Upload ONNX optimized RoBERTa model with quantization

README.md

@@ -0,0 +1,23 @@
+---
+license: mit
+tags:
+- text-classification
+- onnx
+- quantized
+- roberta
+- tweet-topic
+base_model: cardiffnlp/tweet-topic-21-multi
+---
+This is an ONNX-optimized version of [`cardiffnlp/tweet-topic-21-multi`](https://huggingface.co/cardiffnlp/tweet-topic-21-multi) for efficient inference.
+
+## Model Description
+
+This repository contains:
+- **model.onnx**: Regular ONNX exported model
+- **model_quantized.onnx**: INT8 dynamically quantized model for faster inference with minimal accuracy loss
+
+The model is optimized for zero-shot classification tasks across multiple languages.
+
+## Acknowledgments
+
+This ONNX optimization was created for efficient deployment in production environments. Special thanks to the original model authors and the Hugging Face Optimum team.

config.json

@@ -0,0 +1,70 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "arts_&_culture",
+    "1": "business_&_entrepreneurs",
+    "2": "celebrity_&_pop_culture",
+    "3": "diaries_&_daily_life",
+    "4": "family",
+    "5": "fashion_&_style",
+    "6": "film_tv_&_video",
+    "7": "fitness_&_health",
+    "8": "food_&_dining",
+    "9": "gaming",
+    "10": "learning_&_educational",
+    "11": "music",
+    "12": "news_&_social_concern",
+    "13": "other_hobbies",
+    "14": "relationships",
+    "15": "science_&_technology",
+    "16": "sports",
+    "17": "travel_&_adventure",
+    "18": "youth_&_student_life"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "arts_&_culture": 0,
+    "business_&_entrepreneurs": 1,
+    "celebrity_&_pop_culture": 2,
+    "diaries_&_daily_life": 3,
+    "family": 4,
+    "fashion_&_style": 5,
+    "film_tv_&_video": 6,
+    "fitness_&_health": 7,
+    "food_&_dining": 8,
+    "gaming": 9,
+    "learning_&_educational": 10,
+    "music": 11,
+    "news_&_social_concern": 12,
+    "other_hobbies": 13,
+    "relationships": 14,
+    "science_&_technology": 15,
+    "sports": 16,
+    "travel_&_adventure": 17,
+    "youth_&_student_life": 18
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "multi_label_classification",
+  "transformers_version": "4.57.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e0262356d967bb0462fe0abb7d1fb1547210c6fcb810992f45a6fbc48e4a141
+size 498913534

model_quantized.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ec0f338c168218c766bf0c40bf79693131a27818a9a04090a315a36f0c431c7
+size 125507841

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}