resistz
/

TTCL-SimpleQA-RLCR-Llama-3.1-8B-Instruct-DAPO-Math14K

Model card Files Files and versions

Test-time Calibration Learning (TTCL)

TTCL is performed on SimpleQA benchmark based on RLCR-Llama-3.1-8B-Instruct-DAPO-Math14K.

Downloads last month: 17

Safetensors

Model size

8B params

Tensor type

BF16

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including resistz/TTCL-SimpleQA-RLCR-Llama-3.1-8B-Instruct-DAPO-Math14K

Test-time Calibration Learning (TTCL) Models

Test-time calibration learning for large language model reasoning • 49 items • Updated 2 days ago • 3