MARIO-Math-Reasoning / Super_MARIO

MARIO-Math-Reasoning/Super_MARIO Issues

Problem running evaluation
Updated 12 days ago1
Issue about requirements file
Closed a month ago3
About Training data generation.
Closed a month ago2
type of template for training
Closed 2 months ago7
Possible problems about the training dataset
Closed 3 months ago2
Why are the batch size and number of epochs much larger than common SFT settings?
Closed 3 months ago3
Is the model initialized from pre-trained model or model from the last iteration round for each round?
Closed 3 months ago2
Why not directly generate the value, but instead add a value head? Could you explain the reasoning behind this decision?
Closed 4 months ago1
value estimation twice?
Closed 4 months ago5
training code
Closed 4 months ago2
How to initialize first generation child nodes?
Closed 4 months ago1
How to set B1 in Step level Beam Search
Closed 4 months ago3
MCTS training data generation in round1
Closed 4 months ago1
AttributeError: 'RequestOutput' object has no attribute 'value_estimate'
Closed 4 months ago1
About the code
Closed 5 months ago3
数学推理本身是个非对称二元博弈问题
Closed 5 months ago3
AlphaMath listed as AlaphaMath in Huggingface
Closed 5 months ago1
Concern on (first few rounds) sampling efficacy
Closed 5 months ago3