ViT-GPT2-FlowerCaptioner-ONNX

ViT-GPT2-FlowerCaptioner-ONNX/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

ViT-GPT2-FlowerCaptioner-ONNX/README.md

@@ -0,0 +1,115 @@
+---
+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.js
+---
+
+# 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: 0.4930
+- Rouge1: 68.3498
+- Rouge2: 46.7534
+- Rougel: 62.3763
+- Rougelsum: 65.9575
+- Gen Len: 49.82
+
+## 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: 25
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| 0.6986        | 1.0   | 100  | 0.5339          | 64.9813 | 42.4686 | 58.2586 | 63.3933   | 47.25   |
+| 0.3408        | 2.0   | 200  | 0.3263          | 67.5461 | 46.5219 | 62.7962 | 65.6509   | 47.39   |
+| 0.2797        | 3.0   | 300  | 0.2829          | 65.0704 | 42.0682 | 58.4268 | 63.2368   | 56.8    |
+| 0.2584        | 4.0   | 400  | 0.2588          | 65.5074 | 45.227  | 60.2469 | 63.4253   | 52.25   |
+| 0.2589        | 5.0   | 500  | 0.2607          | 66.7346 | 45.8264 | 61.7373 | 64.8857   | 50.64   |
+| 0.2179        | 6.0   | 600  | 0.2697          | 63.8334 | 42.997  | 58.1585 | 61.7704   | 52.43   |
+| 0.1662        | 7.0   | 700  | 0.2631          | 68.6188 | 48.3329 | 63.9474 | 66.6006   | 46.94   |
+| 0.161         | 8.0   | 800  | 0.2749          | 69.0046 | 48.1421 | 63.7844 | 66.8317   | 49.74   |
+| 0.1207        | 9.0   | 900  | 0.3117          | 70.0357 | 48.9002 | 64.416  | 67.7582   | 48.66   |
+| 0.0909        | 10.0  | 1000 | 0.3408          | 65.9578 | 45.2324 | 60.2838 | 63.7493   | 46.92   |
+| 0.0749        | 11.0  | 1100 | 0.3516          | 67.4244 | 46.1985 | 61.6408 | 65.5371   | 46.61   |
+| 0.0665        | 12.0  | 1200 | 0.3730          | 68.6911 | 47.7089 | 63.0381 | 66.6956   | 47.89   |
+| 0.0522        | 13.0  | 1300 | 0.3891          | 67.2365 | 45.4165 | 61.4063 | 64.857    | 48.91   |
+| 0.0355        | 14.0  | 1400 | 0.4128          | 69.1494 | 47.9278 | 63.3334 | 66.5969   | 50.55   |
+| 0.0309        | 15.0  | 1500 | 0.4221          | 66.2447 | 44.937  | 60.1403 | 63.8541   | 50.71   |
+| 0.0265        | 16.0  | 1600 | 0.4343          | 67.8178 | 46.7084 | 61.8173 | 65.4375   | 50.85   |
+| 0.0158        | 17.0  | 1700 | 0.4577          | 67.9846 | 45.9562 | 61.6353 | 65.7207   | 50.81   |
+| 0.0166        | 18.0  | 1800 | 0.4731          | 69.0971 | 47.7001 | 62.856  | 66.7796   | 50.01   |
+| 0.0121        | 19.0  | 1900 | 0.4657          | 68.1397 | 46.4258 | 62.2696 | 65.9332   | 49.15   |
+| 0.0095        | 20.0  | 2000 | 0.4793          | 68.6497 | 47.9446 | 63.0466 | 66.5409   | 50.96   |
+| 0.0086        | 21.0  | 2100 | 0.4780          | 68.4363 | 46.7296 | 62.359  | 66.2626   | 50.02   |
+| 0.0068        | 22.0  | 2200 | 0.4863          | 67.5415 | 46.0821 | 61.57   | 65.4613   | 49.5    |
+| 0.0061        | 23.0  | 2300 | 0.4892          | 68.1283 | 46.5802 | 62.0832 | 66.0203   | 50.21   |
+| 0.006         | 24.0  | 2400 | 0.4912          | 68.1723 | 46.3239 | 62.2007 | 65.6725   | 49.89   |
+| 0.0057        | 25.0  | 2500 | 0.4930          | 68.3498 | 46.7534 | 62.3763 | 65.9575   | 49.82   |
+
+
+### Framework versions
+
+- Transformers 4.43.4
+- Pytorch 2.4.1+cu124
+- Datasets 2.20.0
+- Tokenizers 0.19.1

ViT-GPT2-FlowerCaptioner-ONNX/config.json

@@ -0,0 +1,185 @@
+{
+  "_name_or_path": "./models/FlowerCaptioner",
+  "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,
+  "transformers_version": "4.33.2"
+}

ViT-GPT2-FlowerCaptioner-ONNX/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"
+}

ViT-GPT2-FlowerCaptioner-ONNX/onnx/decoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f51820bb5c0f5a4ed7a56f8cebc0941ea4e76cbcd8b92029e6a692fb01e5a078
+size 613153019

ViT-GPT2-FlowerCaptioner-ONNX/onnx/decoder_model_merged.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc7e62770352f6844e064cdf22cabb6b00c8f7d166c0839e07156f7d2bae73c5
+size 615070521

ViT-GPT2-FlowerCaptioner-ONNX/onnx/decoder_model_merged_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b482ca61962a11ddd30d2a279a5680feedb4cc19e207fee8c2d29860e548deda
+size 158063351

ViT-GPT2-FlowerCaptioner-ONNX/onnx/decoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81802b5229986a911d3ad6e9007fb540702b3ee6b42cbb8e687b816dfd948712
+size 155710792

ViT-GPT2-FlowerCaptioner-ONNX/onnx/decoder_with_past_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8e6cb92689b1b31c3a6f9e4f04e8cf052e6f00e1b433553dc399f4df833ea01
+size 613149344

ViT-GPT2-FlowerCaptioner-ONNX/onnx/decoder_with_past_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcac5392f1f43d1fb64a0c4c4a9d8e32cc87d88213905997f43e72e73e660750
+size 155701341

ViT-GPT2-FlowerCaptioner-ONNX/onnx/encoder_model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d18e307852a5dca94a0e2d2457e4eb3d397820ca509caa7d80aac41fba4b9aa
+size 343410667

ViT-GPT2-FlowerCaptioner-ONNX/onnx/encoder_model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7f417ac897abb1ab3f6df34df104737f9da1beb7ecafab5798bbb128fd9f90e
+size 87000254

ViT-GPT2-FlowerCaptioner-ONNX/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": "ViTFeatureExtractor",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "resample": 2,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "height": 224,
+    "width": 224
+  }
+}

ViT-GPT2-FlowerCaptioner-ONNX/quantize_config.json

@@ -0,0 +1,119 @@
+{
+    "per_channel": false,
+    "reduce_range": false,
+    "per_model_config": {
+        "decoder_model": {
+            "op_types": [
+                "Pow",
+                "Split",
+                "Softmax",
+                "Reshape",
+                "Range",
+                "Slice",
+                "Mul",
+                "Constant",
+                "Gemm",
+                "Shape",
+                "Sub",
+                "Concat",
+                "Tanh",
+                "ConstantOfShape",
+                "LayerNormalization",
+                "Cast",
+                "Squeeze",
+                "Where",
+                "Div",
+                "Gather",
+                "Transpose",
+                "MatMul",
+                "Unsqueeze",
+                "Add"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_model_merged": {
+            "op_types": [
+                "Pow",
+                "If",
+                "Split",
+                "Softmax",
+                "Reshape",
+                "Range",
+                "Slice",
+                "Mul",
+                "Constant",
+                "Gemm",
+                "Shape",
+                "Sub",
+                "Concat",
+                "Tanh",
+                "ConstantOfShape",
+                "LayerNormalization",
+                "Cast",
+                "Squeeze",
+                "Where",
+                "Div",
+                "Gather",
+                "Transpose",
+                "MatMul",
+                "Unsqueeze",
+                "Add"
+            ],
+            "weight_type": "QInt8"
+        },
+        "decoder_with_past_model": {
+            "op_types": [
+                "Pow",
+                "Split",
+                "Softmax",
+                "Reshape",
+                "Range",
+                "Slice",
+                "Mul",
+                "Constant",
+                "Gemm",
+                "Shape",
+                "Sub",
+                "Concat",
+                "Tanh",
+                "ConstantOfShape",
+                "LayerNormalization",
+                "Cast",
+                "Squeeze",
+                "Where",
+                "Div",
+                "Gather",
+                "Transpose",
+                "MatMul",
+                "Unsqueeze",
+                "Add"
+            ],
+            "weight_type": "QInt8"
+        },
+        "encoder_model": {
+            "op_types": [
+                "Softmax",
+                "Reshape",
+                "Conv",
+                "Expand",
+                "Slice",
+                "MatMul",
+                "Mul",
+                "Constant",
+                "Erf",
+                "Shape",
+                "Concat",
+                "ConstantOfShape",
+                "LayerNormalization",
+                "Equal",
+                "Where",
+                "Gather",
+                "Transpose",
+                "Div",
+                "Unsqueeze",
+                "Add"
+            ],
+            "weight_type": "QUInt8"
+        }
+    }
+}

ViT-GPT2-FlowerCaptioner-ONNX/source.txt

@@ -0,0 +1 @@
+https://huggingface.co/cristianglezm/ViT-GPT2-FlowerCaptioner-ONNX

ViT-GPT2-FlowerCaptioner-ONNX/special_tokens_map.json

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

ViT-GPT2-FlowerCaptioner-ONNX/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|>"
+}