metadata
base_model: unsloth/Qwen3.5-9B
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3_5
license: apache-2.0
language:
- en
datasets:
- Roman1111111/gemini-3.1-pro-hard-high-reasoning
Uploaded finetuned model
- Developed by: Entity-27th
- License: apache-2.0
- Finetuned from model : unsloth/Qwen3.5-9B
- Hardware: AMD Instinct MI300X x 1
This qwen3_5 model was trained 2x faster with Unsloth and Huggingface's TRL library.
Stellar Pro is a variant of Qwen3.5-9B, PEFT'd and distilled with gemini-3.1-pro-hard-high-reasoning dataset. Trained on a single MI300X GPU, Stellar Pro is designed to enhance the base model's reasoning capabilities via distillation from Gemini 3.1 Pro.