Upload 9 files

README.md

@@ -0,0 +1,66 @@
+---
+tags:
+- clip
+language: ko
+license: mit
+---
+
+# vitB32_bert_ko_small_clip
+
+[openai/clip-vit-base-patch32](https://huggingface.co/openai/clip-vit-base-patch32) + [lassl/bert-ko-small](https://huggingface.co/lassl/bert-ko-small) CLIP Model
+
+[training code(github)](https://github.com/Bing-su/KoCLIP_training_code)
+
+## Train
+
+SBERT의 [Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://arxiv.org/abs/2004.09813)를 참고하여, `openai/clip-vit-base-patch32` 텍스트 모델의 가중치를 `lassl/bert-ko-small`로 복제하였습니다. 논문과는 달리 mean pooling을 사용하지 않고, huggingface모델의 기본 pooling을 그대로 사용하였습니다.
+
+사용한 데이터: [Aihub 한국어-영어 번역(병렬) 말뭉치](https://aihub.or.kr/aidata/87)
+
+
+## How to Use
+
+#### 1.
+
+```python
+import requests
+from PIL import Image
+from transformers import VisionTextDualEncoderProcessor, VisionTextDualEncoderModel  # or Auto...
+
+model = VisionTextDualEncoderModel.from_pretrained("Bingsu/vitB32_bert_ko_small_clip")
+processor = VisionTextDualEncoderProcessor.from_pretrained("Bingsu/vitB32_bert_ko_small_clip")
+
+url = "http://images.cocodataset.org/val2017/000000039769.jpg"
+image = Image.open(requests.get(url, stream=True).raw)
+
+inputs = processor(text=["고양이 두 마리", "개 두 마리"], images=image, return_tensors="pt", padding=True)
+
+outputs = model(**inputs)
+logits_per_image = outputs.logits_per_image
+probs = logits_per_image.softmax(dim=1)
+```
+
+```pycon
+>>> probs
+tensor([[0.9756, 0.0244]], grad_fn=<SoftmaxBackward0>)
+```
+
+#### 2.
+
+```python
+from transformers import AutoModel, AutoProcessor, pipeline
+
+model = AutoModel.from_pretrained("Bingsu/vitB32_bert_ko_small_clip")
+processor = AutoProcessor.from_pretrained("Bingsu/vitB32_bert_ko_small_clip")
+pipe = pipeline("zero-shot-image-classification", model=model, feature_extractor=processor.feature_extractor, tokenizer=processor.tokenizer)
+
+url = "http://images.cocodataset.org/val2017/000000039769.jpg"
+result = pipe(images=url, candidate_labels=["고양이 한 마리", "고양이 두 마리", "고양이 두 마리와 리모컨 두 개"], hypothesis_template="{}")
+```
+
+```pycon
+>>> result
+[{'score': 0.871887743473053, 'label': '고양이 두 마리와 리모컨 두 개'},
+ {'score': 0.12316706776618958, 'label': '고양이 두 마리'},
+ {'score': 0.004945191089063883, 'label': '고양이 한 마리'}]
+```

config.json

@@ -0,0 +1,162 @@
+{
+  "_name_or_path": "Bingsu/vitB32_bert_ko_small_clip",
+  "architectures": [
+    "VisionTextDualEncoderModel"
+  ],
+  "logit_scale_init_value": 2.6592,
+  "model_type": "vision-text-dual-encoder",
+  "projection_dim": 512,
+  "text_config": {
+    "_name_or_path": "lassl/bert-ko-small",
+    "add_cross_attention": false,
+    "architectures": [
+      "BertForPreTraining"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.1,
+    "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": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 256,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 1024,
+    "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": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 4,
+    "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": 0,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "transformers_version": "4.19.2",
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 51200
+  },
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vision_config": {
+    "_name_or_path": "openai/clip-vit-base-patch32",
+    "add_cross_attention": false,
+    "architectures": null,
+    "attention_dropout": 0.0,
+    "bad_words_ids": 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,
+    "dropout": 0.0,
+    "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_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,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "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": "4.19.2",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3fc251be7844996114de04b8a499032bd1f577d82e3380267a19ea85a450fa8
+size 443105628

preprocessor_config.json

@@ -0,0 +1,21 @@
+{
+  "crop_size": 224,
+  "do_center_crop": true,
+  "do_convert_rgb": 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
+  ],
+  "processor_class": "VisionTextDualEncoderProcessor",
+  "resample": 3,
+  "size": 224
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f9fd5f573fa3c1acfa2bcef605f290a2748141dbc7566d6c2943bc87c0e7134
+size 443187803

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "Bingsu/vitB32_bert_ko_small_clip", "processor_class": "VisionTextDualEncoderProcessor", "tokenizer_class": "BertTokenizer"}