Downloads · 30 days
17
24% of all-time downloads
qwen2.5-7b-instruct-eopd-tooluse
KickItLikeShika/qwen2.5-7b-instruct-eopd-tooluse
qwen2.5-7b-instruct-eopd-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.
Entropy-Aware On-Policy Distillation of Language Models (EOPD): - Paper: https://arxiv.org/abs/2603.07079 - Code: https://github.com/WLS04/EOPD
All-time downloads
70
Public
Parameters
7.6B
15.2 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors15.2 GB · 100%
At a glance
- Model type
- qwen2
- Access
- Public
- Created
- Jun 21, 2026
- Updated
- Jun 21, 2026
- SHA
- 2451cb4d
Model card
From the Hugging Face model README
qwen2.5-7b-eopd-tooluse
Entropy-Aware On-Policy Distillation of Language Models (EOPD):
Student is qwen2.5-7b-instruct and teacher model is qwen2.5-32b-instruct
Trained on Tooluse dataset, split released with Self-Distillation Fine-tuning (SDFT): https://github.com/idanshen/Self-Distillation/tree/main
Model scored 53.6% on the evaluation set
- Type
- qwen2
- Created
- Jun 21, 2026
- Updated
- Jun 21, 2026