Downloads · 30 days
19
17% of all-time downloads
KickItLikeShika/qwen2.5-7b-instruct-infosft-tooluse
qwen2.5-7b-instruct-infosft-tooluse 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.
InfoSFT: Learn More and Forget Less with Information-Aware Token Weighting: - Paper: https://arxiv.org/abs/2605.14967 - Code: https://github.com/Helloworld10011/InfoSFT
Downloads · 30 days
19
17% of all-time downloads
All-time downloads
111
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
InfoSFT: Learn More and Forget Less with Information-Aware Token Weighting:
Trained on Tooluse dataset, split released with Self-Distillation Fine-tuning (SDFT): https://github.com/idanshen/Self-Distillation/tree/main
Model scored 67% on the evaluation set