cxrbon16
/

qwen3-vl-8b-grpo-checkpoint-100-latest

Image-Text-to-Text

text-generation-inference

Model card Files Files and versions

Uploaded finetuned model

Developed by: cxrbon16
License: apache-2.0
Finetuned from model : Berkesule/qwen-3-vl-8b-it-puzzlevqa-sft

This qwen3_vl model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 2

Safetensors

Model size

9B params

Tensor type

BF16

·

Model tree for cxrbon16/qwen3-vl-8b-grpo-checkpoint-100-latest

Base model

Qwen/Qwen3-VL-8B-Instruct

Finetuned

unsloth/Qwen3-VL-8B-Instruct

Finetuned

Berkesule/qwen-3-vl-8b-it-puzzlevqa-sft

Finetuned

(8)

this model