Downloads · 30 days
8
19% of all-time downloads
ALP_R1_Qwen1.5B
SynthLabsAI/ALP_R1_Qwen1.5B
ALP_R1_Qwen1.5B is a reinforcement learning model from SynthLabsAI. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
R1-Distill-Qwen-1.5B trained with Adaptive Length Penalty (ALP) - reduces token usage by ~50% while maintaining performance.
All-time downloads
42
Public
Parameters
1.8B
7.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.6 GB · 100%
At a glance
- Task
- Reinforcement Learning
- License
- apache-2.0
- Model type
- qwen2
- Access
- Public
- Created
- May 7, 2025
- Updated
- Jun 24, 2025
- SHA
- c88b0de1
Base models
Model card
From the Hugging Face model README
ALP_R1_Qwen1.5B
R1-Distill-Qwen-1.5B trained with Adaptive Length Penalty (ALP) - reduces token usage by ~50% while maintaining performance.
Training
- 100 steps GRPO, batch 512, LR 1e-6, β=1e-7
- 16 rollouts/prompt for difficulty estimation
- 8K context window
Performance (Pass@1)
- MATH-500: 0.81
- AIME: 0.252
- OlympiadBench: 0.51
Token Usage
- MATH: 2804→862 (-69%)
- AIME: 4007→3331 (-17%)
- Olympiad: 3606→2107 (-42%)
Usage
prompt = f"{problem} Let's think step by step and output the final answer within \\boxed{{}}."
- Task
- Reinforcement Learning
- Type
- qwen2
- License
- apache-2.0
- Created
- May 7, 2025
- Updated
- Jun 24, 2025