| base_model: Qwen/Qwen3-8B | |
| library_name: peft | |
| pipeline_tag: text-generation | |
| tags: | |
| - peft | |
| - lora | |
| - qwen3 | |
| - lean | |
| - theorem-proving | |
| # DiffLean Qwen3-8B Lean LoRA | |
| This repository contains a LoRA adapter trained on Lean theorem proving data. | |
| ## Base model | |
| - Qwen/Qwen3-8B | |
| ## Format | |
| - PEFT LoRA adapter | |
| - Not full model weights | |
| ## Usage | |
| Load this adapter on top of the base model with PEFT / LLaMA-Factory. | |