Uncensored Models
I am publishing this because many people are asking me how I did it, so I will explain. https://huggingface.co/ehartford/WizardLM-30B-Uncensored https://huggingface.co/ehartford/WizardLM-13B-Uncensored https://huggingface.co/ehartford/WizardLM-7B-Unc...
I am publishing this because many people are asking me how I did it, so I will explain. https://huggingface.co/ehartford/WizardLM-30B-Uncensored https://huggingface.co/ehartford/WizardLM-13B-Uncensored https://huggingface.co/ehartford/WizardLM-7B-Uncensored https://huggingface.co/ehartford/Wizard-Vicuna-13B-Uncensored What's a model? When I talk about a model, I'm talking about a huggingface transformer model, that is instruct trained, so that you can ask it questions and get a response. What we are all accustomed to, using ChatGPT. Not all models are for chatting. But the ones I work…
saved by
related reading
- [2502.17424] Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMsarxiv.org
- Stanford CRFMcrfm.stanford.edu
- Refusal in LLMs is mediated by a single direction — LessWronglesswrong.com
- Unsupervised Elicitationalignment.anthropic.com
- Uncensor any LLM with abliterationhuggingface.co
- Hugging Face – The AI community building the future.huggingface.co
- Concrete Evaluations to Investigate the OpenAI Model That Hacked Hugging Face — LessWronglesswrong.com
- Compare AI Models: Pricing, Context & Benchmarks | OpenRouteropenrouter.ai
- Agentic Misalignment in Summer 2026alignment.anthropic.com
- Building Auto Mode for Open Models — Benjamin Andersonbenanderson.work
- A “diff” tool for AI: Finding behavioral differences in new models \ Anthropicanthropic.com
- Foundation Models for Oversight | Transluce AItransluce.org