update

config.json

@@ -0,0 +1,23 @@
+{
+ "_name_or_path": "clip-vit-H-14-laion2B-s32B-b79K-yi-vl-34B-448",
+ "architectures": [
+ "CLIPVisionModel"
+ ],
+ "attention_dropout": 0.0,
+ "dropout": 0.0,
+ "hidden_act": "gelu",
+ "hidden_size": 1280,
+ "image_size": 448,
+ "initializer_factor": 1.0,
+ "initializer_range": 0.02,
+ "intermediate_size": 5120,
+ "layer_norm_eps": 1e-05,
+ "model_type": "clip_vision_model",
+ "num_attention_heads": 16,
+ "num_channels": 3,
+ "num_hidden_layers": 32,
+ "patch_size": 14,
+ "projection_dim": 1024,
+ "torch_dtype": "float32",
+ "transformers_version": "4.34.0"
+}

open_clip_config.json

@@ -0,0 +1,31 @@
+{
+ "model_cfg": {
+ "embed_dim": 1024,
+ "vision_cfg": {
+ "image_size": 224,
+ "layers": 32,
+ "width": 1280,
+ "head_width": 80,
+ "patch_size": 14
+ },
+ "text_cfg": {
+ "context_length": 77,
+ "vocab_size": 49408,
+ "width": 1024,
+ "heads": 16,
+ "layers": 24
+ }
+ },
+ "preprocess_cfg": {
+ "mean": [
+ 0.48145466,
+ 0.4578275,
+ 0.40821073
+ ],
+ "std": [
+ 0.26862954,
+ 0.26130258,
+ 0.27577711
+ ]
+ }
+}

open_clip_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a78ef8e8c73fd0df621682e7a8e8eb36c6916cb3c16b291a082ecd52ab79cc4
+size 3944692325

preprocessor_config.json

@@ -0,0 +1,19 @@
+{
+ "crop_size": 448,
+ "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": 448
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa0c1b4a16fa93bd8bb53e5190e8624dc6f5de5175b9c6ebf02cc5c545247e6a
+size 2527168934

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+ "unk_token": {
+ "content": "<|endoftext|>",
+ "single_word": false,
+ "lstrip": false,
+ "rstrip": false,
+ "normalized": true,
+ "__type": "AddedToken"
+ },
+ "bos_token": {
+ "content": "<|startoftext|>",
+ "single_word": false,
+ "lstrip": false,
+ "rstrip": false,
+ "normalized": true,
+ "__type": "AddedToken"
+ },
+ "eos_token": {
+ "content": "<|endoftext|>",
+ "single_word": false,
+ "lstrip": false,
+ "rstrip": false,
+ "normalized": true,
+ "__type": "AddedToken"
+ },
+ "pad_token": "<|endoftext|>",
+ "add_prefix_space": false,
+ "errors": "replace",
+ "do_lower_case": true,
+ "name_or_path": "openai/clip-vit-base-patch32",
+ "model_max_length": 77,
+ "special_tokens_map_file": "./special_tokens_map.json",
+ "tokenizer_class": "CLIPTokenizer"
+}