Downloads · 30 days
7
17% of all-time downloads
R1-Qwen-7B-R_HORIZON_Compose_2_reward_all
lulululuyi/R1-Qwen-7B-R_HORIZON_Compose_2_reward_all
R1-Qwen-7B-R_HORIZON_Compose_2_reward_all is a machine learning model from lulululuyi. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
41
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
- Mar 10, 2026
- Updated
- Mar 10, 2026
- SHA
- 224ef618
Model card
From the Hugging Face model README
Model Description
R1-Qwen-7B-R_HORIZON_Compose_2_Reward_All is a reasoning model used in the paper:
“R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?”
This model corresponds to the Naive Training Data (n = 2) setting reported in Table 1, with an additional Reward-All training strategy applied.
- Type
- qwen2
- Created
- Mar 10, 2026
- Updated
- Mar 10, 2026