Text Classification
PyTorch
Safetensors
Transformers
English
janegpt_v2_janus
janegpt
janus
react
interactive
vite
intent-classification
transformer
virtual-assistant
nlp
voice-assistant
offline-ai
edge-deployment
nlu
slot-filling
multitask-learning
assistant-runtime
Eval Results (legacy)
Instructions to use RavinduSen/JaneGPT-v2-Janus with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use RavinduSen/JaneGPT-v2-Janus with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="RavinduSen/JaneGPT-v2-Janus")# Load model directly from transformers import JaneGPTv3NLU model = JaneGPTv3NLU.from_pretrained("RavinduSen/JaneGPT-v2-Janus", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| import sys | |
| from pathlib import Path | |
| def main(): | |
| root = Path(__file__).resolve().parents[1] | |
| sys.path.insert(0, str(root)) | |
| # runtime wrapper (pending slot fill + follow-ups + llama routing) | |
| from runtime.jane_nlu_runtime import JaneNLURuntime | |
| rt = JaneNLURuntime(base_dir=str(root)) | |
| state = {} | |
| dialog = [ | |
| "increase the volume", | |
| "that is not enough", | |
| "that's too loud", | |
| "set volume", | |
| "55", # <- will now resolve pending VALUE | |
| "search", | |
| "cats", # <- will now resolve pending QUERY | |
| "hello", # <- routes to llama without destroying control state | |
| ] | |
| print("== JaneGPT-v2-Janus runtime demo ==") | |
| for u in dialog: | |
| out, state = rt.handle_turn(u, state) | |
| print("\nUSER:", u) | |
| print("OUT :", out) | |
| print("STATE:", state) | |
| if __name__ == "__main__": | |
| main() |