Detective adapter
QLoRA adapter for Qwen/Qwen3-8B, revision b968826d9c46dd6066d109eabc6255188de91218. The base model is not in this repository.
adapter_model.safetensors SHA256: 8755e26df3f370a8396e7acdae6670f2a45c6cdcdbca4ea3d0ce911a059afebc
LoRA r=16, lora_alpha=32, dropout 0.05, PEFT 0.20.0. Load this repository with PeftModel.from_pretrained on that base model.
- Downloads last month
- 7
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support