maheshrawat18/Qwen3-4B-GRPO-sft
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: maheshrawat18/Qwen3-4B-GRPO-sft
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-02 01:08:46 +08:00
commit 1fd833d9c5
14 changed files with 152331 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
README.md Normal file
View File

@@ -0,0 +1,22 @@
---
base_model: maheshrawat18/Qwen3-4B-Thinking-2507-merged
tags:
- text-generation-inference
- transformers
- unsloth
- qwen3
- trl
license: apache-2.0
language:
- 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](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)