Upload 20 files

README.md

@@ -1,3 +1,78 @@
 ---
+tags:
+  - image-to-text
+  - image-captioning
 license: apache-2.0
+metrics:
+  - rouge
+datasets:
+  - Mozilla/flickr30k-transformed-captions
+widget:
+  - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/savanna.jpg
+    example_title: Savanna
+  - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/football-match.jpg
+    example_title: Football Match
+  - src: https://huggingface.co/datasets/mishig/sample_images/resolve/main/airport.jpg
+    example_title: Airport
+base_model:
+  - google/vit-base-patch16-224-in21k
+
+model-index:
+  - name: mozilla/distilvit
+    results:
+      - task:
+          type: image-to-text
+          name: Image To Text
+        dataset:
+          name: Mozilla/flickr30k-transformed-captions
+          type: Mozilla/flickr30k-transformed-captions
+        metrics:
+          - name: ROUGE-1
+            type: rouge
+            value: 43.006
+            verified: true
+          - name: ROUGE-2
+            type: rouge
+            value: 16.9939
+            verified: true
+          - name: ROUGE-L
+            type: rouge
+            value: 38.8923
+            verified: true
+          - name: ROUGE-LSUM
+            type: rouge
+            value: 38.8877
+            verified: true
+          - name: loss
+            type: loss
+            value: 0.19939416646957397
+          - name: gen_len
+            type: gen_len
+            value: 11.327256736227712
+            verified: true
 ---
+
+# distilvit
+
+This model is a work in progress. Fine-tuned version of those base models:
+
+- a VIT model for the image encoder: https://huggingface.co/google/vit-base-patch16-224-in21k
+- a Distilled GPT-2 model for the text decoder: https://huggingface.co/distilbert/distilgpt2
+
+This model was trained on:
+
+- Flickr30k : https://huggingface.co/datasets/nlphuji/flickr30k
+- COCO 2017: https://cocodataset.org
+
+You can get that checkpoint using the 3083a3cef6e3c8dd90df3f088074bbe836b0f403 commit.
+
+It was then further fine-tuned on :
+
+- [Flickr30k debiased](https://huggingface.co/datasets/Mozilla/flickr30k-transformed-captions)
+- [DocOrNot](https://huggingface.co/datasets/Mozilla/docornot)
+- [Alt Text Validation](https://huggingface.co/datasets/Mozilla/alt-text-validation)
+
+For the latter, the dataset was annotated by our team to correct the alt text generated by the model,
+using the [checkvite tool](https://github.com/mozila/checkvite).
+
+You can find the code used to create the model here: https://github.com/mozilla/distilvit

config.json

@@ -0,0 +1,183 @@
+{
+  "_name_or_path": "C:\\Users\\tarek\\Dev\\distilvit\\distilvit\\..\\mozilla/distilvit+fine-tuned",
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "distilbert/distilgpt2",
+    "_num_labels": 1,
+    "activation_function": "gelu_new",
+    "add_cross_attention": true,
+    "architectures": [
+      "GPT2LMHeadModel"
+    ],
+    "attn_pdrop": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 50256,
+    "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,
+    "embd_pdrop": 0.1,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 50256,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0"
+    },
+    "initializer_range": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0
+    },
+    "layer_norm_epsilon": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "gpt2",
+    "n_ctx": 1024,
+    "n_embd": 768,
+    "n_head": 12,
+    "n_inner": null,
+    "n_layer": 6,
+    "n_positions": 1024,
+    "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": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "reorder_and_upcast_attn": false,
+    "repetition_penalty": 1.0,
+    "resid_pdrop": 0.1,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_attn_by_inverse_layer_idx": false,
+    "scale_attn_weights": true,
+    "sep_token_id": null,
+    "summary_activation": null,
+    "summary_first_dropout": 0.1,
+    "summary_proj_to_labels": true,
+    "summary_type": "cls_index",
+    "summary_use_proj": true,
+    "suppress_tokens": null,
+    "task_specific_params": {
+      "text-generation": {
+        "do_sample": true,
+        "max_length": 50
+      }
+    },
+    "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,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50257
+  },
+  "decoder_start_token_id": 50256,
+  "encoder": {
+    "_name_or_path": "google/vit-base-patch16-224-in21k",
+    "add_cross_attention": false,
+    "architectures": [
+      "ViTModel"
+    ],
+    "attention_probs_dropout_prob": 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,
+    "encoder_stride": 16,
+    "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": 0.0,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "image_size": 224,
+    "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-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "vit",
+    "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": 16,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "qkv_bias": true,
+    "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,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "eos_token_id": 50256,
+  "is_encoder_decoder": true,
+  "model_type": "vision-encoder-decoder",
+  "pad_token_id": 50256,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.33.2"
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bos_token_id": 50256,
+  "do_sample": true,
+  "early_stopping": true,
+  "eos_token_id": 50256,
+  "max_length": 50,
+  "max_time": 5,
+  "no_repeat_ngram_size": 2,
+  "num_beams": 2,
+  "pad_token_id": 50256,
+  "repetition_penalty": 1.4,
+  "seed": 12,
+  "temperature": 0.8,
+  "top_p": 0.9,
+  "transformers_version": "4.33.2"
+}

onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b562d5631d23b71d9417071e8041f3eb80e84122a9bbb66dfdec8d46d91594d4
+size 385864797

onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:129100f907e7295525d4529083bfb5bdcc206eedce9f9d4a6223131ea8cb8e87
+size 387342586

onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d636dce4f19d08059cf075c25b75f94f71e5b28081d3be8c3823c07f40c59604
+size 99759579

onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87de04f08ef3a7cec2f3cd71d4de440864ab0a7f4f32ad0764fdb8d26387fe94
+size 98065763

onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3e69a840d8b693b738d31f9bab09434311b1eb022f4c6a89f7c31ae4ac76428
+size 385864377

onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5da506c3668083b54468a4be3d0581c2749abc28c68d4f6f816d7f03548ea977
+size 98063170

onnx/encoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e06aee9b192045a32c40f0bac2e1304e153f7b7521286a65a478893a582b4087
+size 343440632

onnx/encoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90563de4250ab0e12730242476b884529a1a825059c36212bd4ae1dac2e87c56
+size 87038173

preprocessor_config.json

@@ -0,0 +1,22 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "feature_extractor_type": "ViTImageProcessor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c82a8f09d299196b2a3237374d874d008567e0d9d9044c48b24965138d8394e
+size 730052378

quantize_config.json

@@ -0,0 +1,125 @@
+{
+    "per_channel": false,
+    "reduce_range": false,
+    "per_model_config": {
+        "decoder_model": {
+            "op_types": [
+                "Add",
+                "Transpose",
+                "Squeeze",
+                "Range",
+                "Slice",
+                "ConstantOfShape",
+                "MatMul",
+                "Where",
+                "ReduceMean",
+                "Div",
+                "Unsqueeze",
+                "Split",
+                "Cast",
+                "Gemm",
+                "Tanh",
+                "Pow",
+                "Mul",
+                "Gather",
+                "Reshape",
+                "Softmax",
+                "Sqrt",
+                "Shape",
+                "Constant",
+                "Sub",
+                "Concat"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_model_merged": {
+            "op_types": [
+                "Add",
+                "Transpose",
+                "Squeeze",
+                "Range",
+                "Slice",
+                "ConstantOfShape",
+                "MatMul",
+                "Where",
+                "ReduceMean",
+                "Div",
+                "Unsqueeze",
+                "Split",
+                "Cast",
+                "Gemm",
+                "Tanh",
+                "Pow",
+                "Mul",
+                "Gather",
+                "Reshape",
+                "Softmax",
+                "Sqrt",
+                "Shape",
+                "Constant",
+                "Sub",
+                "If",
+                "Concat"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_with_past_model": {
+            "op_types": [
+                "Add",
+                "Transpose",
+                "Squeeze",
+                "Range",
+                "Slice",
+                "ConstantOfShape",
+                "MatMul",
+                "Where",
+                "ReduceMean",
+                "Div",
+                "Unsqueeze",
+                "Split",
+                "Cast",
+                "Gemm",
+                "Tanh",
+                "Pow",
+                "Mul",
+                "Gather",
+                "Reshape",
+                "Softmax",
+                "Sqrt",
+                "Shape",
+                "Constant",
+                "Sub",
+                "Concat"
+            ],
+            "weight_type": "QInt8"
+        },
+        "encoder_model": {
+            "op_types": [
+                "Add",
+                "Transpose",
+                "Equal",
+                "Slice",
+                "Expand",
+                "ConstantOfShape",
+                "MatMul",
+                "Where",
+                "ReduceMean",
+                "Div",
+                "Unsqueeze",
+                "Conv",
+                "Pow",
+                "Mul",
+                "Gather",
+                "Reshape",
+                "Softmax",
+                "Sqrt",
+                "Shape",
+                "Constant",
+                "Sub",
+                "Erf",
+                "Concat"
+            ],
+            "weight_type": "QUInt8"
+        }
+    }
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6124d14554c856f07f64ebbca472baff63ce12555bd850dbac15bdf294e64c5
+size 4728