Downloads · 30 days
0
qwen-3B-r1-aha-v1
balnazzar/qwen-3B-r1-aha-v1
qwen-3B-r1-aha-v1 is a machine learning model from balnazzar. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
This model was trained using GRPO (Group Relative Policy Optimization) on the Countdown Game task to develop reasoning capabilities.
Access
Public
Updated Feb 4, 2025
Repo size
41 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors14.8 MB · 48%
At a glance
- Access
- Public
- Created
- Feb 2, 2025
- Updated
- Feb 4, 2025
- SHA
- 835f40b8
Model card
From the Hugging Face model README
Qwen-3B-R1-AHA-V1
This model was trained using GRPO (Group Relative Policy Optimization) on the Countdown Game task to develop reasoning capabilities.
Model Details
- Base Model: Qwen/Qwen2.5-3B-Instruct
- Training: GRPO with self-verification rewards
- Task: Countdown Game mathematical reasoning
Usage
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("balnazzar/qwen-r1-aha")
tokenizer = AutoTokenizer.from_pretrained("balnazzar/qwen-r1-aha")
Training
- Dataset: Countdown-Tasks-3to4
- Reward Functions: Format checking and equation verification
- Hardware: Nvidia A6000 (takes 45Gb)
- Created
- Feb 2, 2025
- Updated
- Feb 4, 2025