KickItLikeShika
/

qwen2.5-7b-instruct-infosft-science

Model card Files Files and versions

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

qwen2.5-7b-eopd-tooluse

InfoSFT: Learn More and Forget Less with Information-Aware Token Weighting:

Paper: https://arxiv.org/abs/2605.14967
Code: https://github.com/Helloworld10011/InfoSFT

Trained on Tooluse dataset, split released with Self-Distillation Fine-tuning (SDFT): https://github.com/idanshen/Self-Distillation/tree/main

Model scored 66.27% on the evaluation set

Downloads last month: 12

Safetensors

Model size

8B params

Tensor type

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including KickItLikeShika/qwen2.5-7b-instruct-infosft-science

iSDFT: Info-Proximal Self-Distillation Fine-Tuning

iSDFT Trained Models • 66 items • Updated 7 days ago • 4

Paper for KickItLikeShika/qwen2.5-7b-instruct-infosft-science

InfoSFT: Learn More and Forget Less with Information-Aware Token Weighting

Paper • 2605.14967 • Published May 14