Upload sib200_mbert_cda_llama_multilingual model

README.md

@@ -0,0 +1,42 @@
+# SIB200 CDA Model with Llama
+
+This model was trained on the SIB200 dataset using Counterfactual Data Augmentation (CDA) with counterfactuals generated by Llama.
+
+## Training Parameters
+
+- **Dataset**: SIB200
+- **Mode**: CDA
+- **Selection Model**: Llama
+- **Selection Method**: Random
+- **Train Size**: 700 examples
+- **Epochs**: 20
+- **Batch Size**: 8
+- **Effective Batch Size**: 32 (batch_size * gradient_accumulation_steps)
+- **Learning Rate**: 8e-06
+- **Patience**: 8
+- **Max Length**: 192
+- **Gradient Accumulation Steps**: 4
+- **Warmup Ratio**: 0.1
+- **Weight Decay**: 0.01
+- **Optimizer**: AdamW
+- **Scheduler**: cosine_with_warmup
+- **Random Seed**: 42
+
+## Performance
+
+- **Overall Accuracy**: 78.45%
+- **Overall Loss**: 0.0194
+
+### Language-Specific Performance
+- **English (EN)**: 83.84%
+- **German (DE)**: 87.88%
+- **Arabic (AR)**: 56.57%
+- **Spanish (ES)**: 88.89%
+- **Hindi (HI)**: 79.80%
+- **Swahili (SW)**: 73.74%
+
+## Model Information
+
+- **Base Model**: bert-base-multilingual-cased
+- **Task**: Topic Classification
+- **Languages**: 6 languages (EN, DE, AR, ES, HI, SW)

config.json

@@ -0,0 +1,49 @@
+{
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "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",
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e012f30e99f060dc4cc1fc4541ff23fa0a2a4fa2df9712d0e9c03a0017a6e495
+size 711458836

model_metadata.json

@@ -0,0 +1,10 @@
+{
+  "model_name": "sib200-bert-base-multilingual-cased-cda-llama-random",
+  "description": "SIB200 Multilingual CDA-Llama Model",
+  "huggingface_url": "https://huggingface.co/fledor/sib200-bert-base-multilingual-cased-cda-llama-random",
+  "local_path": null,
+  "mode": "cda-llama",
+  "dataset": "sib200",
+  "task": "multilingual",
+  "source": "huggingface"
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "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 +1,63 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 192,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}