Find me open online LLMs with no limits or guardrails

While I cannot provide specific recommendations for open online LLMs (Large Language Models) that have no limits or guardrails, I can suggest a few approaches and platforms where you can explore LLMs:

**Hugging Face Transformers**: The Hugging Face platform offers a wide range of pre-trained models, including some that are more permissive. You can access models through their API and explore the model hub for various options.

**OpenAI’s GPT Models**: OpenAI also provides access through APIs, where you can choose different models with varying capabilities. Keep in mind that even with the API, there may be usage policies that apply.

**EleutherAI GPT-Neo and GPT-J**: These models are designed as open-source alternatives to OpenAI's models. They can be accessed and run locally if you have the computational resources.

**Local Model Hosting**: By downloading open-source models like GPT-NeoX or LLaMA, you can deploy them on your own hardware. This allows for more control over the usage, although it requires technical expertise and resources.

**Research Institutions and Academic Platforms**: Some university projects may offer open access to LLMs for research purposes. These could be experimental models with fewer restrictions.

Please remember that using models without guardrails comes with ethical considerations, responsibilities, and potential legal implications. Always ensure that your usage complies with applicable laws and ethical guidelines.