Elstuhn/Qwen2.5-1.5B-Instruct-abliterated
TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kPublished:Feb 28, 2026Architecture:Transformer0.0K Warm

Elstuhn/Qwen2.5-1.5B-Instruct-abliterated is a 1.5 billion parameter instruction-tuned causal language model, fine-tuned from Qwen/Qwen2.5-1.5B-Instruct. Developed by Elstuhn, this model has undergone a process to significantly reduce its safety filters and censorship. It is specifically designed for use cases where unconstrained text generation is desired, demonstrating a substantial decrease in refusal rates compared to its base model.

Loading preview...