Upload folder using huggingface_hub

README.md

@@ -0,0 +1,74 @@
+---
+language: en
+tags:
+- token-classification
+- ner
+- named-entity-recognition
+- roberta
+- restaurant
+- mit-restaurant
+datasets:
+- mit_restaurant
+metrics:
+- f1
+- precision
+- recall
+- accuracy
+widget:
+- text: "I want a reservation at an italian restaurant with outdoor seating"
+  example_title: "Restaurant query"
+- text: "Find me a cheap chinese place near downtown"
+  example_title: "Restaurant search"
+---
+
+# RoBERTa Large for MIT Restaurant NER
+
+This model is a fine-tuned version of RoBERTa Large on the MIT Restaurant dataset for Named Entity Recognition (NER).
+
+## Model Description
+
+- **Model type:** Token Classification (NER)
+- **Base model:** roberta-large
+- **Dataset:** MIT Restaurant NER dataset
+- **Languages:** English
+- **Task:** Named Entity Recognition for restaurant domain
+
+## Entity Types
+
+The model can identify the following entity types:
+['O', 'B-Amenity', 'I-Amenity', 'B-Cuisine', 'I-Cuisine', 'B-Dish', 'I-Dish', 'B-Hours', 'I-Hours', 'B-Location', 'I-Location', 'B-Price', 'I-Price', 'B-Rating', 'I-Rating', 'B-Restaurant_Name', 'I-Restaurant_Name']
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline
+
+tokenizer = AutoTokenizer.from_pretrained("niruthiha/roberta-large-mit-restaurant-ner")
+model = AutoModelForTokenClassification.from_pretrained("niruthiha/roberta-large-mit-restaurant-ner")
+
+# Using pipeline
+nlp = pipeline("ner", model=model, tokenizer=tokenizer, aggregation_strategy="simple")
+result = nlp("I want a reservation at an italian restaurant with outdoor seating")
+print(result)
+
+# Manual usage
+inputs = tokenizer("I want a reservation at an italian restaurant", return_tensors="pt")
+outputs = model(**inputs)
+```
+
+## Training Details
+
+- Fine-tuned on MIT Restaurant NER dataset
+- Training epochs: 5
+- Learning rate: 1e-5
+- Batch size: 16
+- Gradient accumulation steps: 2
+
+## Dataset
+
+The MIT Restaurant dataset contains restaurant-related queries with entity annotations.
+Dataset source: https://groups.csail.mit.edu/sls/downloads/restaurant/
+
+## Performance
+
+The model achieves good performance on restaurant domain NER tasks. Specific metrics will be updated after evaluation.

config.json

@@ -0,0 +1,65 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "id2label": {
+    "0": "O",
+    "1": "B-Amenity",
+    "2": "I-Amenity",
+    "3": "B-Cuisine",
+    "4": "I-Cuisine",
+    "5": "B-Dish",
+    "6": "I-Dish",
+    "7": "B-Hours",
+    "8": "I-Hours",
+    "9": "B-Location",
+    "10": "I-Location",
+    "11": "B-Price",
+    "12": "I-Price",
+    "13": "B-Rating",
+    "14": "I-Rating",
+    "15": "B-Restaurant_Name",
+    "16": "I-Restaurant_Name"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "label2id": {
+    "B-Amenity": 1,
+    "B-Cuisine": 3,
+    "B-Dish": 5,
+    "B-Hours": 7,
+    "B-Location": 9,
+    "B-Price": 11,
+    "B-Rating": 13,
+    "B-Restaurant_Name": 15,
+    "I-Amenity": 2,
+    "I-Cuisine": 4,
+    "I-Dish": 6,
+    "I-Hours": 8,
+    "I-Location": 10,
+    "I-Price": 12,
+    "I-Rating": 14,
+    "I-Restaurant_Name": 16,
+    "O": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8afce2aa862f4a6433e13eb6420eadc5d48f59af7de3354df4d52fb42befb0a6
+size 1417358292

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "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": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ee8c05659a087fc0e79e4c341c4131415f6cdc72aeb6945a3ec9f0d7cd99bc
+size 5304