Upload folder using huggingface_hub

README.md

@@ -0,0 +1,31 @@
+---
+tags:
+  - vision
+---
+
+This repository contains the clip-vit-large-patch14to16-336 model, which is modified from https://huggingface.co/openai/clip-vit-large-patch14-336 by resizing the position embedding and patch embeding to the patch size of 16.
+
+Please refer to our [**paper**](https://huggingface.co/papers/2501.07783) and [**GitHub repository**](https://github.com/OpenGVLab/PIIP/tree/main/llava) for introduction and usage.
+
+
+
+## Citation
+
+If you find this project useful in your research, please consider citing:
+
+```BibTeX
+@article{piip,
+  title={Parameter-Inverted Image Pyramid Networks},
+  author={Zhu, Xizhou and Yang, Xue and Wang, Zhaokai and Li, Hao and Dou, Wenhan and Ge, Junqi and Lu, Lewei and Qiao, Yu and Dai, Jifeng},
+  journal={arXiv preprint arXiv:2406.04330},
+  year={2024}
+}
+
+@article{piip_v2,
+  title={Parameter-Inverted Image Pyramid Networks for Visual Perception and Multimodal Understanding},
+  author={Wang, Zhaokai and Zhu, Xizhou and Yang, Xue and Luo, Gen and Li, Hao and Tian, Changyao and Dou, Wenhan and Ge, Junqi and Lu, Lewei and Qiao, Yu and Dai, Jifeng},
+  journal={arXiv preprint arXiv:2501.07783},
+  year={2025}
+}
+```
+

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "clip-vit-large-patch14to16-336",
+  "architectures": [
+    "CLIPModel"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 768,
+  "text_config": {
+    "dropout": 0.0,
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "model_type": "clip_text_model",
+    "num_attention_heads": 12,
+    "projection_dim": 768
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "vision_config": {
+    "dropout": 0.0,
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 16,
+    "projection_dim": 768
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9838bf0ad1addf77f820a911d1104a596fe0625556ccfd703019bcadde21ccd
+size 1712032756

preprocessor_config.json

@@ -0,0 +1,20 @@
+{
+    "crop_size": 336,
+    "do_center_crop": true,
+    "do_normalize": true,
+    "do_resize": true,
+    "feature_extractor_type": "CLIPFeatureExtractor",
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "resample": 3,
+    "size": 336
+  }
+  

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "49406": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49407": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}