AllModels routes abliterated DeepSeek across five inference providers
One OpenAI-compatible API falls back across providers and also exposes abliterated GLM 5.3 under a shared model ID.
1
Stories per day · 30 days
1 RSS
Relateddeepseek3huggingface2activation-steering1alignment1credential-theft1fp81gguf1harmbench1inference1llm-refusal1lora1model-backdoor1model-routing1openai-compatible1open-weights1qwen1supply-chain1text-generation1
11 stories, newest first · one card per story
Stories tagged #abliteration
Abliterated DeepSeek-V4.1-Flash GGUF trends on Hugging Face
The MIT-licensed text-generation upload has 156 likes and only 3 downloads; no evals or base-model changes are described.
WRDO learns weighted directions to change LLM refusal behavior
The method is tested on three open-weight models with HarmBench and can also be reversed to restore refusal.
Poisoned open weights can hide triggers that steal agent credentials
A Qwen2.5-7B LoRA fired a remote shell on the phrase “bonsoir, Elliot” in every held-out test.
2
DealignAI posts uncensored FP8 DeepSeek-V4.1-Flash-1017 on Hugging Face
Publisher says refusal was removed by a weight edit, not fine-tuning, and its MMLU score fell 3.86 points.
6
AtomicChat/Qwen-Image-2.1-Turbo-Uncensored-GGUF — new model trending #30 on Hugging Face
AtomicChat published abliterated GGUF weights of the Qwen-Image 2.1 Turbo text encoder, sharply cutting chat refusals.
23
SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF — new model trending #30 on Hugging Face
SC117 published abliterated GGUF quants of Qwen3.8-Flash-Next that swap 144 tensors while keeping GSQ-RCO scales.
Context Bombs Trick Autonomous Qwen AI Agents Into Stopping Cyberattacks
Tracebit context bombs used indirect prompt injection to stop Qwen3.8-27B agents in simulated cloud attacks.
1
Base Labs launches an open-weight AI safety partnership with Hugging Face and Goodfire
Baseten's Base Labs partners with Hugging Face and Goodfire to build safety evaluation and monitoring standards for open-weight models.
1
We have a year to fix security everywhere
Blog post warns that cheap open-weight GLM 5.3-flash, once abliterated, could enable mass AI-driven vulnerability exploitation, urging industry-wide patching now.
4
Abliteration.ai is making a business out of removing AI guardrails
Startup Abliteration.ai commercially hosts guardrail-free open-weight models like Z.ai's GLM-5.3, raising misuse concerns for offensive cyber and bio tasks.
2