Add model

README.md

@@ -0,0 +1,14 @@
+---
+tags:
+- clip
+library_name: open_clip
+pipeline_tag: zero-shot-image-classification
+license: cc-by-nc-4.0
+---
+# Model card for vit_base_patch16_clip_224.metaclip_400m
+
+## Model Details
+- **dataset:** MetaCLIP-400M
+
+## Model Usage
+This model is a dual use `open_clip` and `timm` model. Model name in OpenCLIP is `ViT-B-16-quickgelu`, and timm name is `vit_base_patch16_clip_224.metaclip_400m`.

open_clip_config.json

@@ -0,0 +1,33 @@
+{
+  "model_cfg": {
+    "embed_dim": 512,
+    "quick_gelu": true,
+    "vision_cfg": {
+      "image_size": 224,
+      "layers": 12,
+      "width": 768,
+      "patch_size": 16
+    },
+    "text_cfg": {
+      "context_length": 77,
+      "vocab_size": 49408,
+      "width": 512,
+      "heads": 8,
+      "layers": 12
+    }
+  },
+  "preprocess_cfg": {
+    "mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "interpolation": "bicubic",
+    "resize_mode": "shortest"
+  }
+}

open_clip_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17b019f72e45bd43264683c7bd0b3f7910feddd86b4cf439c9b603a94bf36800
+size 598516980

open_clip_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:548a0463a7a0c1371ab9492317050ca1a84e5328051b0ba9d0b6019f30e24601
+size 598599478

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": false,
+  "do_lower_case": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 77,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": "<|endoftext|>"
+}