Updated model

README.md

@@ -1,7 +1,6 @@
 ---
 language:
 - en
-license: mit
 tags:
 - psychology
 - emotion-recognition
@@ -10,7 +9,6 @@ tags:
 - trigger-extraction
 datasets:
 - daily_dialog
-inference: false
 ---
 
 # RECCON: Emotional Trigger Extraction Model
@@ -22,7 +20,7 @@ This repository contains the weights and custom inference handler to deploy RECC
 ## 🧠 Model Details
 
 - **Task**: Extractive Question Answering (Span Extraction)
-- **Base Model**: `roberta-base`
+- **Base Model**: `SpanBERT` (without context)
 - **Training Dataset**: [RECCON Dataset](https://github.com/declare-lab/RECCON) (derived from DailyDialog)
 - **Paper**: [Recognizing Emotion Cause in Conversations (Poria et al., 2021)](https://arxiv.org/abs/2012.11820)
 
@@ -35,7 +33,7 @@ Ensure the following files are present in the root of this repository:
 1.  `handler.py`: The custom inference logic (included).
 2.  `requirements.txt`: Dependencies (included).
 3.  `model.safetensors` (or `pytorch_model.bin`): The model weights.
-4.  `config.json`: The RoBERTa model configuration.
+4.  `config.json`: The BERT model configuration.
 5.  `tokenizer.json` / `vocab.json`: Tokenizer files.
 
 ### Configuration

config.json

@@ -1,26 +1,26 @@
 {
   "architectures": [
-    "RobertaForQuestionAnswering"
+    "BertForQuestionAnswering"
   ],
   "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
   "classifier_dropout": null,
+  "directionality": "bidi",
   "dtype": "float32",
-  "eos_token_id": 2,
   "hidden_act": "gelu",
   "hidden_dropout_prob": 0.1,
   "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
   "num_attention_heads": 12,
   "num_hidden_layers": 12,
-  "pad_token_id": 1,
+  "output_past": true,
+  "pad_token_id": 0,
   "position_embedding_type": "absolute",
-  "transformers_version": "4.57.1",
-  "type_vocab_size": 1,
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 50265
+  "vocab_size": 28996
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e82e93aaf74df78452904601c8ba6502a1e4b90bd9b26ed55ddfe0a279e8fc18
-size 496250232
+oid sha256:a6672b27522322c199b40ef0d8d8ea2300a745a02942b74e0f48f14a5fa61cbc
+size 430908208

special_tokens_map.json

@@ -1,51 +1,7 @@
 {
-  "bos_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "cls_token": {
-    "content": "<s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "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": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "sep_token": {
-    "content": "</s>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<unk>",
-    "lstrip": false,
-    "normalized": true,
-    "rstrip": false,
-    "single_word": false
-  }
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
 }

tokenizer_config.json

@@ -1,58 +1,58 @@
 {
-  "add_prefix_space": false,
   "added_tokens_decoder": {
     "0": {
-      "content": "<s>",
+      "content": "[PAD]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "1": {
-      "content": "<pad>",
+    "100": {
+      "content": "[UNK]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "2": {
-      "content": "</s>",
+    "101": {
+      "content": "[CLS]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "3": {
-      "content": "<unk>",
+    "102": {
+      "content": "[SEP]",
       "lstrip": false,
-      "normalized": true,
+      "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "50264": {
-      "content": "<mask>",
-      "lstrip": true,
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     }
   },
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
-  "cls_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
   "do_lower_case": false,
-  "eos_token": "</s>",
-  "errors": "replace",
   "extra_special_tokens": {},
-  "mask_token": "<mask>",
-  "model_max_length": 512,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "tokenizer_class": "RobertaTokenizer",
-  "unk_token": "<unk>"
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
 }