open_clip

src/open_clip/model_configs/convnext_base.json

+{
+    "embed_dim": 512,
+    "vision_cfg": {
+        "timm_model_name": "convnext_base",
+        "timm_model_pretrained": false,
+        "timm_pool": "",
+        "timm_proj": "linear",
+        "timm_drop": 0.0,
+        "timm_drop_path": 0.1,
+        "image_size": 224
+    },
+    "text_cfg": {
+        "context_length": 77,
+        "vocab_size": 49408,
+        "width": 512,
+        "heads": 8,
+        "layers": 12
+    }
+}
\ No newline at end of file

src/open_clip/model_configs/convnext_base_w.json

+{
+    "embed_dim": 640,
+    "vision_cfg": {
+        "timm_model_name": "convnext_base",
+        "timm_model_pretrained": false,
+        "timm_pool": "",
+        "timm_proj": "linear",
+        "timm_drop": 0.0,
+        "timm_drop_path": 0.1,
+        "image_size": 256
+    },
+    "text_cfg": {
+        "context_length": 77,
+        "vocab_size": 49408,
+        "width": 640,
+        "heads": 10,
+        "layers": 12
+    }
+}
\ No newline at end of file

src/open_clip/model_configs/convnext_base_w_320.json

+{
+    "embed_dim": 640,
+    "vision_cfg": {
+        "timm_model_name": "convnext_base",
+        "timm_model_pretrained": false,
+        "timm_pool": "",
+        "timm_proj": "linear",
+        "timm_drop": 0.0,
+        "timm_drop_path": 0.1,
+        "image_size": 320
+    },
+    "text_cfg": {
+        "context_length": 77,
+        "vocab_size": 49408,
+        "width": 640,
+        "heads": 10,
+        "layers": 12
+    }
+}
\ No newline at end of file

src/open_clip/model_configs/convnext_large.json

+{
+    "embed_dim": 768,
+    "vision_cfg": {
+        "timm_model_name": "convnext_large",
+        "timm_model_pretrained": false,
+        "timm_pool": "",
+        "timm_proj": "linear",
+        "timm_drop": 0.0,
+        "timm_drop_path": 0.1,
+        "image_size": 224
+    },
+    "text_cfg": {
+        "context_length": 77,
+        "vocab_size": 49408,
+        "width": 768,
+        "heads": 12,
+        "layers": 12
+    }
+}
\ No newline at end of file

src/open_clip/model_configs/convnext_large_d.json

+{
+    "embed_dim": 768,
+    "vision_cfg": {
+        "timm_model_name": "convnext_large",
+        "timm_model_pretrained": false,
+        "timm_pool": "",
+        "timm_proj": "mlp",
+        "timm_drop": 0.0,
+        "timm_drop_path": 0.1,
+        "image_size": 256
+    },
+    "text_cfg": {
+        "context_length": 77,
+        "vocab_size": 49408,
+        "width": 768,
+        "heads": 12,
+        "layers": 16
+    }
+}
\ No newline at end of file

src/open_clip/model_configs/convnext_large_d_320.json

+{
+    "embed_dim": 768,
+    "vision_cfg": {
+        "timm_model_name": "convnext_large",
+        "timm_model_pretrained": false,
+        "timm_pool": "",
+        "timm_proj": "mlp",
+        "timm_drop": 0.0,
+        "timm_drop_path": 0.1,
+        "image_size": 320
+    },
+    "text_cfg": {
+        "context_length": 77,
+        "vocab_size": 49408,
+        "width": 768,
+        "heads": 12,
+        "layers": 16
+    }
+}
\ No newline at end of file

src/open_clip/model_configs/convnext_small.json

+{
+    "embed_dim": 512,
+    "vision_cfg": {
+        "timm_model_name": "convnext_small",
+        "timm_model_pretrained": false,
+        "timm_pool": "",
+        "timm_proj": "linear",
+        "timm_drop": 0.0,
+        "timm_drop_path": 0.1,
+        "image_size": 224
+    },
+    "text_cfg": {
+        "context_length": 77,
+        "vocab_size": 49408,
+        "width": 512,
+        "heads": 8,
+        "layers": 12
+    }
+}
\ No newline at end of file

src/open_clip/model_configs/convnext_tiny.json

+{
+    "embed_dim": 1024,
+    "vision_cfg": {
+        "timm_model_name": "convnext_tiny",
+        "timm_model_pretrained": false,
+        "timm_pool": "",
+        "timm_proj": "linear",
+        "timm_drop": 0.0,
+        "timm_drop_path": 0.1,
+        "image_size": 224
+    },
+    "text_cfg": {
+        "context_length": 77,
+        "vocab_size": 49408,
+        "width": 512,
+        "heads": 8,
+        "layers": 12
+    }
+}
\ No newline at end of file

src/open_clip/model_configs/convnext_xlarge.json

+{
+    "embed_dim": 1024,
+    "vision_cfg": {
+        "timm_model_name": "convnext_xlarge",
+        "timm_model_pretrained": false,
+        "timm_pool": "",
+        "timm_proj": "linear",
+        "timm_drop": 0.0,
+        "timm_drop_path": 0.1,
+        "image_size": 256
+    },
+    "text_cfg": {
+        "context_length": 77,
+        "vocab_size": 49408,
+        "width": 1024,
+        "heads": 16,
+        "layers": 20
+    }
+}
\ No newline at end of file

src/open_clip/model_configs/convnext_xxlarge.json

+{
+    "embed_dim": 1024,
+    "vision_cfg": {
+        "timm_model_name": "convnext_xxlarge",
+        "timm_model_pretrained": false,
+        "timm_pool": "",
+        "timm_proj": "linear",
+        "timm_drop": 0.0,
+        "timm_drop_path": 0.1,
+        "image_size": 256
+    },
+    "text_cfg": {
+        "context_length": 77,
+        "vocab_size": 49408,
+        "width": 1024,
+        "heads": 16,
+        "layers": 24
+    }
+}
\ No newline at end of file

src/open_clip/model_configs/convnext_xxlarge_320.json

+{
+    "embed_dim": 1024,
+    "vision_cfg": {
+        "timm_model_name": "convnext_xxlarge",
+        "timm_model_pretrained": false,
+        "timm_pool": "",
+        "timm_proj": "linear",
+        "timm_drop": 0.0,
+        "timm_drop_path": 0.1,
+        "image_size": 320
+    },
+    "text_cfg": {
+        "context_length": 77,
+        "vocab_size": 49408,
+        "width": 1024,
+        "heads": 16,
+        "layers": 24
+    }
+}
\ No newline at end of file

src/open_clip/model_configs/mt5-base-ViT-B-32.json

+{
+    "embed_dim": 512,
+    "vision_cfg": {
+        "image_size": 224,
+        "layers": 12,
+        "width": 768,
+        "patch_size": 32
+    },
+    "text_cfg": {
+        "hf_model_name": "google/mt5-base",
+        "hf_tokenizer_name": "google/mt5-base",
+        "hf_pooler_type": "mean_pooler"
+    }
+}

src/open_clip/model_configs/mt5-xl-ViT-H-14.json

+{
+    "embed_dim": 1024,
+    "vision_cfg": {
+        "image_size": 224,
+        "layers": 32,
+        "width": 1280,
+        "head_width": 80,
+        "patch_size": 14
+    },
+    "text_cfg": {
+        "hf_model_name": "google/mt5-xl",
+        "hf_tokenizer_name": "google/mt5-xl",
+        "hf_pooler_type": "mean_pooler"
+    }
+}

src/open_clip/model_configs/nllb-clip-base-siglip.json

+{
+    "embed_dim": 768,
+    "custom_text": true,
+    "init_logit_bias": -10,
+    "vision_cfg": {
+        "image_size": 384,
+        "timm_model_name": "vit_base_patch16_siglip_384",
+        "timm_model_pretrained": false,
+        "timm_pool": "map",
+        "timm_proj": "none"
+    },
+    "text_cfg": {
+        "hf_model_name": "facebook/nllb-200-distilled-600M",
+        "hf_tokenizer_name": "facebook/nllb-200-distilled-600M",
+        "hf_proj_type": "linear",
+        "hf_pooler_type": "cls_pooler"
+    }
+}
\ No newline at end of file

src/open_clip/model_configs/nllb-clip-base.json

+{
+    "embed_dim": 512,
+    "vision_cfg": {
+        "image_size": 224,
+        "layers": 12,
+        "width": 768,
+        "patch_size": 32
+    },
+    "text_cfg": {
+        "hf_model_name": "facebook/nllb-200-distilled-600M",
+        "hf_tokenizer_name": "facebook/nllb-200-distilled-600M",
+        "hf_proj_type": "linear",
+        "hf_pooler_type": "cls_pooler"
+    }
+}
\ No newline at end of file

src/open_clip/model_configs/nllb-clip-large-siglip.json

+{
+    "embed_dim": 1152,
+    "custom_text": true,
+    "init_logit_bias": -10,
+    "vision_cfg": {
+        "image_size": 384,
+        "timm_model_name": "vit_so400m_patch14_siglip_384",
+        "timm_model_pretrained": false,
+        "timm_pool": "map",
+        "timm_proj": "none"
+    },
+    "text_cfg": {
+        "hf_model_name": "facebook/nllb-200-distilled-1.3B",
+        "hf_tokenizer_name": "facebook/nllb-200-distilled-1.3B",
+        "hf_proj_type": "linear",
+        "hf_pooler_type": "cls_pooler"
+    }
+}
\ No newline at end of file

src/open_clip/model_configs/nllb-clip-large.json

+{
+    "embed_dim": 1024,
+    "vision_cfg": {
+        "image_size": 224,
+        "layers": 32,
+        "width": 1280,
+        "head_width": 80,
+        "patch_size": 14
+    },
+    "text_cfg": {
+        "hf_model_name": "facebook/nllb-200-distilled-1.3B",
+        "hf_tokenizer_name": "facebook/nllb-200-distilled-1.3B",
+        "hf_proj_type": "linear",
+        "hf_pooler_type": "cls_pooler"
+    }
+}
\ No newline at end of file

src/open_clip/model_configs/roberta-ViT-B-32.json

+{
+    "embed_dim": 512,
+    "quick_gelu": true,
+    "vision_cfg": {
+        "image_size": 224,
+        "layers": 12,
+        "width": 768,
+        "patch_size": 32
+    },
+    "text_cfg": {
+        "hf_model_name": "roberta-base",
+        "hf_tokenizer_name": "roberta-base",
+        "hf_pooler_type": "mean_pooler"
+    }
+}

src/open_clip/model_configs/swin_base_patch4_window7_224.json

+{
+    "embed_dim": 640,
+    "vision_cfg": {
+        "timm_model_name": "swin_base_patch4_window7_224",
+        "timm_model_pretrained": false,
+        "timm_pool": "",
+        "timm_proj": "linear",
+        "image_size": 224
+    },
+    "text_cfg": {
+        "context_length": 77,
+        "vocab_size": 49408,
+        "width": 640,
+        "heads": 10,
+        "layers": 12
+    }
+}
\ No newline at end of file

src/open_clip/model_configs/vit_medium_patch16_gap_256.json

+{
+    "embed_dim": 512,
+    "vision_cfg": {
+        "timm_model_name": "vit_medium_patch16_gap_256",
+        "timm_model_pretrained": false,
+        "timm_pool": "",
+        "timm_proj": "linear",
+        "image_size": 256
+    },
+    "text_cfg": {
+        "context_length": 77,
+        "vocab_size": 49408,
+        "width": 512,
+        "heads": 8,
+        "layers": 12
+    }
+}
\ No newline at end of file