initial commit

config.json

@@ -0,0 +1,165 @@
+{
+  "_commit_hash": null,
+  "architectures": [
+    "CLIPModel"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 512,
+  "text_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 512,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 2048,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 77,
+    "min_length": 0,
+    "model_type": "clip_text_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 8,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.29.2",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 49408
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "clip_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 32,
+    "prefix": null,
+    "problem_type": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.29.2",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4daa7650d2b47e55c37b5ca7dcabe826fd82407c26028a574bcc422f35a94aa4
+size 605222477

scripts/pt_model.py

@@ -0,0 +1,50 @@
+import argparse
+import torch
+from transformers import CLIPConfig, CLIPModel
+from transformers.models.clip.convert_clip_original_pytorch_to_hf import copy_text_model_and_projection, copy_vison_model_and_projection
+from clip.clip import build_model
+
+@torch.no_grad()
+def convert_clip_checkpoint(checkpoint_path, pytorch_dump_folder_path, config_path=None):
+    """
+    Copy/paste/tweak model's weights to transformers design. Adapted from
+    https://github.com/huggingface/transformers/blob/3723329d014a7b144863e597ea4fe6de5e6a8279/src/transformers/models/clip/convert_clip_original_pytorch_to_hf.py#LL108C1-L138C55
+    """
+    if config_path is not None:
+        config = CLIPConfig.from_pretrained(config_path)
+    else:
+        config = CLIPConfig(projection_dim=512, text_config={}, vision_config={})
+
+    hf_model = CLIPModel(config).eval()
+
+    # Load the pre-trained checkpoint, this can be downloaded from the OneDrive link shared by the authors: https://1drv.ms/u/s!ApXgPqe9kykTgwD4Np3-f7ODAot8?e=zLVlJ2
+    checkpoint = torch.load(checkpoint_path, map_location="cpu")
+    pt_model = build_model(checkpoint["state_dict"])
+    pt_model = pt_model.float()
+    pt_model = pt_model.eval()
+
+    copy_text_model_and_projection(hf_model, pt_model)
+    copy_vison_model_and_projection(hf_model, pt_model)
+    hf_model.logit_scale = pt_model.logit_scale
+
+    input_ids = torch.arange(0, 77).unsqueeze(0)
+    pixel_values = torch.randn(1, 3, 224, 224)
+
+    hf_outputs = hf_model(input_ids=input_ids, pixel_values=pixel_values, return_dict=True)
+    hf_logits_per_image = hf_outputs.logits_per_image
+    hf_logits_per_text = hf_outputs.logits_per_text
+    pt_logits_per_image, pt_logits_per_text = pt_model(pixel_values, input_ids)
+
+    assert torch.allclose(hf_logits_per_image, pt_logits_per_image, atol=1e-3)
+    assert torch.allclose(hf_logits_per_text, pt_logits_per_text, atol=1e-3)
+
+    hf_model.save_pretrained(pytorch_dump_folder_path)
+    
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--pytorch_dump_folder_path", default=None, type=str, help="Path to the output PyTorch model.")
+    parser.add_argument("--checkpoint_path", default="PubMedCLIP_ViT32.pth", type=str, help="Path to PubMedCLIP ViT32 checkpoint")
+    parser.add_argument("--config_path", default=None, type=str, help="Path to hf config.json of model to convert")
+    args = parser.parse_args()
+    convert_clip_checkpoint(args.checkpoint_path, args.pytorch_dump_folder_path, args.config_path)