Upload 8 files

README.md

@@ -0,0 +1,68 @@
+---
+language: en
+license: mit
+tags:
+- vision
+model_name: microsoft/git-large-textcaps
+pipeline_tag: image-to-text
+---
+
+# GIT (GenerativeImage2Text), large-sized, fine-tuned on TextCaps, R*
+
+R = re-trained by removing some offensive captions in cc12m dataset
+
+GIT (short for GenerativeImage2Text) model, large-sized version, fine-tuned on TextCaps. It was introduced in the paper [GIT: A Generative Image-to-text Transformer for Vision and Language](https://arxiv.org/abs/2205.14100) by Wang et al. and first released in [this repository](https://github.com/microsoft/GenerativeImage2Text).
+
+Disclaimer: The team releasing GIT did not write a model card for this model so this model card has been written by the Hugging Face team.
+
+## Model description
+
+GIT is a Transformer decoder conditioned on both CLIP image tokens and text tokens. The model is trained using "teacher forcing" on a lot of (image, text) pairs.
+
+The goal for the model is simply to predict the next text token, giving the image tokens and previous text tokens.
+
+The model has full access to (i.e. a bidirectional attention mask is used for) the image patch tokens, but only has access to the previous text tokens (i.e. a causal attention mask is used for the text tokens) when predicting the next text token.
+
+![GIT architecture](https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/transformers/model_doc/git_architecture.jpg)
+
+This allows the model to be used for tasks like:
+
+- image and video captioning
+- visual question answering (VQA) on images and videos
+- even image classification (by simply conditioning the model on the image and asking it to generate a class for it in text).
+
+## Intended uses & limitations
+
+You can use the raw model for image captioning. See the [model hub](https://huggingface.co/models?search=microsoft/git) to look for
+fine-tuned versions on a task that interests you.
+
+### How to use
+
+For code examples, we refer to the [documentation](https://huggingface.co/transformers/main/model_doc/git.html).
+
+## Training data
+
+From the paper:
+
+> We collect 0.8B image-text pairs for pre-training, which include COCO (Lin et al., 2014), Conceptual Captions
+(CC3M) (Sharma et al., 2018), SBU (Ordonez et al., 2011), Visual Genome (VG) (Krishna et al., 2016),
+Conceptual Captions (CC12M) (Changpinyo et al., 2021), ALT200M (Hu et al., 2021a), and an extra 0.6B
+data following a similar collection procedure in Hu et al. (2021a).
+
+=> however this is for the model referred to as "GIT" in the paper, which is not open-sourced.
+
+This checkpoint is "GIT-large", which is a smaller variant of GIT trained on 20 million image-text pairs.
+
+Next, the model was fine-tuned on TextCaps.
+
+See table 11 in the [paper](https://arxiv.org/abs/2205.14100) for more details.
+
+### Preprocessing
+
+We refer to the original repo regarding details for preprocessing during training.
+
+During validation, one resizes the shorter edge of each image, after which center cropping is performed to a fixed-size resolution. Next, frames are normalized across the RGB channels with the ImageNet mean and standard deviation.
+
+## Evaluation results
+
+For evaluation results, we refer readers to the [paper](https://arxiv.org/abs/2205.14100).

config.json

@@ -0,0 +1,106 @@
+{
+  "_commit_hash": null,
+  "architectures": [
+    "GitForCausalLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 101,
+  "classifier_dropout": null,
+  "eos_token_id": 102,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 1024,
+  "model_type": "git",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "num_image_with_embedding": null,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "use_cache": true,
+  "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,
+    "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": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "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": "git_vision_model",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_channels": 3,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "patch_size": 14,
+    "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": "4.26.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "vocab_size": 30522
+}

preprocessor_config.json

@@ -0,0 +1,28 @@
+{
+  "crop_size": {
+    "height": 224,
+    "width": 224
+  },
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "CLIPImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "processor_class": "GitProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "shortest_edge": 224
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb3f55213b6a6e8d1e451705c911c6c2e8c2dcaa46027176dd20b57438eb8a2a
+size 1576966105

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 512,
+  "name_or_path": "bert-base-uncased",
+  "pad_token": "[PAD]",
+  "processor_class": "GitProcessor",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}