Instructions to use noctuashap/ZhiXin_embedding with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use noctuashap/ZhiXin_embedding with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="noctuashap/ZhiXin_embedding")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("noctuashap/ZhiXin_embedding") model = AutoModel.from_pretrained("noctuashap/ZhiXin_embedding") - Notebooks
- Google Colab
- Kaggle
ZhiXin_embedding
This model contains the fine-tuned retrieval embeddings of the ZhiXin model. For the fine-tuned model, see ZhiXin_model.
ZhiXin, introduced in the paper ZhiXin – A RAG-based Virtual Assistant for Persons with Intellectual and Developmental Disabilities, is a Retrieval-Augmented Generation (RAG) language model system specifically tailored to support parents of children with intellectual and developmental disorders. The core component of ZhiXin is a fine-tuned language model based on the Qwen2-7b-Instruct model. Leveraging Supervised Fine-Tuning (SFT) techniques, this specialized LLM has been trained to understand and address the unique challenges faced by parents and caregivers, providing relevant, empathetic, and reliable guidance.
- Downloads last month
- 3