Initial commit

.gitattributes

@@ -0,0 +1,42 @@
+*.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
+qwen3.5-0.8b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen3.5-0.8b-chinese-ft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen3.5-2b-chinese-ft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen3.5-4b-chinese-ft/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen3.5-2b-chinese-ft-orig/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen3.5-4b-chinese-ft-orig/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen3.5-2b/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,39 @@
+---
+license: apache-2.0
+language:
+- en
+- sw
+- uk
+- zh
+tags:
+- text-classification
+- multilingual
+- emotion-recognition
+---
+
+# MMD2 — BRIGHTER Multilingual Emotion Classifiers
+
+Fine-tuned models for the **BRIGHTER** benchmark (SemEval-2025 Task 11):
+multilingual multi-label emotion classification.
+
+Submitted as part of the **Mining Media Data 2** course project.
+
+## Task
+
+- **Input:** short text (tweet / comment) in one of 28 languages
+- **Output:** one or more emotion labels from {anger, disgust, fear, joy, sadness, surprise}
+- **Metric:** macro-F1 over emotion labels
+
+## Models in this repository
+
+| Directory | Base model |
+|---|---|
+| `mbert/` | `google-bert/bert-base-multilingual-cased` |
+| `qwen3.5-0.8b/` | `Qwen/Qwen3.5-0.8B` |
+| `qwen3.5-0.8b-chinese-ft/` | `Qwen/Qwen3.5-0.8B` |
+| `qwen3.5-2b-chinese-ft/` | `Qwen/Qwen3.5-2B` |
+| `qwen3.5-4b-chinese-ft/` | `Qwen/Qwen3.5-4B` |
+
+## Dataset
+
+[BRIGHTER (SemEval-2025 Task 11)](https://brighter-dataset.github.io/)

mbert/config.json

@@ -0,0 +1,51 @@
+{
+  "add_cross_attention": false,
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": null,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "dtype": "float32",
+  "eos_token_id": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "anger",
+    "1": "disgust",
+    "2": "fear",
+    "3": "joy",
+    "4": "sadness",
+    "5": "surprise"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "is_decoder": false,
+  "label2id": {
+    "anger": 0,
+    "disgust": 1,
+    "fear": 2,
+    "joy": 3,
+    "sadness": 4,
+    "surprise": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "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",
+  "problem_type": "multi_label_classification",
+  "tie_word_embeddings": true,
+  "transformers_version": "5.10.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": false,
+  "vocab_size": 119547
+}