Upload 10 files

README.md

@@ -1,3 +1,34 @@
----
-license: apache-2.0
----
+---
+tags:
+- clip
+library_name: open_clip
+pipeline_tag: zero-shot-image-classification
+license: other
+license_name: apple-ascl
+license_link: https://github.com/apple/ml-mobileclip/blob/main/LICENSE_weights_data
+---
+
+# MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
+
+MobileCLIP was introduced in [MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training
+](https://arxiv.org/pdf/2311.17049.pdf) (CVPR 2024), by Pavan Kumar Anasosalu Vasu, Hadi Pouransari, Fartash Faghri, Raviteja Vemulapalli, Oncel Tuzel.
+
+This repository contains the **MobileCLIP-B (LT)** checkpoint for OpenCLIP.
+
+![MobileCLIP Performance Figure](fig_accuracy_latency.png)
+
+### Highlights
+
+* Our smallest variant `MobileCLIP-S0` obtains similar zero-shot performance as [OpenAI](https://arxiv.org/abs/2103.00020)'s ViT-B/16 model while being 4.8x faster and 2.8x smaller.
+* `MobileCLIP-S2` obtains better avg zero-shot performance than [SigLIP](https://arxiv.org/abs/2303.15343)'s ViT-B/16 model while being 2.3x faster and 2.1x smaller, and trained with 3x less seen samples.
+* `MobileCLIP-B`(LT) attains zero-shot ImageNet performance of **77.2%** which is significantly better than recent works like [DFN](https://arxiv.org/abs/2309.17425) and [SigLIP](https://arxiv.org/abs/2303.15343) with similar architectures or even [OpenAI's ViT-L/14@336](https://arxiv.org/abs/2103.00020).
+
+## Checkpoints
+
+| Model                                                     | # Seen <BR>Samples (B) | # Params (M) <BR> (img + txt) | Latency (ms) <BR> (img + txt) | IN-1k Zero-Shot <BR> Top-1 Acc. (%) | Avg. Perf. (%) <BR> on 38 datasets |
+|:----------------------------------------------------------|:----------------------:|:-----------------------------:|:-----------------------------:|:-----------------------------------:|:----------------------------------:|
+| [MobileCLIP-S0](https://hf.co/pcuenq/MobileCLIP-S0)       |           13           |          11.4 + 42.4          |           1.5 + 1.6           |                67.8                 |                58.1                |
+| [MobileCLIP-S1](https://hf.co/pcuenq/MobileCLIP-S1)       |           13           |          21.5 + 63.4          |           2.5 + 3.3           |                72.6                 |                61.3                |
+| [MobileCLIP-S2](https://hf.co/pcuenq/MobileCLIP-S2)       |           13           |          35.7 + 63.4          |           3.6 + 3.3           |                74.4                 |                63.7                |
+| [MobileCLIP-B](https://hf.co/pcuenq/MobileCLIP-B)         |           13           |          86.3 + 63.4          |          10.4 + 3.3           |                76.8                 |                65.2                |
+| [MobileCLIP-B (LT)](https://hf.co/pcuenq/MobileCLIP-B-LT) |           36           |          86.3 + 63.4          |          10.4 + 3.3           |                77.2                 |                65.8                |

open_clip_config.json

@@ -0,0 +1,37 @@
+{
+  "model_cfg": {
+    "embed_dim": 512,
+    "vision_cfg": {
+      "timm_model_name": "vit_base_mci_224",
+      "timm_model_pretrained": false,
+      "timm_pool": "token",
+      "timm_proj": null,
+      "timm_drop": 0.0,
+      "timm_drop_path": 0.0,
+      "image_size": 224
+    },
+    "text_cfg": {
+      "context_length": 77,
+      "vocab_size": 49408,
+      "width": 512,
+      "heads": 8,
+      "layers": 12,
+      "no_causal_mask": false
+    },
+    "custom_text": true
+  },
+  "preprocess_cfg": {
+    "mean": [
+      0.0,
+      0.0,
+      0.0
+    ],
+    "std": [
+      1.0,
+      1.0,
+      1.0
+    ],
+    "interpolation": "bilinear",
+    "resize_mode": "shortest"
+  }
+}

open_clip_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24e11895c9fd90221880f0530ea4c2de251056bf741db5a36028f69d73e092c3
+size 599146420

open_clip_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99c035dfc5709774316aefffa260256278c78aee0bb9377ae81a77150982b01b
+size 599238878

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|>"
+}