This model is from paper "Can A Gamer Train A Mathematical Reasoning Model?" which examines training a mathematical reasoning model on a single gaming GPU, namely RTX 3080 TI.
Model Details
Model Description
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("shinysup/YouronMath")
tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2.5-Math-1.5B")
Developed by: Andrew Shin
Funded by [optional]: [More Information Needed]
Shared by [optional]: [More Information Needed]
Model type: [More Information Needed]
Language(s) (NLP): [More Information Needed]
License: MIT License
Finetuned from model [optional]: Qwen2.5-Math-1.5B
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
