This is a LoRA (Low-Rank Adaptation) fine-tuned model based on bert-base-uncased for Intent Classification - Classifies text into categories like business, technology, science, etc..

This model is part of the semantic-router project and is optimized for use with the Candle framework in Rust.

Model Details

Base Model: bert-base-uncased
Task: Intent Classification
Framework: Candle (Rust)
Model Size: ~418MB
LoRA Rank: N/A
LoRA Alpha: N/A
Target Modules:

Usage

With semantic-router (Recommended)

python

from semantic_router import SemanticRouter

# The model will be automatically downloaded and used
router = SemanticRouter()
results = router.classify_batch(["Your text here"])

With Candle (Rust)

rust

use candle_core::{Device, Tensor};
use candle_transformers::models::bert::BertModel;

// Load the model using Candle
let device = Device::Cpu;
let model = BertModel::load(&device, &config, &weights)?;

Training Details

This model was fine-tuned using LoRA (Low-Rank Adaptation) technique:

Rank: 16
Alpha: 32
Dropout: 0.1
Target Modules:

Performance

Intent Classification - Classifies text into categories like business, technology, science, etc.

For detailed performance metrics, see the training results.

Files

model.safetensors: LoRA adapter weights
config.json: Model configuration
lora_config.json: LoRA-specific configuration
tokenizer.json: Tokenizer configuration
label_mapping.json: Label mappings for classification

Citation

If you use this model, please cite:

bibtex

@misc{semantic-router-lora,
  title={LoRA Fine-tuned Models for Semantic Router},
  author={Semantic Router Team},
  year={2025},
  url={https://github.com/vllm-project/semantic-router}
}

License

Apache 2.0

llm-semantic-router/lora_intent_classifier_bert-base-uncased_model

lora_intent_classifier_bert-base-uncased_model

Model Description