Files
ModelHub XC dd6915c1df 初始化项目,由ModelHub XC社区提供模型
Model: MildConcussion/Qwen2.5-3B-Instruct-abliterated-16bit-GRPO
Source: Original Platform
2026-09-13 17:26:43 +08:00

626 B

base_model, tags, license, language
base_model tags license language
MildConcussion/Qwen2.5-3B-Instruct-abliterated
text-generation-inference
transformers
unsloth
qwen2
trl
grpo
apache-2.0
en

Uploaded model

  • Developed by: MildConcussion
  • License: apache-2.0
  • Finetuned from model : MildConcussion/Qwen2.5-3B-Instruct-abliterated

This qwen2 model was trained 2x faster with Unsloth and Huggingface's TRL library.