Add files using upload-large-folder tool

.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

@@ -1,130 +1,130 @@
----
-language: en
-license: mit
-library_name: onnxruntime
-tags:
-- clip
-- vision
-- zero-shot-classification
-- image-text-similarity
-- onnx
-- vit-b32
-pipeline_tag: zero-shot-image-classification
-widget:
-- text: a cat
-  example_image: >-
-    https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/cat.png
-- text: a dog
-  example_image: >-
-    https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/dog.png
-base_model:
-- openai/clip-vit-base-patch32
----
-
-# **CLIP ViT-B/32 (ONNX)**
-
-This repository contains the **ONNX-exported version of OpenAI’s CLIP model (ViT-B/32)**, optimized for inference using [ONNX Runtime](https://onnxruntime.ai/). It supports **fast image-text similarity and zero-shot classification** without requiring PyTorch or TensorFlow.
-
----
-
-## **Model Details**
-
-* **Base Model:** [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32)
-* **Export Format:** ONNX
-* **Architecture:** Vision Transformer (ViT-B/32)
-* **File Size:** \~600 MB
-* **Use Case:** Zero-shot classification, image-text similarity, and retrieval.
-
----
-
-## **Files Included**
-
-```
-model.onnx               # ONNX version of CLIP (ViT-B/32)
-config.json              # Model configuration
-preprocessor_config.json # Preprocessing steps for the CLIPProcessor
-tokenizer.json           # Tokenizer vocabulary and merges
-vocab.json               # BPE vocabulary
-merges.txt               # BPE merges
-special_tokens_map.json  # Special tokens mapping
-tokenizer_config.json    # Tokenizer configuration
-```
-
----
-
-## **How to Use**
-
-### **1. Install Dependencies**
-
-```bash
-pip install onnxruntime transformers huggingface_hub pillow numpy
-```
-
----
-
-### **2. Load the Model and Processor**
-
-```python
-from huggingface_hub import hf_hub_download
-from transformers import CLIPProcessor
-import onnxruntime as ort
-from PIL import Image
-import numpy as np
-
-# Download ONNX model from this repo
-repo_id = "sayantan47/clip-vit-b32-onnx"
-onnx_path = hf_hub_download(repo_id=repo_id, filename="model.onnx")
-
-# Load ONNX Runtime session
-session = ort.InferenceSession(onnx_path, providers=["CPUExecutionProvider"])
-
-# Load CLIP Processor (tokenizer + image preprocessor)
-processor = CLIPProcessor.from_pretrained(repo_id)
-
-# Example input
-image = Image.open("example.jpg")
-texts = ["a dog", "a cat"]
-
-# Preprocess
-inputs = processor(text=texts, images=image, return_tensors="np", padding=True)
-
-# Ensure correct dtype for ONNX
-inputs = {k: (v.astype(np.int64) if v.dtype == np.int32 else v) for k, v in inputs.items()}
-
-# Run inference
-outputs = session.run(None, inputs)
-logits_per_image = outputs[0]
-probs = np.exp(logits_per_image) / np.exp(logits_per_image).sum(-1, keepdims=True)
-print("Probabilities:", probs)
-```
-
----
-
-## **Applications**
-
-* **Zero-Shot Classification:** Classify images by comparing them to textual descriptions.
-* **Image Similarity:** Compare embeddings between two images or between images and text.
-* **Search Engines:** Use as the backbone for image-text retrieval systems.
-
----
-
-## **ONNX Runtime Performance**
-
-* **CPU-only:** Works out of the box with `onnxruntime` on CPUs.
-* **GPU:** To use CUDA, install `onnxruntime-gpu` and ensure you have **CUDA 12 and cuDNN 9** installed.
-
-  ```bash
-  pip install onnxruntime-gpu
-  ```
-
----
-
-## **Export Command Used**
-
-The model was exported using [Hugging Face Optimum](https://huggingface.co/docs/optimum/index) with:
-
-```bash
-python -m optimum.exporters.onnx --model=openai/clip-vit-base-patch32 onnx_model/
-```
-
+---
+language: en
+license: mit
+library_name: onnxruntime
+tags:
+- clip
+- vision
+- zero-shot-classification
+- image-text-similarity
+- onnx
+- vit-b32
+pipeline_tag: zero-shot-image-classification
+widget:
+- text: a cat
+  example_image: >-
+    https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/cat.png
+- text: a dog
+  example_image: >-
+    https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/dog.png
+base_model:
+- openai/clip-vit-base-patch32
+---
+
+# **CLIP ViT-B/32 (ONNX)**
+
+This repository contains the **ONNX-exported version of OpenAI’s CLIP model (ViT-B/32)**, optimized for inference using [ONNX Runtime](https://onnxruntime.ai/). It supports **fast image-text similarity and zero-shot classification** without requiring PyTorch or TensorFlow.
+
+---
+
+## **Model Details**
+
+* **Base Model:** [openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32)
+* **Export Format:** ONNX
+* **Architecture:** Vision Transformer (ViT-B/32)
+* **File Size:** \~600 MB
+* **Use Case:** Zero-shot classification, image-text similarity, and retrieval.
+
+---
+
+## **Files Included**
+
+```
+model.onnx               # ONNX version of CLIP (ViT-B/32)
+config.json              # Model configuration
+preprocessor_config.json # Preprocessing steps for the CLIPProcessor
+tokenizer.json           # Tokenizer vocabulary and merges
+vocab.json               # BPE vocabulary
+merges.txt               # BPE merges
+special_tokens_map.json  # Special tokens mapping
+tokenizer_config.json    # Tokenizer configuration
+```
+
+---
+
+## **How to Use**
+
+### **1. Install Dependencies**
+
+```bash
+pip install onnxruntime transformers huggingface_hub pillow numpy
+```
+
+---
+
+### **2. Load the Model and Processor**
+
+```python
+from huggingface_hub import hf_hub_download
+from transformers import CLIPProcessor
+import onnxruntime as ort
+from PIL import Image
+import numpy as np
+
+# Download ONNX model from this repo
+repo_id = "sayantan47/clip-vit-b32-onnx"
+onnx_path = hf_hub_download(repo_id=repo_id, filename="model.onnx")
+
+# Load ONNX Runtime session
+session = ort.InferenceSession(onnx_path, providers=["CPUExecutionProvider"])
+
+# Load CLIP Processor (tokenizer + image preprocessor)
+processor = CLIPProcessor.from_pretrained(repo_id)
+
+# Example input
+image = Image.open("example.jpg")
+texts = ["a dog", "a cat"]
+
+# Preprocess
+inputs = processor(text=texts, images=image, return_tensors="np", padding=True)
+
+# Ensure correct dtype for ONNX
+inputs = {k: (v.astype(np.int64) if v.dtype == np.int32 else v) for k, v in inputs.items()}
+
+# Run inference
+outputs = session.run(None, inputs)
+logits_per_image = outputs[0]
+probs = np.exp(logits_per_image) / np.exp(logits_per_image).sum(-1, keepdims=True)
+print("Probabilities:", probs)
+```
+
+---
+
+## **Applications**
+
+* **Zero-Shot Classification:** Classify images by comparing them to textual descriptions.
+* **Image Similarity:** Compare embeddings between two images or between images and text.
+* **Search Engines:** Use as the backbone for image-text retrieval systems.
+
+---
+
+## **ONNX Runtime Performance**
+
+* **CPU-only:** Works out of the box with `onnxruntime` on CPUs.
+* **GPU:** To use CUDA, install `onnxruntime-gpu` and ensure you have **CUDA 12 and cuDNN 9** installed.
+
+  ```bash
+  pip install onnxruntime-gpu
+  ```
+
+---
+
+## **Export Command Used**
+
+The model was exported using [Hugging Face Optimum](https://huggingface.co/docs/optimum/index) with:
+
+```bash
+python -m optimum.exporters.onnx --model=openai/clip-vit-base-patch32 onnx_model/
+```
+
 ---

onnx/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e3796fadb6cb16ad79ff34c0873d29cd9ce1578ec621286c13072c6f1014346
+size 605593696

onnx/model_bnb4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e70d5ff773c939a1fcfbe135a344141a8711c617af1914cee33c278649cea15
+size 181695925

onnx/model_fp16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b33a72860c26713ff564d36a162be4e968ee1e50b2418f449076c067735d4fab
+size 303515168

onnx/model_q4.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f518bedb1851294737a141e06149883cb289160760224f2da5498886e49d5cb
+size 189403477

onnx/model_q4f16.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fa5651801a45889d15576d445b23172f706be5b5d17f6d96a61b486cf4a5252
+size 125818295

onnx/model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0898a3facfdb27f0a041e57649b4989cfd094e4a0040d6ae75ed69917dfc7328
+size 153695702

onnx/model_uint8.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ac011172c8c022937bb83dad2e8fc207f52f19972b36e14808cc3c8042c4e60
+size 152738540