Text Classification
Transformers
Safetensors
English
llama
text-generation
intent-classification
awq
Eval Results (legacy)
text-embeddings-inference
4-bit precision
Instructions to use emasoga3/llama3-intent-awq-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use emasoga3/llama3-intent-awq-4bit with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="emasoga3/llama3-intent-awq-4bit")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("emasoga3/llama3-intent-awq-4bit") model = AutoModelForCausalLM.from_pretrained("emasoga3/llama3-intent-awq-4bit") - Notebooks
- Google Colab
- Kaggle
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
Evaluation results
- Intent Classification Accuracyself-reported85.200