Update README.md

README.md

@@ -10,7 +10,7 @@ metrics:
 tags:
 - multimodal
 model-index:
-- name: LLaVA-NeXT-Video-7B-Qwen2
+- name: LLaVA-Video-7B-Qwen2
   results:
   - task:
       type: multimodal
@@ -116,7 +116,7 @@ base_model:
 - lmms-lab/llava-onevision-qwen2-7b-si
 ---
 
-# LLaVA-NeXT-Video-7B-Qwen2-Video-Only
+# LLaVA-Video-7B-Qwen2-Video-Only
 
 ##  Table of Contents
 
@@ -132,7 +132,7 @@ base_model:
 In contrast to lmms-lab/LLaVA-NeXT-Video-7B-Qwen2, this is a 7B model trained on [LLaVA-Video-178K](https://huggingface.co/datasets/lmms-lab/LLaVA-NeXT-Video-SFT-Data) only, based on Qwen2 language model with a context window of 32K tokens.
 
 
-This model supports up to 110 frames and achieves comparable results to those of lmms-lab/LLaVA-NeXT-Video-7B-Qwen2 in terms of video benchmarks.
+This model supports up to 110 frames and achieves comparable results to those of lmms-lab/LLaVA-Video-7B-Qwen2 in terms of video benchmarks.
 
 - **Repository:** [LLaVA-VL/LLaVA-NeXT](https://github.com/LLaVA-VL/LLaVA-NeXT?tab=readme-ov-file)
 - **Point of Contact:** [Yuanhan Zhang](https://zhangyuanhan-ai.github.io/)
@@ -184,7 +184,7 @@ def load_video(self, video_path, max_frames_num,fps=1,force_sample=False):
     spare_frames = vr.get_batch(frame_idx).asnumpy()
     # import pdb;pdb.set_trace()
     return spare_frames,frame_time,video_time
-pretrained = "lmms-lab/LLaVA-NeXT-Video-7B-Qwen2-Video-Only "
+pretrained = "lmms-lab/LLaVA-Video-7B-Qwen2-Video-Only "
 model_name = "llava_qwen"
 device = "cuda"
 device_map = "auto"