resistz
/

TTCL-MATH500-RLCR-Qwen3-4B-DAPO-Math14K

Model card Files Files and versions

Test-time Calibration Learning (TTCL)

TTCL is performed on MATH500 benchmark based on RLCR-Qwen3-4B-DAPO-Math14K.

Downloads last month: 18

Safetensors

Model size

4B params

Tensor type

BF16

·

Inference Providers NEW

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

Model tree for resistz/TTCL-MATH500-RLCR-Qwen3-4B-DAPO-Math14K

Base model

Qwen/Qwen3-4B-Base

Finetuned

Finetuned

(1151)

this model

Collection including resistz/TTCL-MATH500-RLCR-Qwen3-4B-DAPO-Math14K

Test-time Calibration Learning (TTCL) Models

Test-time calibration learning for large language model reasoning • 43 items • Updated 11 days ago • 3