llama3-intent-awq-4bit

LLama 3 8B fine-tuned for intent classification with AWQ 4-bit quantization

Model Details

  • Model Type: Fine-tuned LLaMa 3 8B
  • Quantization: AWQ 4-bit
  • Tasks: Intent Classification
  • Training Data: Custom dataset for intent classification
  • Supported Intents: turn_on_light, turn_off_light, chat, call, text
Downloads last month
5
Safetensors
Model size
1.98B params
Tensor type
I32
·
F16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Evaluation results