license, base_model, base_model_relation, library_name, pipeline_tag, tags

license	base_model	base_model_relation	library_name	pipeline_tag	tags
apache-2.0	Qwen/Qwen2.5-7B-Instruct	merge	transformers	text-generation	safety alignment

HARC — Qwen2.5-7B-Instruct

HARC safety-alignment LoRA merged into Qwen/Qwen2.5-7B-Instruct (full standalone model). Part of the HARC release; see paper arXiv:2607.00572.

from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("microsoft/HARC-Qwen2.5-7B-Instruct", torch_dtype="bfloat16", device_map="auto")
tok = AutoTokenizer.from_pretrained("microsoft/HARC-Qwen2.5-7B-Instruct")