Text Generation
PEFT
Safetensors
Chinese
qwen3
lora
dialogue-act-planning
psychological-counseling
conversational
Instructions to use UEC-InabaLab/CounselTraj with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use UEC-InabaLab/CounselTraj with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B") model = PeftModel.from_pretrained(base_model, "UEC-InabaLab/CounselTraj") - Notebooks
- Google Colab
- Kaggle
Download examples/trajectory.json from UEC-InabaLab/CounselTraj: direct link, hf CLI and curl.
- Browser
- Download file 1.35 kB
-
https://huggingface.co/UEC-InabaLab/CounselTraj/resolve/main/examples/trajectory.json
- Command line
-
hf download hf://UEC-InabaLab/CounselTraj/examples/trajectory.json
-
curl -L -o trajectory.json https://huggingface.co/UEC-InabaLab/CounselTraj/resolve/main/examples/trajectory.json
1.35 kB
| { | |
| "index": 0, | |
| "id": "synthetic-example-001", | |
| "source_dataset": "synthetic_example", | |
| "source_id": "example-001", | |
| "topic": "emotion_anxiety", | |
| "topic_zh": "情绪焦虑", | |
| "turn_count": null, | |
| "input": "client:最近快考试了,我总担心考不好,晚上也睡不着。\ncounselor:听起来考试的压力让你一直很紧张。\nclient:是的,我想知道怎么让自己放松一点。", | |
| "features": { | |
| "emotion": 2, | |
| "request": 0, | |
| "detail": 2, | |
| "hesitation": 0, | |
| "positive": 0, | |
| "relation": 0, | |
| "career": 0, | |
| "crisis": 0, | |
| "knowledge": 0, | |
| "topic": "emotion_anxiety", | |
| "topic_zh": "情绪焦虑", | |
| "turn_count": 0, | |
| "chars": 82 | |
| }, | |
| "topic_group": "emotion", | |
| "target_len": 8, | |
| "output": "counselor:[Greeting] client:[Greeting] counselor:[OpenQuestion] client:[SelfDisclosure] counselor:[Affirm] client:[DetailedDescription] counselor:[Affirm] client:[Thanking] counselor:[Greeting]", | |
| "tag_counts": { | |
| "Greeting": 3, | |
| "OpenQuestion": 1, | |
| "SelfDisclosure": 1, | |
| "Affirm": 2, | |
| "DetailedDescription": 1, | |
| "Thanking": 1 | |
| }, | |
| "role_tag_counts": { | |
| "client": { | |
| "Greeting": 1, | |
| "SelfDisclosure": 1, | |
| "DetailedDescription": 1, | |
| "Thanking": 1 | |
| }, | |
| "counselor": { | |
| "Greeting": 2, | |
| "OpenQuestion": 1, | |
| "Affirm": 2 | |
| } | |
| } | |
| } | |