metadata

language: en
license: mit
tags:
  - natural-language-inference
  - sentence-transformers
  - transformers
  - nlp
  - model-card

NoInstruct-small-Embedding-v0-nli

Base Model: avsolatorio/NoInstruct-small-Embedding-v0
Task: Natural Language Inference (NLI)
Framework: Hugging Face Transformers, Sentence Transformers

NoInstruct-small-Embedding-v0-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 avsolatorio/NoInstruct-small-Embedding-v0 for improved performance on NLI tasks.

Intended Use

NoInstruct-small-Embedding-v0-nli is ideal for applications requiring understanding of logical relationships between sentences, including:

Semantic textual similarity
Question answering
Dialogue systems
Content moderation

Performance

NoInstruct-small-Embedding-v0-nli was trained on the sentence-transformers/all-nli dataset, achieving competitive results in sentence pair classification.

Performance on the MNLI matched validation set:

Accuracy: 0.7687
Precision: 0.77
Recall: 0.77
F1-score: 0.77

Training details

Training Details

Dataset:
- Used 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: 64
- Optimizer: AdamW (weight decay: 0.01)
- Training Duration: Up to 10 epochs

Reproducibility

To ensure reproducibility:

Fixed random seed: 42
Environment:
- Python: 3.10.12
- PyTorch: 2.5.1
- Transformers: 4.44.2

Usage Instructions

Using Sentence Transformers

from sentence_transformers import CrossEncoder

model_name = "agentlans/NoInstruct-small-Embedding-v0-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)

Using Transformers Library

from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch

model_name = "agentlans/NoInstruct-small-Embedding-v0-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)

Limitations and Ethical Considerations

NoInstruct-small-Embedding-v0-nli may reflect biases present in the training data. Users should evaluate its performance in specific contexts to ensure fairness and accuracy.

Conclusion

NoInstruct-small-Embedding-v0-nli offers a robust solution for NLI tasks, enhancing avsolatorio/NoInstruct-small-Embedding-v0's capabilities with straightforward integration into existing frameworks. It aids developers in building intelligent applications that require nuanced language understanding.