Upload model

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,228 @@
+{
+  "architectures": [
+    "VisionEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "google-bert/bert-base-multilingual-cased",
+    "add_cross_attention": true,
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "directionality": "bidi",
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "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": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "pooler_fc_size": 768,
+    "pooler_num_attention_heads": 12,
+    "pooler_num_fc_layers": 3,
+    "pooler_size_per_head": 128,
+    "pooler_type": "first_token_transform",
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "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,
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 119547
+  },
+  "decoder_start_token_id": 0,
+  "early_stopping": null,
+  "encoder": {
+    "_name_or_path": "Zannatul/google-vit-base-patch16-384-in21k-batch_16_epoch_4_classes_24_final_withAug_12th_May",
+    "add_cross_attention": false,
+    "architectures": [
+      "ViTForImageClassification"
+    ],
+    "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": "Bhapa Pitha(\u09ad\u09be\u09aa\u09be \u09aa\u09bf\u09a0\u09be)",
+      "1": "Biriyani(\u09ac\u09bf\u09b0\u09bf\u09df\u09be\u09a8\u09bf)",
+      "2": "Chicken Pulao(\u09ae\u09cb\u09b0\u0997 \u09aa\u09cb\u09b2\u09be\u0993)",
+      "3": "Chickpease Bhuna(\u099b\u09cb\u09b2\u09be\u09ad\u09c1\u09a8\u09be)",
+      "4": "Egg Curry(\u09a1\u09bf\u09ae\u09ad\u09c1\u09a8\u09be)",
+      "5": "Falooda(\u09ab\u09be\u09b2\u09c1\u09a6\u09be)",
+      "6": "Fuchka(\u09ab\u09c1\u099a\u0995\u09be)",
+      "7": "Haleem(\u09b9\u09be\u09b2\u09bf\u09ae)",
+      "8": "Jalebi(\u099c\u09bf\u09b2\u09be\u09aa\u09c0)",
+      "9": "Kala Bhuna(\u0995\u09be\u09b2\u09be \u09ad\u09c1\u09a8\u09be)",
+      "10": "Khichuri(\u0996\u09bf\u099a\u09c1\u09a1\u09bc\u09bf)",
+      "11": "Malpua Pitha(\u09ae\u09be\u09b2\u09aa\u09c1\u09df\u09be \u09aa\u09bf\u09a0\u09be)",
+      "12": "Mustard Hilsa(\u09b8\u09b0\u09b7\u09c7 \u0987\u09b2\u09bf\u09b6)",
+      "13": "Nakshi Pitha(\u09a8\u0995\u09b6\u09bf \u09aa\u09bf\u09a0\u09be)",
+      "14": "Panta Ilish(\u09aa\u09be\u09a8\u09cd\u09a4\u09be \u0987\u09b2\u09bf\u09b6)",
+      "15": "Patishapta Pitha(\u09aa\u09be\u099f\u09bf\u09b8\u09be\u09aa\u099f\u09be)",
+      "16": "Prawn Malai Curry(\u099a\u09bf\u0982\u09dc\u09bf \u09ae\u09be\u09b2\u09be\u0987\u0995\u09be\u09b0\u09c0)",
+      "17": "Rasgulla(\u09b0\u09b8\u0997\u09cb\u09b2\u09cd\u09b2\u09be)",
+      "18": "Rose Cookies(\u09ab\u09c1\u09b2\u099d\u09c1\u09b0\u09bf \u09aa\u09bf\u09a0\u09be)",
+      "19": "Roshmalai(\u09b0\u09b8\u09ae\u09be\u09b2\u09be\u0987)",
+      "20": "Shahi Tukra(\u09b6\u09be\u09b9\u09bf \u099f\u09c1\u0995\u09b0\u09be)",
+      "21": "Shingara(\u09b8\u09bf\u0999\u09cd\u0997\u09be\u09b0\u09be)",
+      "22": "Sweet Yogurt(\u09ae\u09bf\u09b7\u09cd\u099f\u09bf \u09a6\u0987)",
+      "23": "Tehari(\u09a4\u09c7\u09b9\u09be\u09b0\u09bf)"
+    },
+    "image_size": 384,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "Bhapa Pitha(\u09ad\u09be\u09aa\u09be \u09aa\u09bf\u09a0\u09be)": "0",
+      "Biriyani(\u09ac\u09bf\u09b0\u09bf\u09df\u09be\u09a8\u09bf)": "1",
+      "Chicken Pulao(\u09ae\u09cb\u09b0\u0997 \u09aa\u09cb\u09b2\u09be\u0993)": "2",
+      "Chickpease Bhuna(\u099b\u09cb\u09b2\u09be\u09ad\u09c1\u09a8\u09be)": "3",
+      "Egg Curry(\u09a1\u09bf\u09ae\u09ad\u09c1\u09a8\u09be)": "4",
+      "Falooda(\u09ab\u09be\u09b2\u09c1\u09a6\u09be)": "5",
+      "Fuchka(\u09ab\u09c1\u099a\u0995\u09be)": "6",
+      "Haleem(\u09b9\u09be\u09b2\u09bf\u09ae)": "7",
+      "Jalebi(\u099c\u09bf\u09b2\u09be\u09aa\u09c0)": "8",
+      "Kala Bhuna(\u0995\u09be\u09b2\u09be \u09ad\u09c1\u09a8\u09be)": "9",
+      "Khichuri(\u0996\u09bf\u099a\u09c1\u09a1\u09bc\u09bf)": "10",
+      "Malpua Pitha(\u09ae\u09be\u09b2\u09aa\u09c1\u09df\u09be \u09aa\u09bf\u09a0\u09be)": "11",
+      "Mustard Hilsa(\u09b8\u09b0\u09b7\u09c7 \u0987\u09b2\u09bf\u09b6)": "12",
+      "Nakshi Pitha(\u09a8\u0995\u09b6\u09bf \u09aa\u09bf\u09a0\u09be)": "13",
+      "Panta Ilish(\u09aa\u09be\u09a8\u09cd\u09a4\u09be \u0987\u09b2\u09bf\u09b6)": "14",
+      "Patishapta Pitha(\u09aa\u09be\u099f\u09bf\u09b8\u09be\u09aa\u099f\u09be)": "15",
+      "Prawn Malai Curry(\u099a\u09bf\u0982\u09dc\u09bf \u09ae\u09be\u09b2\u09be\u0987\u0995\u09be\u09b0\u09c0)": "16",
+      "Rasgulla(\u09b0\u09b8\u0997\u09cb\u09b2\u09cd\u09b2\u09be)": "17",
+      "Rose Cookies(\u09ab\u09c1\u09b2\u099d\u09c1\u09b0\u09bf \u09aa\u09bf\u09a0\u09be)": "18",
+      "Roshmalai(\u09b0\u09b8\u09ae\u09be\u09b2\u09be\u0987)": "19",
+      "Shahi Tukra(\u09b6\u09be\u09b9\u09bf \u099f\u09c1\u0995\u09b0\u09be)": "20",
+      "Shingara(\u09b8\u09bf\u0999\u09cd\u0997\u09be\u09b0\u09be)": "21",
+      "Sweet Yogurt(\u09ae\u09bf\u09b7\u09cd\u099f\u09bf \u09a6\u0987)": "22",
+      "Tehari(\u09a4\u09c7\u09b9\u09be\u09b0\u09bf)": "23"
+    },
+    "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": "single_label_classification",
+    "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": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "eos_token_id": 2,
+  "is_encoder_decoder": true,
+  "length_penalty": null,
+  "max_length": null,
+  "model_type": "vision-encoder-decoder",
+  "no_repeat_ngram_size": null,
+  "num_beams": null,
+  "pad_token_id": 1,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,11 @@
+{
+  "decoder_start_token_id": 0,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "length_penalty": 2.0,
+  "max_length": 64,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.45.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1798894c6c6cfa17ff5035dec5131e72da36515fd04db8b2cccfade1511aea15
+size 1172155476