upload files

README copy.md

@@ -0,0 +1,12 @@
+---
+title: Final Instagram Caption Model
+emoji: 🌍
+colorFrom: green
+colorTo: gray
+sdk: gradio
+sdk_version: 4.44.1
+app_file: app.py
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "GitForCausalLM",
+    "parent_library": "transformers.models.git.modeling_git"
+  },
+  "base_model_name_or_path": "microsoft/git-base",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier"
+  ],
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "value",
+    "query"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43229defd2d74cf95ce3eeb187b493d6a409cf75b93ed92f9eb077e9347a6c25
+size 593144

app.py

@@ -0,0 +1,40 @@
+
+from transformers import pipeline, AutoProcessor, AutoModelForCausalLM
+import gradio as gr
+import torch
+
+processor = AutoProcessor.from_pretrained("microsoft/git-base")
+model = AutoModelForCausalLM.from_pretrained('./')
+
+def predict(image):
+        # Prepare the image using the processor
+        inputs = processor(images=image, return_tensors="pt")
+
+        # Move inputs to the appropriate device
+        device = "cuda" if torch.cuda.is_available() else "cpu"
+        inputs = {key: value.to(device) for key, value in inputs.items()}
+        model.to(device)
+
+        # Generate the caption
+        outputs = model.generate(**inputs)
+
+        # Decode the generated caption
+        caption = processor.batch_decode(outputs, skip_special_tokens=True)[0]
+
+        return caption
+
+
+with gr.Blocks() as demo:
+    image = gr.Image(type="pil")
+    predict_btn = gr.Button("Predict", variant="primary")
+    output = gr.Label(label="Generated Caption")
+
+    inputs = [image]
+    outputs = [output]
+
+    predict_btn.click(predict, inputs=inputs, outputs=outputs)
+
+if __name__ == "__main":
+    demo.launch() # Local machine only
+    # demo.launch(server_name="0.0.0.0") # LAN access to local machine
+    # demo.launch(share=True) # Public access to local machine