resistz
/

RLCR-Calibrated-Llama-3.1-8B-Instruct-DAPO-Math14K-40Step

Model card Files Files and versions

RLCR-calibrated Llama-3.1-8B-Instruct on DAPO-Math-14K

Llama-3.1-8B-Instruct is trained on DAPO-Math14k using RLCR.

Downloads last month: 7

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/RLCR-Calibrated-Llama-3.1-8B-Instruct-DAPO-Math14K-40Step

Test-time Calibration Learning (TTCL) Models

Test-time calibration learning for large language model reasoning • 72 items • Updated 25 days ago • 3