Qwen3.6-27B SecAlign
This repository contains a LoRA adapter for Qwen/Qwen3.6-27B. It does not include the base model weights. The supplied training metadata identifies direct preference optimization (DPO) with TRL.
To use the adapter, load the base model and apply this repository's adapter with PEFT. The adapter_config.json file records the base model and LoRA configuration; adapter_model.safetensors contains the adapter weights.
Training framework versions
- PEFT 0.19.1
- TRL 1.3.0
- Transformers 5.7.0.dev0
- PyTorch 2.8.0+cu128
- Datasets 4.8.5
- Tokenizers 0.22.2
- Downloads last month
- 14
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for SammySpace/Qwen3.6-27B_SecAlign
Base model
Qwen/Qwen3.6-27B