Downloads · 30 days
14
33% of all-time downloads
opsd-qwen2.5-7b-omnimath
TASMAYU/opsd-qwen2.5-7b-omnimath
opsd-qwen2.5-7b-omnimath is a machine learning model from TASMAYU. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This repository contains a Qwen 2.5 7B model post-trained using On-Policy Self-Distillation (OPSD) over the complex, Olympiad-level Omni-MATH dataset.
All-time downloads
42
Public
Parameters
7.6B
15.2 GB on disk
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors15.2 GB · 100%
At a glance
- License
- mit
- Model type
- qwen2
- Access
- Public
- Created
- Sep 3, 2026
- Updated
- Sep 6, 2026
- SHA
- 490f93d5
Base models
Datasets
Model card
From the Hugging Face model README
Qwen 2.5 7B - OPSD (On Policy Self Distillation ) on Omni-MATH
This repository contains a Qwen 2.5 7B model post-trained using On-Policy Self-Distillation (OPSD) over the complex, Olympiad-level Omni-MATH dataset.
The training run optimized the model for 1,000 steps with a maximum sequence generation limit expanded to 1024 tokens to allow natural, uninterrupted mathematical reasoning paths.
How to Load and Use This Model
You can load this model directly into your code using the Transformers library:
from transformers import AutoModelForCausalLM, AutoTokenizer
import torch
model_id = "TASMAYU/opsd-qwen2.5-7b-omnimath"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
model_id,
torch_dtype=torch.bfloat16,
device_map="auto"
)
- Type
- qwen2
- License
- mit
- Created
- Sep 3, 2026
- Updated
- Sep 6, 2026