update app (#5)

- update app (49a81e87b12c424ddc163194fa0b62d05713c2d0)

app.py

@@ -78,6 +78,15 @@ model_x = AutoModelForVision2Seq.from_pretrained(
     torch_dtype=torch.float16
 ).to(device).eval()
 
+# Nemesis-VLMer-7B-0818
+MODEL_ID_N = "prithivMLmods/Nemesis-VLMer-7B-0818"
+processor_n = AutoProcessor.from_pretrained(MODEL_ID_N, trust_remote_code=True)
+model_n = Qwen2_5_VLForConditionalGeneration.from_pretrained(
+    MODEL_ID_N,
+    trust_remote_code=True,
+    torch_dtype=torch.float16
+).to(device).eval()
+
 # Preprocessing functions for SmolDocling-256M
 def add_random_padding(image, min_percent=0.1, max_percent=0.10):
     """Add random padding to an image based on its size."""
@@ -144,6 +153,9 @@ def generate_image(model_name: str, text: str, image: Image.Image,
     elif model_name == "Typhoon-OCR-7B":
         processor = processor_l
         model = model_l
+    elif model_name == "Nemesis-VLMer-7B":
+        processor = processor_n
+        model = model_n
     else:
         yield "Invalid model selected.", "Invalid model selected."
         return
@@ -222,6 +234,9 @@ def generate_video(model_name: str, text: str, video_path: str,
     elif model_name == "Typhoon-OCR-7B":
         processor = processor_l
         model = model_l
+    elif model_name == "Nemesis-VLMer-7B":
+        processor = processor_n
+        model = model_n
     else:
         yield "Invalid model selected.", "Invalid model selected."
         return
@@ -352,7 +367,7 @@ with gr.Blocks(css=css, theme="bethecloud/storj_theme") as demo:
                     formatted_output = gr.Markdown(label="(Result.md)")
             
             model_choice = gr.Radio(
-                choices=["Nanonets-OCR-s", "MonkeyOCR-Recognition", "Typhoon-OCR-7B", "SmolDocling-256M-preview"],
+                choices=["Nanonets-OCR-s", "MonkeyOCR-Recognition", "Typhoon-OCR-7B", "SmolDocling-256M-preview", "Nemesis-VLMer-7B"],
                 label="Select Model",
                 value="Nanonets-OCR-s"
             )
@@ -362,6 +377,7 @@ with gr.Blocks(css=css, theme="bethecloud/storj_theme") as demo:
             gr.Markdown("> [SmolDocling-256M](https://huggingface.co/ds4sd/SmolDocling-256M-preview): SmolDocling is a multimodal Image-Text-to-Text model designed for efficient document conversion. It retains Docling's most popular features while ensuring full compatibility with Docling through seamless support for DoclingDocuments.")
             gr.Markdown("> [MonkeyOCR-Recognition](https://huggingface.co/echo840/MonkeyOCR): MonkeyOCR adopts a Structure-Recognition-Relation (SRR) triplet paradigm, which simplifies the multi-tool pipeline of modular approaches while avoiding the inefficiency of using large multimodal models for full-page document processing.")
             gr.Markdown("> [Typhoon-OCR-7B](https://huggingface.co/scb10x/typhoon-ocr-7b): A bilingual document parsing model built specifically for real-world documents in Thai and English inspired by models like olmOCR based on Qwen2.5-VL-Instruction. Extracts and interprets embedded text (e.g., chart labels, captions) in Thai or English.")
+            gr.Markdown("> [Nemesis-VLMer-7B-0818](https://huggingface.co/prithivMLmods/Nemesis-VLMer-7B-0818): The Nemesis-VLMer-7B-0818 model is a fine-tuned version of Qwen2.5-VL-7B-Instruct, optimized for Reasoning, Content Analysis, and Visual Question Answering. Built on top of the Qwen2.5-VL architecture, this model enhances multimodal comprehension capabilities ")
             gr.Markdown(">⚠️note: all the models in space are not guaranteed to perform well in video inference use cases.")  
             
     image_submit.click(