Upload Indo RoBERTa Base for NLI for Indonesian NLI

README.md

@@ -0,0 +1,73 @@
+---
+language: id
+license: mit
+tags:
+- indonesian
+- nli
+- natural-language-inference
+- text-classification
+- afaji--indonli
+datasets:
+- afaji/indonli
+---
+# Unknown for Indonesian Natural Language Inference
+
+This model is fine-tuned on the [IndoNLI dataset](afaji/indonli) for natural language inference in Indonesian.
+
+## Model Description
+
+- **Model Type:** Unknown
+- **Task:** Natural Language Inference (Textual Entailment)
+- **Language:** Indonesian
+- **License:** MIT
+
+## Training Procedure
+
+## Dataset
+
+This model was trained on the [IndoNLI dataset](afaji/indonli), which contains 10k sentence pairs as a benchmark for natural language inference (NLI) in Indonesian.
+
+The dataset is split into:
+- Training set: 10k pairs
+- Validation set: 2.5k pairs
+- Test set (lay): 2.5k pairs
+- Test set (expert): 2.5k pairs
+
+## Usage
+
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+
+tokenizer = AutoTokenizer.from_pretrained("fabhiansan/indo-roberta-nli")
+model = AutoModelForSequenceClassification.from_pretrained("fabhiansan/indo-roberta-nli")
+
+# Prepare the input
+premise = "Seorang wanita sedang makan di restoran."
+hypothesis = "Seorang wanita sedang berada di luar ruangan."
+
+# Tokenize the input
+inputs = tokenizer(premise, hypothesis, return_tensors="pt")
+
+# Get the prediction
+outputs = model(**inputs)
+predictions = outputs.logits.argmax(dim=1)
+
+# Map predictions to labels
+id2label = {0: "entailment", 1: "neutral", 2: "contradiction"}
+predicted_label = id2label[predictions.item()]
+print(f"Predicted label: {predicted_label}")
+```
+
+## Citation
+
+If you use this model, please cite the IndoNLI paper:
+
+```bibtex
+@inproceedings{mahendra-etal-2021-indonli,
+    title = {IndoNLI: A Natural Language Inference Dataset for Indonesian},
+    author = {Mahendra, Rahmad and Aji, Alham Fikri and Louvan, Samuel and Rahman, Fahrurrozi and Vania, Clara},
+    booktitle = {Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing},
+    year = {2021},
+    publisher = {Association for Computational Linguistics},
+}
+```

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "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": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.50.0",
+  "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:fcc33e96a8115f3ed8a6ef50313eb4ec1056cd6eeeacce8fd6e5ba0203f6a036
+size 498615900

pretrained_model_name.txt

@@ -0,0 +1 @@
+flax-community/indonesian-roberta-base

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
+    },
+    "4": {
+      "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>"
+}