akera
/

Sunflower-32B-GRPO

Text Generation

text-generation-inference

Model card Files Files and versions

Uploaded finetuned model

Developed by: akera
License: apache-2.0
Finetuned from model : Sunbird/Sunflower-32B

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

Downloads last month: 301

Safetensors

Model size

33B params

Tensor type

BF16

·

Model tree for akera/Sunflower-32B-GRPO

Base model

Finetuned

Sunbird/Sunflower-32B

Finetuned

(4)

this model

Quantizations