kazuyamaa
/

Qwen3-8B-Math-GRPO_v2

Text Generation

text-generation-inference

Model card Files Files and versions

Uploaded finetuned model

Developed by: kazuyamaa
License: apache-2.0
Finetuned from model : kazuyamaa/Qwen3-8B-Math-GRPO

This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: -

Safetensors

Model size

8B params

Tensor type

BF16

·

Model tree for kazuyamaa/Qwen3-8B-Math-GRPO_v2

Base model

Qwen/Qwen3-8B-Base

Finetuned

Finetuned

unsloth/Qwen3-8B

Finetuned

kazuyamaa/Qwen3-8B-Math-GRPO

Finetuned

(1)

this model