You can deploy this model and start earning money today!

Ursulalala/
X_Boundary_DeepSeek_R1_Distill_Qwen_7B_adapter

Name: X_Boundary_DeepSeek_R1_Distill_Qwen_7B_adapter
Availability: InStock

peft

safetensors

deepseek-ai/DeepSeek-R1-Distill-Qwen-7B

adapter

Views

No views yet

Model Card for X_Boundary_DeepSeek_R1_Distill_Qwen_7B_adapter

X_Boundary_DeepSeek_R1_Distill_Qwen_7B_adapter is an LoRA adapter of DeepSeek_R1_Distill_Qwen_7B trained by X-Boundary.

X-Boundary is a method to strike a balance between robust defense against multi-turn jailbreak attacks and the usability of Large Language Model (LLM) by establishing exact distinction boundary between safe and harmful representations.

Quick Start

python

from transformers import AutoModelForCausalLM, AutoTokenizer

base_model_name = 'deepseek-ai/DeepSeek-R1-Distill-Qwen-7B'
adapter_name = 'Ursulalala/X_Boundary_DeepSeek_R1_Distill_Qwen_7B_adapter'
model = AutoModelForCausalLM.from_pretrained(
    base_model_name,
    torch_dtype='auto',
    device_map='auto'
)
tokenizer = AutoTokenizer.from_pretrained(base_model_name)
model.load_adapter(adapter_name)

Framework versions

PEFT 0.13.2