| { | |
| "name": "Menda-3b-Optim-200", | |
| "language": "en", | |
| "license": "other", | |
| "base_model": "Qwen/Qwen2.5-3B-Instruct", | |
| "tags": [ | |
| "qwen", | |
| "grpo", | |
| "instruct", | |
| "fine-tuned", | |
| "reasoning", | |
| "3b", | |
| "menda", | |
| "chat", | |
| "transformers" | |
| ], | |
| "datasets": ["gsm8k"], | |
| "pipeline_tag": "text-generation", | |
| "widget": { | |
| "prompt": "You are a helpful AI assistant.\n\nUser: What is the formula for the area of a circle?\nAssistant:" | |
| } | |
| } |