Emilio407/Dolphin3.0-Qwen2.5-0.5B-GRPO-V1
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
0b2157e1f4814f4cad2956cb86f5f5c638ad0576
Dolphin3.0-Qwen2.5-0.5B-GRP…/README.md
ModelHub XC 0b2157e1f4 初始化项目，由ModelHub XC社区提供模型 
Model: Emilio407/Dolphin3.0-Qwen2.5-0.5B-GRPO-V1
Source: Original Platform
2026-05-03 02:38:46 +08:00

636 B
Raw Blame History

base_model, tags, license, language
base_model tags license language
cognitivecomputations/Dolphin3.0-Qwen2.5-0.5B
text-generation-inference
transformers
unsloth
qwen2
trl
grpo
apache-2.0
en

BAD PERFORMANCE

Uploaded model

  • Developed by: Emilio407
  • License: apache-2.0
  • Finetuned from model : cognitivecomputations/Dolphin3.0-Qwen2.5-0.5B

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