Instructions to use ShinojiResearch/Amadeus-Preview with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use ShinojiResearch/Amadeus-Preview with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("NyxKrage/Microsoft_Phi-4") model = PeftModel.from_pretrained(base_model, "ShinojiResearch/Amadeus-Preview") - Notebooks
- Google Colab
- Kaggle
Model Card for Model ID
Model Details
Model Description
- Developed by: Shinoji Research
- Funded by [optional]: Shinoji Research
- Shared by [optional]: [More Information Needed]
- Model type: [More Information Needed]
- Language(s) (NLP): [More Information Needed]
- License: Purely machine generated works are not eligilble for copyright protection. Out of respect for the license of Phi-4, we will only distribute the adapter file (for now).
- *Finetuned from model NyxKrage/Microsoft_Phi-4:
Model Sources [optional]
Uses
This is a super undertrained preview of Phi-4 trained on PowerInfer/QWQ-LONGCOT-500K dataset , heavily inspired by: https://huggingface.co/PowerInfer/SmallThinker-3B-Preview. It does produce slightly different responses than Phi-base but needs more training.
Assuming nothing goes wrong with the training process, in about 2 weeks we should have a completed version.
Training Details
Training Data
Trained on https://huggingface.co/datasets/PowerInfer/QWQ-LONGCOT-500K
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for ShinojiResearch/Amadeus-Preview
Base model
NyxKrage/Microsoft_Phi-4