Upload 8 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,52 @@
+---
+license: mit
+datasets:
+- markury/AndroAtlas
+language:
+- en
+base_model:
+- google/paligemma-3b-mix-448
+pipeline_tag: image-text-to-text
+tags:
+- captioning
+---
+
+```python
+import torch
+from transformers import PaliGemmaForConditionalGeneration, PaliGemmaProcessor
+from PIL import Image
+
+def download_model(model_id):
+    model = PaliGemmaForConditionalGeneration.from_pretrained(model_id)
+    processor = PaliGemmaProcessor.from_pretrained(model_id)
+    return model, processor
+
+def infer(model, processor, image_path, text, max_new_tokens=128):
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    model = model.to(device)
+    model.eval()
+
+    image = Image.open(image_path)
+    inputs = processor(text=text, images=image, return_tensors="pt").to(device)
+
+    with torch.inference_mode():
+        generated_ids = model.generate(
+            **inputs,
+            max_new_tokens=max_new_tokens,
+            do_sample=False
+        )
+    
+    result = processor.batch_decode(generated_ids, skip_special_tokens=True)
+    return result[0][len(text):].lstrip("\n")
+
+def main():
+    model_id = "prolapse/malensfw-paligemma-fp16"
+    model, processor = download_model(model_id)
+    image_path = "/path/to/image.png"
+    prompt = "describe this photo"
+    result = infer(model, processor, image_path, text)
+    print(result)
+
+if __name__ == "__main__":
+    main()
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image>": 257152
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.42.4"
+}

preprocessor_config.json

@@ -0,0 +1,25 @@
+{
+  "do_convert_rgb": null,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "SiglipImageProcessor",
+  "image_seq_length": 1024,
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "processor_class": "PaliGemmaProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 448,
+    "width": 448
+  }
+}

special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<image>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a15d33625f5a34be43c42d23acc1f26f026c9cd9d6f8ab3d9da05dd2a62e643c
+size 17770231

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8986bb4f423f07f8c7f70d0dbe3526fb2316056c17bae71b1ea975e77a168fc6
+size 4264023