ModelHub XC 1fd833d9c5 初始化项目,由ModelHub XC社区提供模型
Model: maheshrawat18/Qwen3-4B-GRPO-sft
Source: Original Platform
2026-05-02 01:08:46 +08:00

base_model, tags, license, language
base_model tags license language
maheshrawat18/Qwen3-4B-Thinking-2507-merged
text-generation-inference
transformers
unsloth
qwen3
trl
apache-2.0
en

Uploaded model

  • Developed by: maheshrawat18
  • License: apache-2.0
  • Finetuned from model : maheshrawat18/Qwen3-4B-Thinking-2507-merged

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

Description
Model synced from source: maheshrawat18/Qwen3-4B-GRPO-sft
Readme 2 MiB
Languages
Jinja 100%