upload model

README.md

@@ -1,3 +1,93 @@
----
-license: apache-2.0
----
+---
+language:
+- en
+tags:
+- image-to-text
+- image-captioning
+license: apache-2.0
+base_model: nlpconnect/vit-gpt2-image-captioning
+widget:
+- src: >-
+    https://huggingface.co/datasets/cristianglezm/FlowerEvolver-Dataset/resolve/main/flowers/001.png
+  example_title: Flower 1
+- src: >-
+    https://huggingface.co/datasets/cristianglezm/FlowerEvolver-Dataset/resolve/main/flowers/002.png
+  example_title: Flower 2
+- src: >-
+    https://huggingface.co/datasets/cristianglezm/FlowerEvolver-Dataset/resolve/main/flowers/003.png
+  example_title: Flower 3
+datasets:
+- cristianglezm/FlowerEvolver-Dataset
+metrics:
+- rouge
+pipeline_tag: image-to-text
+library_name: transformers
+---
+
+# ViT-GPT2-FlowerCaptioner
+
+This model is a fine-tuned version of [nlpconnect/vit-gpt2-image-captioning](https://huggingface.co/nlpconnect/vit-gpt2-image-captioning) on the [FlowerEvolver-dataset](https://huggingface.co/datasets/cristianglezm/FlowerEvolver-Dataset) dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3075
+- Rouge1: 66.3702
+- Rouge2: 45.5642
+- Rougel: 61.401
+- Rougelsum: 64.0587
+- Gen Len: 49.97
+
+## sample running code
+
+with python
+
+```python
+from transformers import pipeline
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+FlowerCaptioner = pipeline("image-to-text", model="cristianglezm/ViT-GPT2-FlowerCaptioner", device=device)
+FlowerCaptioner(["flower1.png"])
+# A flower with 12 petals in a smooth gradient of green and blue. 
+# The center is green with black accents. The stem is long and green.
+```
+
+with javascript
+
+```javascript
+import { pipeline } from '@xenova/transformers';
+
+// Allocate a pipeline for image-to-text
+let pipe = await pipeline('image-to-text', 'cristianglezm/ViT-GPT2-FlowerCaptioner-ONNX');
+
+let out = await pipe('flower image url');
+// A flower with 12 petals in a smooth gradient of green and blue. 
+// The center is green with black accents. The stem is long and green.
+```
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| 0.6755        | 1.0   | 100  | 0.5339          | 60.9402 | 39.3331 | 54.6889 | 59.45     | 36.75   |
+| 0.3666        | 2.0   | 200  | 0.3331          | 65.5149 | 43.0245 | 59.3121 | 62.7329   | 52.82   |
+| 0.2983        | 3.0   | 300  | 0.3075          | 66.3702 | 45.5642 | 61.401  | 64.0587   | 49.97   |
+
+
+### Framework versions
+
+- Transformers 4.33.2
+- Pytorch 2.4.1+cu124
+- Datasets 2.20.0
+- Tokenizers 0.13.3

config.json

@@ -0,0 +1,186 @@
+{
+  "_name_or_path": "nlpconnect/vit-gpt2-image-captioning",
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "bos_token_id": 50256,
+  "decoder": {
+    "_name_or_path": "",
+    "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": 50256,
+    "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",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "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": 12,
+    "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": 50256,
+    "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": "",
+    "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.2"
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "decoder_start_token_id": 50256,
+  "eos_token_id": 50256,
+  "max_new_tokens": 128,
+  "pad_token_id": 50256,
+  "transformers_version": "4.33.2"
+}

preprocessor_config.json

@@ -0,0 +1,23 @@
+{
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "feature_extractor_type": "ViTFeatureExtractor",
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_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 sha256:9e93652a34d58078990f9ba2846811b986b9d9e1704f170e4b9df255807b0319
+size 956935738

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 +1,17 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "max_length": 32,
+  "model_max_length": 1024,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|endoftext|>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "stride": 0,
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ff5e250ca1d776218baf4d1a255bdc396495e4c8da8b2c2a5057ab9b2372c48
+size 4600