Upload 4 files

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,12 +1,16 @@
----
-title: Moondream Webui
-emoji: 😻
-colorFrom: indigo
-colorTo: green
-sdk: gradio
-sdk_version: 4.42.0
-app_file: app.py
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: moondream-webui
+emoji: 🌔🌔🌔
+colorFrom: indigo
+colorTo: blue
+sdk: gradio
+sdk_version: 4.42.0
+app_file: app.py
+pinned: false
+short_description: demo of batch processing with moondream
+license: apache-2.0
+preload_from_hub:
+- vikhyatk/moondream2
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,65 @@
+import spaces
+import torch
+import re
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from PIL import Image
+
+if torch.cuda.is_available():
+    device, dtype = "cuda", torch.float16
+else:
+    device, dtype = "cpu", torch.float32
+
+model_id = "vikhyatk/moondream2"
+revision = "2024-08-26"
+tokenizer = AutoTokenizer.from_pretrained(model_id, revision=revision)
+moondream = AutoModelForCausalLM.from_pretrained(
+    model_id, trust_remote_code=True, revision=revision, torch_dtype=dtype
+).to(device=device)
+moondream.eval()
+
+@spaces.GPU
+def answer_questions(image_tuples, prompt_text):
+    result = ""
+    Q_and_A = ""
+    prompts = [p.strip() for p in prompt_text.split(',')]  
+    image_embeds = [img[0] for img in image_tuples if img[0] is not None]
+
+    #print(f"\nprompts: {prompts}\n\n")
+    answers = []
+    for prompt in prompts:
+        image_answers = moondream.batch_answer(
+            images=[img.convert("RGB") for img in image_embeds],
+            prompts=[prompt] * len(image_embeds),
+            tokenizer=tokenizer,
+        )
+        answers.append(image_answers)
+    
+    for i, prompt in enumerate(prompts):
+        Q_and_A += f"### Q: {prompt}\n"
+        for j, image_tuple in enumerate(image_tuples):
+            image_name = f"image{j+1}"
+            answer_text = answers[i][j]  
+            Q_and_A += f"**{image_name} A:** \n {answer_text} \n\n"
+
+    result = {'headers': prompts, 'data': answers} 
+    #print(f"result\n{result}\n\nQ_and_A\n{Q_and_A}\n\n")
+    return Q_and_A, result
+
+with gr.Blocks() as demo:
+    gr.Markdown("# MoonDream WebUI")
+    gr.Markdown("## 🌔 Modify by https://huggingface.co/spaces/Csplk/moondream2-batch-processing")
+    gr.Markdown("## 🌔 moondream2\nA tiny vision language model. [GitHub](https://github.com/vikhyatk/moondream)")
+    with gr.Row():
+        img = gr.Gallery(label="Upload Images", type="pil", preview=True, columns=4)
+    with gr.Row():
+        prompt = gr.Textbox(label="Input Prompts", placeholder="Enter prompts (one prompt for each image provided) separated by commas. Ex: Describe this image, What is in this image?", lines=8)
+    with gr.Row():
+        submit = gr.Button("Submit")
+    with gr.Row():
+        output = gr.Markdown(label="Questions and Answers", line_breaks=True)
+    with gr.Row():
+        output2 = gr.Dataframe(label="Structured Dataframe", type="array", wrap=True)
+    submit.click(answer_questions, [img, prompt], [output, output2])
+
+demo.queue().launch()

requirements.txt

@@ -0,0 +1,5 @@
+timm
+transformers
+einops
+accelerate
+torch