Upload 8 files

README.md

@@ -1,3 +1,131 @@
----
-license: mit
----
+---
+language: en
+license: mit
+tags:
+  - natural-language-inference
+  - sentence-transformers
+  - transformers
+  - nlp
+  - model-card
+---
+
+# mobilebert-uncased-nli
+
+- **Base Model:** [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased)
+- **Task:** Natural Language Inference (NLI)
+- **Framework:** Hugging Face Transformers, Sentence Transformers
+
+mobilebert-uncased-nli is a fine-tuned NLI model that classifies the relationship between pairs of sentences into three categories: entailment, neutral, and contradiction. It enhances the capabilities of [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased) for improved performance on NLI tasks.
+
+## Intended Use
+mobilebert-uncased-nli is ideal for applications requiring understanding of logical relationships between sentences, including:
+
+- Semantic textual similarity
+- Question answering
+- Dialogue systems
+- Content moderation
+
+## Performance
+mobilebert-uncased-nli was trained on the [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli) dataset, achieving competitive results in sentence pair classification.
+
+Performance on the MNLI matched validation set:
+- Accuracy: 0.7645
+- Precision: 0.77
+- Recall: 0.76
+- F1-score: 0.76
+
+## Training details
+
+<details>
+<summary><strong>Training Details</strong></summary>
+
+- **Dataset:** 
+  - Used [sentence-transformers/all-nli](https://huggingface.co/datasets/sentence-transformers/all-nli).
+  
+- **Sampling:**
+  - 100 000 training samples and 10 000 evaluation samples.
+
+- **Fine-tuning Process:**
+  - Custom Python script with adaptive precision training (bfloat16).
+  - Early stopping based on evaluation loss.
+
+- **Hyperparameters:**
+  - **Learning Rate:** 2e-5
+  - **Batch Size:** 32
+  - **Optimizer:** AdamW (weight decay: 0.01)
+  - **Training Duration:** Up to 10 epochs
+
+</details>
+
+<details>
+<summary><strong>Reproducibility</strong></summary>
+
+To ensure reproducibility:
+- Fixed random seed: 42
+- Environment:
+  - Python: 3.10.12
+  - PyTorch: 2.5.1
+  - Transformers: 4.44.2
+
+</details>
+
+## Usage Instructions
+
+## Using Sentence Transformers
+```python
+from sentence_transformers import CrossEncoder
+
+model_name = "agentlans/mobilebert-uncased-nli"
+model = CrossEncoder(model_name)
+scores = model.predict(
+    [
+        ("A man is eating pizza", "A man eats something"),
+        (
+            "A black race car starts up in front of a crowd of people.",
+            "A man is driving down a lonely road.",
+        ),
+    ]
+)
+
+label_mapping = ["entailment", "neutral", "contradiction"]
+labels = [label_mapping[score_max] for score_max in scores.argmax(axis=1)]
+print(labels)
+# Output: ['entailment', 'contradiction']
+```
+
+## Using Transformers Library
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
+
+model_name = "agentlans/mobilebert-uncased-nli"
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+
+features = tokenizer(
+    [
+        "A man is eating pizza",
+        "A black race car starts up in front of a crowd of people.",
+    ],
+    ["A man eats something", "A man is driving down a lonely road."],
+    padding=True,
+    truncation=True,
+    return_tensors="pt",
+)
+
+model.eval()
+with torch.no_grad():
+    scores = model(**features).logits
+    label_mapping = ["entailment", "neutral", "contradiction"]
+    labels = [label_mapping[score_max] for score_max in scores.argmax(dim=1)]
+    print(labels)
+# Output: ['entailment', 'contradiction']
+```
+
+## Limitations and Ethical Considerations
+mobilebert-uncased-nli may reflect biases present in the training data. Users should evaluate its performance in specific contexts to ensure fairness and accuracy.
+
+## Conclusion
+mobilebert-uncased-nli offers a robust solution for NLI tasks, enhancing [google/mobilebert-uncased](https://huggingface.co/google/mobilebert-uncased)'s capabilities with straightforward integration into existing frameworks. It aids developers in building intelligent applications that require nuanced language understanding.
+
+

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "google/mobilebert-uncased",
+  "architectures": [
+    "MobileBertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_activation": false,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "relu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 512,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "intra_bottleneck_size": 128,
+  "key_query_shared_bottleneck": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "mobilebert",
+  "normalization_type": "no_norm",
+  "num_attention_heads": 4,
+  "num_feedforward_networks": 4,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "trigram_input": true,
+  "true_hidden_size": 128,
+  "type_vocab_size": 2,
+  "use_bottleneck": true,
+  "use_bottleneck_attention": false,
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f20855e484a47835e886d405a5a9e4cab9efaa16c9257ec0293806d5eeb05921
+size 98472172

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "MobileBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa79b243ad52b4293d04df8a81935052f46aea9d913649061f397c49f27f1c36
+size 5176