beyoru/MinCoder-4B-Expert
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: beyoru/MinCoder-4B-Expert
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-06 15:11:18 +08:00
commit e45c8b6963
13 changed files with 152322 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
README.md Normal file
View File

@@ -0,0 +1,27 @@
---
base_model:
- beyoru/EvolLLM
tags:
- text-generation-inference
- transformers
- qwen3
- code
- tool
- agent
- evolution
- merge
- RL
- grpo
license: apache-2.0
language:
- en
---
This model is fine-tuned Qwen model using a custom reinforcement learning (RL) framework that rewards the model for producing solutions passing automated test cases — similar to the process of programming task evaluation on LeetCode.
<p align="center">
<img src="https://cdn-uploads.huggingface.co/production/uploads/65905af887944e494e37e09a/s4drmYGEYWZyt2ZUkxIpI.png" width="300">
</p>
Instead of relying on labeled ground truth answers, the model learns through test-case-based rewards, promoting generalization and reasoning ability in algorithmic problem-solving.