intent-router
IntentRouterTrain
MODF-SIR: a Multi-agent Omni-modal Distilled Framework for Social Intelligence Reasoning
MODF-SIR is a lightweight MLLM-based, distillation-augmented, multi-agent collaborative framework for social intelligence reasoning.
🔖 Model Details
Model type: Omni-modal Large Language Model
License: BSD-3-Clause
Project Page: Arxiv: https://arxiv.org/abs/2606.12018
Code Repository: GitHub: https://github.com/eeee-sys/MODF-SIR
👀 MODF-SIR… See the full description on the dataset page: https://huggingface.co/datasets/Harry-1234/IntentRouterTrain.WAMP-Router-Intent-Dataset
WAMP Router Intent Dataset
This dataset was created for training the WAMP-proxy semantic router. It contains user queries in Russian and English across various domains (Technical, Medicine, Art, Philosophy, etc.) classified into three intent categories.
Dataset Structure
The dataset consists of two columns:
text: The user query string.
label: The integer class ID.
label_text: Human-readable class name.
Labels
0 (Summary): General requests for recaps, TL;DR… See the full description on the dataset page: https://huggingface.co/datasets/naranor/WAMP-Router-Intent-Dataset.router-intent-classifier-50kagent-intent-routerintent_router
viet-robot-voice-commands-log
A synthetic log of simple voice commands given to a home robot/assistant.
Columns:
id: row id
timestamp_local: local time string
text_vi: Vietnamese utterance
text_en: rough English translation
detected_intent: clean_room, go_dock, play_music, answer_question, small_talk, other
target_room: optional target room if applicable
note_en: short English note
Manually authored for demos and testing.
License
MIT