Uploaded finetuned model

Developed by: ertghiu256
License: apache-2.0
Finetuned from model : unsloth/qwen3-4b-thinking-2507-unsloth-bnb-4bit
Config: learning_rate: 3e-4, steps: 384, dataset: TeichAI/gpt-5.1-high-reasoning-1000x

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

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for ertghiu256/Qwen3-4b-thinking-gpt5.1-distill

Base model

Finetuned

(138)

this model

Quantizations