_group(
+    models={
+        "Video-LLaVA-7B-Chat": {
+            DownloadSource.DEFAULT: "LanguageBind/Video-LLaVA-7B-hf",
+        },
+    },
+    template="video_llava",
+    vision=True,
+)
+
+
 register_model_group(
     models={
         "XuanYuan-6B": {
@@ -1735,7 +1841,7 @@ register_model_group(
             DownloadSource.DEFAULT: "Duxiaoman-DI/XuanYuan-70B",
             DownloadSource.MODELSCOPE: "Duxiaoman-DI/XuanYuan-70B",
         },
-        "XuanYuan-2-70B": {
+        "XuanYuan2-70B": {
             DownloadSource.DEFAULT: "Duxiaoman-DI/XuanYuan2-70B",
             DownloadSource.MODELSCOPE: "Duxiaoman-DI/XuanYuan2-70B",
         },
@@ -1747,31 +1853,31 @@ register_model_group(
             DownloadSource.DEFAULT: "Duxiaoman-DI/XuanYuan-70B-Chat",
             DownloadSource.MODELSCOPE: "Duxiaoman-DI/XuanYuan-70B-Chat",
         },
-        "XuanYuan-2-70B-Chat": {
+        "XuanYuan2-70B-Chat": {
             DownloadSource.DEFAULT: "Duxiaoman-DI/XuanYuan2-70B-Chat",
             DownloadSource.MODELSCOPE: "Duxiaoman-DI/XuanYuan2-70B-Chat",
         },
-        "XuanYuan-6B-int8-Chat": {
+        "XuanYuan-6B-Chat-8bit": {
             DownloadSource.DEFAULT: "Duxiaoman-DI/XuanYuan-6B-Chat-8bit",
             DownloadSource.MODELSCOPE: "Duxiaoman-DI/XuanYuan-6B-Chat-8bit",
         },
-        "XuanYuan-6B-int4-Chat": {
+        "XuanYuan-6B-Chat-4bit": {
             DownloadSource.DEFAULT: "Duxiaoman-DI/XuanYuan-6B-Chat-4bit",
             DownloadSource.MODELSCOPE: "Duxiaoman-DI/XuanYuan-6B-Chat-4bit",
         },
-        "XuanYuan-70B-int8-Chat": {
+        "XuanYuan-70B-Chat-8bit": {
             DownloadSource.DEFAULT: "Duxiaoman-DI/XuanYuan-70B-Chat-8bit",
             DownloadSource.MODELSCOPE: "Duxiaoman-DI/XuanYuan-70B-Chat-8bit",
         },
-        "XuanYuan-70B-int4-Chat": {
+        "XuanYuan-70B-Chat-4bit": {
             DownloadSource.DEFAULT: "Duxiaoman-DI/XuanYuan-70B-Chat-4bit",
             DownloadSource.MODELSCOPE: "Duxiaoman-DI/XuanYuan-70B-Chat-4bit",
         },
-        "XuanYuan-2-70B-int8-Chat": {
+        "XuanYuan2-70B-Chat-8bit": {
             DownloadSource.DEFAULT: "Duxiaoman-DI/XuanYuan2-70B-Chat-8bit",
             DownloadSource.MODELSCOPE: "Duxiaoman-DI/XuanYuan2-70B-Chat-8bit",
         },
-        "XuanYuan-2-70B-int4-Chat": {
+        "XuanYuan2-70B-Chat-4bit": {
             DownloadSource.DEFAULT: "Duxiaoman-DI/XuanYuan2-70B-Chat-4bit",
             DownloadSource.MODELSCOPE: "Duxiaoman-DI/XuanYuan2-70B-Chat-4bit",
         },
@@ -1876,19 +1982,19 @@ register_model_group(
             DownloadSource.DEFAULT: "01-ai/Yi-34B-Chat",
             DownloadSource.MODELSCOPE: "01ai/Yi-34B-Chat",
         },
-        "Yi-6B-int8-Chat": {
+        "Yi-6B-Chat-8bits": {
             DownloadSource.DEFAULT: "01-ai/Yi-6B-Chat-8bits",
             DownloadSource.MODELSCOPE: "01ai/Yi-6B-Chat-8bits",
         },
-        "Yi-6B-int4-Chat": {
+        "Yi-6B-Chat-4bits": {
             DownloadSource.DEFAULT: "01-ai/Yi-6B-Chat-4bits",
             DownloadSource.MODELSCOPE: "01ai/Yi-6B-Chat-4bits",
         },
-        "Yi-34B-int8-Chat": {
+        "Yi-34B-Chat-8bits": {
             DownloadSource.DEFAULT: "01-ai/Yi-34B-Chat-8bits",
             DownloadSource.MODELSCOPE: "01ai/Yi-34B-Chat-8bits",
         },
-        "Yi-34B-int4-Chat": {
+        "Yi-34B-Chat-4bits": {
             DownloadSource.DEFAULT: "01-ai/Yi-34B-Chat-4bits",
             DownloadSource.MODELSCOPE: "01ai/Yi-34B-Chat-4bits",
         },
@@ -1939,10 +2045,10 @@ register_model_group(
 
 register_model_group(
     models={
-        "YiVL-6B-Chat": {
+        "Yi-VL-6B-Chat": {
             DownloadSource.DEFAULT: "BUAADreamer/Yi-VL-6B-hf",
         },
-        "YiVL-34B-Chat": {
+        "Yi-VL-34B-Chat": {
             DownloadSource.DEFAULT: "BUAADreamer/Yi-VL-34B-hf",
         },
     },
diff --git a/src/llamafactory/model/loader.py b/src/llamafactory/model/loader.py
index 030ce90f..c90913ae 100644
--- a/src/llamafactory/model/loader.py
+++ b/src/llamafactory/model/loader.py
@@ -25,7 +25,7 @@ from .model_utils.misc import register_autoclass
 from .model_utils.mod import convert_pretrained_model_to_mod, load_mod_pretrained_model
 from .model_utils.unsloth import load_unsloth_pretrained_model
 from .model_utils.valuehead import load_valuehead_params
-from .model_utils.visual import get_image_seqlen
+from .model_utils.visual import get_image_seqlen, get_patch_size, get_vision_feature_select_strategy
 from .patcher import patch_config, patch_model, patch_tokenizer, patch_valuehead_model
 
 
@@ -100,9 +100,11 @@ def load_tokenizer(model_args: "ModelArguments") -> "TokenizerModule":
         setattr(processor, "tokenizer", tokenizer)
         setattr(processor, "image_seqlen", get_image_seqlen(config))
         setattr(processor, "image_resolution", model_args.image_resolution)
+        setattr(processor, "patch_size", get_patch_size(config))
         setattr(processor, "video_resolution", model_args.video_resolution)
         setattr(processor, "video_fps", model_args.video_fps)
         setattr(processor, "video_maxlen", model_args.video_maxlen)
+        setattr(processor, "vision_feature_select_strategy", get_vision_feature_select_strategy(config))
     except Exception:
         processor = None
 
@@ -155,7 +157,6 @@ def load_model(
                 load_class = AutoModelForVision2Seq
             else:
                 load_class = AutoModelForCausalLM
-
             if model_args.train_from_scratch:
                 model = load_class.from_config(config)
             else:
diff --git a/src/llamafactory/model/model_utils/misc.py b/src/llamafactory/model/model_utils/misc.py
index 342a1008..4883fa23 100644
--- a/src/llamafactory/model/model_utils/misc.py
+++ b/src/llamafactory/model/model_utils/misc.py
@@ -34,7 +34,7 @@ def find_all_linear_modules(model: "PreTrainedModel", freeze_vision_tower: bool)
         forbidden_modules.add("output_layer")
     elif model_type == "internlm2":
         forbidden_modules.add("output")
-    elif model_type in ["llava", "paligemma"]:
+    elif model_type in ["llava", "llava_next", "llava_next_video", "paligemma", "video_llava"]:
         forbidden_modules.add("multi_modal_projector")
     elif model_type == "qwen2_vl":
         forbidden_modules.add("merger")
diff --git a/src/llamafactory/model/model_utils/visual.py b/src/llamafactory/model/model_utils/visual.py
index 23f880a6..c2aeb0dd 100644
--- a/src/llamafactory/model/model_utils/visual.py
+++ b/src/llamafactory/model/model_utils/visual.py
@@ -92,7 +92,7 @@ def autocast_projector_dtype(model: "PreTrainedModel", model_args: "ModelArgumen
 
     if getattr(model, "quantization_method", None):
         model_type = getattr(model.config, "model_type", None)
-        if model_type in ["llava", "paligemma"]:
+        if model_type in ["llava", "llava_next", "llava_next_video", "paligemma", "video_llava"]:
             mm_projector: "torch.nn.Module" = getattr(model, "multi_modal_projector")
         elif model_type == "qwen2_vl":
             mm_projector: "torch.nn.Module" = getattr(getattr(model, "visual"), "merger")
@@ -108,7 +108,13 @@ def configure_visual_model(config: "PretrainedConfig") -> None:
     Patches VLMs before loading them.
     """
     model_type = getattr(config, "model_type", None)
-    if model_type == "llava":  # required for ds zero3 and valuehead models
+    if model_type in [
+        "llava",
+        "llava_next",
+        "llava_next_video",
+        "paligemma",
+        "video_llava",
+    ]:  # required for ds zero3 and valuehead models
         setattr(config, "hidden_size", getattr(config.text_config, "hidden_size", None))
 
     if getattr(config, "is_yi_vl_derived_model", None):
@@ -122,7 +128,7 @@ def get_forbidden_modules(config: "PretrainedConfig", finetuning_args: "Finetuni
     """
     model_type = getattr(config, "model_type", None)
     forbidden_modules = set()
-    if model_type in ["llava", "paligemma"]:
+    if model_type in ["llava", "llava_next", "llava_next_video", "paligemma", "video_llava"]:
         if finetuning_args.freeze_vision_tower:
             forbidden_modules.add("vision_tower")
 
@@ -150,12 +156,28 @@ def get_image_seqlen(config: "PretrainedConfig") -> int:
             image_seqlen += 1
     elif model_type == "paligemma":
         image_seqlen = config.vision_config.num_image_tokens
-    elif model_type == "qwen2_vl":  # variable length
+    else:
         image_seqlen = -1
 
     return image_seqlen
 
 
+def get_patch_size(config: "PretrainedConfig") -> int:
+    r"""
+    Computes the patch size of the vit.
+    """
+    patch_size = getattr(config.vision_config, "patch_size", -1)
+    return patch_size
+
+
+def get_vision_feature_select_strategy(config: "PretrainedConfig") -> int:
+    r"""
+    Get the vision_feature_select_strategy.
+    """
+    vision_feature_select_strategy = getattr(config, "vision_feature_select_strategy", "default")
+    return vision_feature_select_strategy
+
+
 def patch_target_modules(
     config: "PretrainedConfig", finetuning_args: "FinetuningArguments", target_modules: Sequence[str]
 ) -> Union[str, List[str]]:
@@ -164,7 +186,7 @@ def patch_target_modules(
     """
     model_type = getattr(config, "model_type", None)
     if finetuning_args.freeze_vision_tower:
-        if model_type in ["llava", "paligemma"]:
+        if model_type in ["llava", "llava_next", "llava_next_video", "paligemma", "video_llava"]:
             return "^(?!.*vision_tower).*(?:{}).*".format("|".join(target_modules))
         elif model_type == "qwen2_vl":
             return "^(?!.*visual).*(?:{}).*".format("|".join(target_modules))
diff --git a/src/llamafactory/webui/common.py b/src/llamafactory/webui/common.py
index 0ad2929e..d4e9be51 100644
--- a/src/llamafactory/webui/common.py
+++ b/src/llamafactory/webui/common.py
@@ -115,13 +115,6 @@ def get_model_path(model_name: str) -> str:
     return model_path
 
 
-def get_prefix(model_name: str) -> str:
-    r"""
-    Gets the prefix of the model name to obtain the model family.
-    """
-    return model_name.split("-")[0]
-
-
 def get_model_info(model_name: str) -> Tuple[str, str]:
     r"""
     Gets the necessary information of this model.
@@ -137,21 +130,14 @@ def get_template(model_name: str) -> str:
     r"""
     Gets the template name if the model is a chat model.
     """
-    if (
-        model_name
-        and any(suffix in model_name for suffix in ("-Chat", "-Instruct"))
-        and get_prefix(model_name) in DEFAULT_TEMPLATE
-    ):
-        return DEFAULT_TEMPLATE[get_prefix(model_name)]
-
-    return "default"
+    return DEFAULT_TEMPLATE.get(model_name, "default")
 
 
 def get_visual(model_name: str) -> bool:
     r"""
     Judges if the model is a vision language model.
     """
-    return get_prefix(model_name) in VISION_MODELS
+    return model_name in VISION_MODELS
 
 
 def list_checkpoints(model_name: str, finetuning_type: str) -> "gr.Dropdown":
diff --git a/tests/data/test_mm_plugin.py b/tests/data/test_mm_plugin.py
index 3ccba7f4..bd2eb45a 100644
--- a/tests/data/test_mm_plugin.py
+++ b/tests/data/test_mm_plugin.py
@@ -136,6 +136,38 @@ def test_llava_plugin():
     _check_plugin(**check_inputs)
 
 
+def test_llava_next_plugin():
+    tokenizer, processor = _load_tokenizer_module(model_name_or_path="llava-hf/llava-v1.6-vicuna-7b-hf")
+    llava_next_plugin = get_mm_plugin(name="llava_next", image_token="<image>")
+    check_inputs = {"plugin": llava_next_plugin, "tokenizer": tokenizer, "processor": processor}
+    image_seqlen = 1176
+    check_inputs["expected_mm_messages"] = [
+        {
+            key: value.replace("<image>", "<image>" * image_seqlen)
+            for key, value in message.items()
+        }
+        for message in MM_MESSAGES
+    ]
+    check_inputs["expected_mm_inputs"] = _get_mm_inputs(processor)
+    _check_plugin(**check_inputs)
+
+
+def test_llava_next_video_plugin():
+    tokenizer, processor = _load_tokenizer_module(model_name_or_path="llava-hf/LLaVA-NeXT-Video-7B-hf")
+    llava_next_video_plugin = get_mm_plugin(name="llava_next_video", image_token="<image>", video_token="<video>")
+    check_inputs = {"plugin": llava_next_video_plugin, "tokenizer": tokenizer, "processor": processor}
+    image_seqlen = 1176
+    check_inputs["expected_mm_messages"] = [
+        {
+            key: value.replace("<image>", "<image>" * image_seqlen)
+            for key, value in message.items()
+        }
+        for message in MM_MESSAGES
+    ]
+    check_inputs["expected_mm_inputs"] = _get_mm_inputs(processor)
+    _check_plugin(**check_inputs)
+
+
 @pytest.mark.skipif(not HF_TOKEN, reason="Gated model.")
 def test_paligemma_plugin():
     tokenizer, processor = _load_tokenizer_module(model_name_or_path="google/paligemma-3b-pt-224")
@@ -167,3 +199,19 @@ def test_qwen2_vl_plugin():
     ]
     check_inputs["expected_mm_inputs"] = _get_mm_inputs(processor)
     _check_plugin(**check_inputs)
+
+
+def test_video_llava_plugin():
+    tokenizer, processor = _load_tokenizer_module(model_name_or_path="LanguageBind/Video-LLaVA-7B-hf")
+    video_llava_plugin = get_mm_plugin(name="video_llava", image_token="<image>", video_token="<video>")
+    check_inputs = {"plugin": video_llava_plugin, "tokenizer": tokenizer, "processor": processor}
+    image_seqlen = 256
+    check_inputs["expected_mm_messages"] = [
+        {
+            key: value.replace("<image>", "<image>" * image_seqlen)
+            for key, value in message.items()
+        }
+        for message in MM_MESSAGES
+    ]
+    check_inputs["expected_mm_inputs"] = _get_mm_inputs(processor)
+    _check_plugin(**check_inputs)