test

app.py

@@ -8,8 +8,10 @@ from PIL import Image, ImageDraw
 from io import BytesIO
 import re
 
-from deepseek_vl.models import DeepseekVLV2Processor, DeepseekVLV2ForCausalLM
-from deepseek_vl.utils.io import load_pil_images
+from deepseek_vl2.models import DeepseekVLV2Processor, DeepseekVLV2ForCausalLM
+from deepseek_vl2.utils.io import load_pil_images
+
+
 from transformers import AutoModelForCausalLM
 
 
@@ -56,9 +58,8 @@ def rescale_bounding_boxes(bounding_boxes, original_width, original_height, scal
 
 def deepseek():
     print("helloe!!!!")
-        
     # specify the path to the model
-    model_path = "deepseek-ai/deepseek-vl2-small"
+    model_path = "deepseek-ai/deepseek-vl2-tiny"
     vl_chat_processor: DeepseekVLV2Processor = DeepseekVLV2Processor.from_pretrained(model_path)
     tokenizer = vl_chat_processor.tokenizer
 
@@ -70,29 +71,11 @@ def deepseek():
         {
             "role": "<|User|>",
             "content": "<image>\n<|ref|>The giraffe at the back.<|/ref|>.",
-            "images": ["./images/visual_grounding.jpeg"],
+            "images": ["./images/visual_grounding_1.jpeg"],
         },
         {"role": "<|Assistant|>", "content": ""},
     ]
 
-    ## multiple images (or in-context learning) conversation example
-    # conversation = [
-    #     {
-    #         "role": "User",
-    #         "content": "<image_placeholder>A dog wearing nothing in the foreground, "
-    #                    "<image_placeholder>a dog wearing a santa hat, "
-    #                    "<image_placeholder>a dog wearing a wizard outfit, and "
-    #                    "<image_placeholder>what's the dog wearing?",
-    #         "images": [
-    #             "images/dog_a.png",
-    #             "images/dog_b.png",
-    #             "images/dog_c.png",
-    #             "images/dog_d.png",
-    #         ],
-    #     },
-    #     {"role": "Assistant", "content": ""}
-    # ]
-
     # load images and prepare for inputs
     pil_images = load_pil_images(conversation)
     prepare_inputs = vl_chat_processor(
@@ -106,7 +89,7 @@ def deepseek():
     inputs_embeds = vl_gpt.prepare_inputs_embeds(**prepare_inputs)
 
     # run the model to get the response
-    outputs = vl_gpt.language_model.generate(
+    outputs = vl_gpt.language.generate(
         inputs_embeds=inputs_embeds,
         attention_mask=prepare_inputs.attention_mask,
         pad_token_id=tokenizer.eos_token_id,
@@ -117,9 +100,10 @@ def deepseek():
         use_cache=True
     )
 
-    answer = tokenizer.decode(outputs[0].cpu().tolist(), skip_special_tokens=True)
+    answer = tokenizer.decode(outputs[0].cpu().tolist(), skip_special_tokens=False)
     print(f"{prepare_inputs['sft_format'][0]}", answer)
 
+
 @spaces.GPU
 def run_example(image, text_input, model_id="OS-Copilot/OS-Atlas-Base-7B"):
 

requirements.txt

@@ -6,5 +6,4 @@ torchvision
 transformers
 accelerate==0.30.0
 qwen-vl-utils
-deepseek-vl @ git+https://github.com/deepseek-ai/DeepSeek-VL.git
-
+deepseek-vl2 @ git+https://github.com/deepseek-ai/DeepSeek-VL2.git