Downloads · 30 days
14
14% of all-time downloads
KickItLikeShika/qwen-2.5-7b-instruct-taid-science
qwen-2.5-7b-instruct-taid-science is a machine learning model from KickItLikeShika. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Trained using Temporally Adaptive Interpolated Distillation (TAID): - Paper: https://arxiv.org/abs/2501.16937 - Code: https://github.com/SakanaAI/TAID
Downloads · 30 days
14
14% of all-time downloads
All-time downloads
100
Public
Parameters
7.6B
15.2 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors15.2 GB · 100%
From the Hugging Face model README
Trained using Temporally Adaptive Interpolated Distillation (TAID):
Student is qwen2.5-7b-instruct and teacher model is qwen2.5-32b-instruct
Trained on Science dataset, split released with Self-Distillation Fine-tuning (SDFT): https://github.com/idanshen/Self-Distillation/tree/main
Model scored 49.3% on the evaluation set