Upload folder using huggingface_hub

README.md

@@ -32,7 +32,7 @@ We built the Sa2VA series based on Qwen2-VL and InternVL2/2.5. In the following
 
 | Model Name |                             Base MLLM                             |                                 Language Part                                 |                       HF Link                        |
 |:----------:|:-----------------------------------------------------------------:|:-----------------------------------------------------------------------------:|:----------------------------------------------------:|
-|  Sa2VA-1B  | [InternVL2.5-1B](https://huggingface.co/OpenGVLab/InternVL2_5-1B) |   [Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct)    | [🤗 link](https://huggingface.co/ByteDance/Sa2VA-1B) |
+|  Sa2VA-1B  | [InternVL2.0-1B](https://huggingface.co/OpenGVLab/InternVL2-1B) |   [Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct)    | [🤗 link](https://huggingface.co/ByteDance/Sa2VA-1B) |
 |  Sa2VA-4B  | [InternVL2.5-4B](https://huggingface.co/OpenGVLab/InternVL2_5-4B) |    [Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct)     | [🤗 link](https://huggingface.co/ByteDance/Sa2VA-4B) |
 |  Sa2VA-8B  | [InternVL2.5-8B](https://huggingface.co/OpenGVLab/InternVL2_5-8B) |  [internlm2_5-7b-chat](https://huggingface.co/internlm/internlm2_5-7b-chat)   | [🤗 link](https://huggingface.co/ByteDance/Sa2VA-8B) |
 
@@ -67,7 +67,7 @@ tokenizer = AutoTokenizer.from_pretrained(path, trust_remote_code=True, use_fast
 
 # for image chat
 image_path = "/PATH/TO/IMAGE"
-text_prompts = "Please describe the image."
+text_prompts = "<image>\nPlease describe the image."
 image = Image.open(image_path).convert('RGB')
 input_dict = {
     'image': image,
@@ -81,7 +81,7 @@ answer = return_dict["prediction"] # the text format answer
 
 # for image chat with segmentation output
 image_path = "/PATH/TO/IMAGE"
-text_prompts = "Could you please give me a brief description of the image? Please respond with interleaved segmentation masks for the corresponding parts of the answer."
+text_prompts = "<image>\nCould you please give me a brief description of the image? Please respond with interleaved segmentation masks for the corresponding parts of the answer."
 image = Image.open(image_path).convert('RGB')
 input_dict = {
     'image': image,
@@ -97,7 +97,7 @@ masks = return_dict['prediction_masks']  # segmentation masks, list(np.array(1,
 # for chat with visual prompt (mask format) input
 mask_prompts = np.load('/PATH/TO/pred_masks.npy') # np.array(n_prompts, h, w)
 image_path = "/PATH/TO/IMAGE"
-text_prompts = "Can you provide me with a detailed description of the region in the picture marked by region1."
+text_prompts = "<image>\nCan you provide me with a detailed description of the region in the picture marked by region1."
 image = Image.open(image_path).convert('RGB')
 input_dict = {
     'image': image,
@@ -116,7 +116,7 @@ images_paths = [os.path.join(video_folder, image_path) for image_name in images_
 if len(images_paths) > 5:  # uniformly sample 5 frames
     step = (len(images_paths) - 1) // (5 - 1)
     images_paths = [images_paths[0]] + images_paths[1:-1][::step][1:] + [images_paths[-1]]
-text_prompts = "Please describe the video."
+text_prompts = "<image>\nPlease describe the video."
 input_dict = {
     'video': images_paths,
     'text': text_prompts,
@@ -132,7 +132,7 @@ answer = return_dict["prediction"] # the text format answer
 video_folder = "/PATH/TO/VIDEO_FOLDER"
 images_paths = os.listdir(video_folder)
 images_paths = [os.path.join(video_folder, image_path) for image_name in images_paths]
-text_prompts = "Please segment the person."
+text_prompts = "<image>\nPlease segment the person."
 input_dict = {
     'video': images_paths,
     'text': text_prompts,