Add BLIP diagram captioner trained on AI2D part-to-whole data

README.md

@@ -1,3 +1,30 @@
 ---
 license: mit
+library_name: transformers
+pipeline_tag: image-to-text
+base_model: Salesforce/blip-image-captioning-base
+tags:
+- blip
+- accessibility
+- diagram-captioning
 ---
+
+# VisAble diagram captioner
+
+BLIP fine-tuned on AI2D-Caption diagrams to produce part-to-whole descriptions for blind and
+low-vision students. The vision encoder was frozen and only the text decoder was trained, using a
+cross entropy loss that up-weights AI2D entity labels by 5.0x.
+
+Trained for 10 epochs, batch size 8, learning rate 5e-05.
+
+```python
+from transformers import BlipForConditionalGeneration, BlipProcessor
+from PIL import Image
+
+processor = BlipProcessor.from_pretrained("hkondle/CapstoneMainModel-10ep")
+model = BlipForConditionalGeneration.from_pretrained("hkondle/CapstoneMainModel-10ep")
+
+image = Image.open("diagram.png").convert("RGB")
+inputs = processor(images=image, return_tensors="pt")
+print(processor.decode(model.generate(**inputs, max_length=256, num_beams=4)[0], skip_special_tokens=True))
+```

config.json

@@ -0,0 +1,89 @@
+{
+  "architectures": [
+    "BlipForConditionalGeneration"
+  ],
+  "dtype": "float32",
+  "image_text_hidden_size": 256,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "label_smoothing": 0.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "blip",
+  "projection_dim": 512,
+  "text_config": {
+    "add_cross_attention": false,
+    "attention_probs_dropout_prob": 0.0,
+    "bos_token_id": 30522,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "dtype": "float32",
+    "encoder_hidden_size": 768,
+    "eos_token_id": 2,
+    "finetuning_task": null,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.0,
+    "hidden_size": 768,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": true,
+    "label_smoothing": 0.0,
+    "layer_norm_eps": 1e-12,
+    "max_position_embeddings": 512,
+    "model_type": "blip_text_model",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "pad_token_id": 0,
+    "prefix": null,
+    "projection_dim": 768,
+    "pruned_heads": {},
+    "sep_token_id": 102,
+    "task_specific_params": null,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "torchscript": false,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 30524
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.0.0",
+  "vision_config": {
+    "add_cross_attention": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "dropout": 0.0,
+    "dtype": "float32",
+    "eos_token_id": null,
+    "finetuning_task": null,
+    "hidden_act": "gelu",
+    "hidden_size": 768,
+    "image_size": 384,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "layer_norm_eps": 1e-05,
+    "model_type": "blip_vision_model",
+    "num_attention_heads": 12,
+    "num_channels": 3,
+    "num_hidden_layers": 12,
+    "pad_token_id": null,
+    "patch_size": 16,
+    "prefix": null,
+    "projection_dim": 512,
+    "pruned_heads": {},
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "torchscript": false,
+    "use_bfloat16": false
+  }
+}

generation_config.json

@@ -0,0 +1,29 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 30522,
+  "diversity_penalty": 0.0,
+  "do_sample": false,
+  "early_stopping": false,
+  "encoder_no_repeat_ngram_size": 0,
+  "eos_token_id": 2,
+  "length_penalty": 1.0,
+  "max_length": 20,
+  "min_length": 0,
+  "no_repeat_ngram_size": 0,
+  "num_beam_groups": 1,
+  "num_beams": 1,
+  "num_return_sequences": 1,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "output_scores": false,
+  "pad_token_id": 0,
+  "remove_invalid_values": false,
+  "repetition_penalty": 1.0,
+  "return_dict_in_generate": false,
+  "temperature": 1.0,
+  "top_k": 50,
+  "top_p": 1.0,
+  "transformers_version": "5.0.0",
+  "typical_p": 1.0,
+  "use_cache": true
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c079de1c52f8650f54c7b368e66de66bd0d1cf0bab76b0087f6c409d7aea8c0
+size 989839224

processor_config.json

@@ -0,0 +1,27 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_convert_rgb": true,
+    "do_normalize": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "image_mean": [
+      0.48145466,
+      0.4578275,
+      0.40821073
+    ],
+    "image_processor_type": "BlipImageProcessorFast",
+    "image_std": [
+      0.26862954,
+      0.26130258,
+      0.27577711
+    ],
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "size": {
+      "height": 384,
+      "width": 384
+    }
+  },
+  "processor_class": "BlipProcessor"
+}

tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "backend": "tokenizers",
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "is_local": false,
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "processor_class": "BlipProcessor",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}