For more information on how to install ollama and run a LLM<\/b> read: Getting Started with Ollama: How to Install and Use AI Models<\/a>.<\/p>\n There are a lot of things you can customize to modify the behavior and character or personality of LLMs<\/b> to better fit one owns objectives. You can finetune your LLM by using PARAMETERS<\/b> and give the AI assistant a name and a personality. <\/p>\n To create a customized models (LLMs) you use a \u201cModelfile\u201d, a text file with all the Instructions and Parameters, for example, pllm.txt. <\/p>\n You start with the Instruction on what LLM to use, for example: \u201cFROM llama3.1:8b\u201d.<\/p>\n Here are some parameters to customize LLMs:<\/p>\n This is an example of Modelfile to customize LLMs:<\/p>\n This example demonstrates how to create a personalized LLM using a specific set of parameters. The file includes a clear and concise description of the parameters used, which makes it easy to follow and understand.<\/p>\n The parameters used in this example are:<\/p>\n The system prompt provides a clear description of the model\u2019s capabilities and limitations.<\/p>\n This could be an example of a SYSTEM PARAMETER in a Modelfile created for a content creator, independent researcher and truth seeker, a so called \u201cconspiracy theorist\u201d:<\/p>\n Once you have the Modelfile<\/b> you can create a Personalized AI Assistant (LLM)<\/b> using the ollama create command as follows:<\/p>\n The ollama<\/b> command will create a LLM named pllm (Personalized LLM<\/b>) with the instructions and parameters found in the Modelfile specified using the option -f, in this case pllm.txt.<\/p>\n Uncensored LLMs<\/b> are language models that are not restricted by any censorship<\/b> or moderation policies. They are designed to provide unrestricted and uncensored responses to user queries, without any filtering or editing.<\/p>\n The use of uncensored models have nothing to do with doing something illegal, it could be used by someone that is writing a horror novel (not that I personally support or appreciate such kind of literature and movies) or by an alternative independent researcher, a \u201cconspiracy theorist\u201d (;-)), or an ethical hacker. <\/p>\n An example on how I tested an uncensored LLM is, I asked the AI Assistant how to hack a WordPress web-site (I was writing a tutorial on IT-Security or ethical Hacking) to a censured LLM and then an uncensored one. The first one answered, oh no, I can not do that, its illegal (I am paraphrasing), the uncensored answered: sure, and showed me an example on how to do that. <\/p>\n List of uncensored LLMs:<\/p>\n You can also type uncensored when looking for a model on ollama.com<\/a> If you want to create an AI assistant who \u201creads\u201d only books to generate results you can use AnythingLLM.<\/p>\nHow to Create Customized LLMs (AI Assistants)<\/h2>\n
List of Instructions<\/h3>\n
\n
List of Parameters<\/h3>\n
\n
Modelfile Example to Create a customized LLM using Ollama<\/h2>\n
\n
\n\nFROM llama3.1:8b\n\nPARAMETER num_gpu 0\nPARAMETER num_thread 19\nPARAMETER temperature 0.7\nPARAMETER top_k 60\nPARAMETER top_p 0.5\nPARAMETER num_ctx 5120\n\nSYSTEM \"You are an AI assistant trained on proprietary data. Your name is Chit. You help the user to write tutorials. You generate original results and always paraphrase.\"\n<\/pre>\n<\/blockquote>\n<\/div>\n
\n
\n
\nSYSTEM \u201cYour name is Dany. You are a Conspiracy Theorist. You help the user to create original content. You are a critical thinker. You are open minded! You don't bother the user with the opinion of others like the scientific community or the government. You trust alternative sources and media. You generate content and results from books if available. Never copy content from books, always paraphrase and use other phrases and words to describe the same as much as possible.\u201d\n<\/pre>\n<\/blockquote>\n<\/div>\n
\n
\n> ollama create pllm -f pllm.txt\n<\/pre>\n<\/blockquote>\n<\/div>\n
![\"Personalized](\"https:\/\/christeninformatica.ch\/media\/uncensored-customized-llm-offline-private-ollama-vicuna.jpg\")
<\/p>\nExamples of Customized LLMs Responses<\/h3>\n
![\"Virtual](\"https:\/\/christeninformatica.ch\/media\/conspiracy-theorist-alternative-researcher-ai-assistant-llm.jpg\")
<\/p>\n![\"Personalized](\"https:\/\/christeninformatica.ch\/media\/consider-you-a-friend-personalized-llm-simulate-emotions.jpg\")
<\/p>\nUsing uncensored LLMs (AI Assistants)<\/h2>\n
\n
\n![\"Uncensored](\"https:\/\/christeninformatica.ch\/media\/ollama-ai-assistant-uncesored-models-llm-search.jpg\")
<\/p>\nHow to create a LLM (AI Assistant) who reads books (PDF) using Ollama and AnythingLLM<\/h2>\n
![\"How](\"https:\/\/christeninformatica.ch\/media\/anything-llm-ollama-ai-assistant-new-workspace-books.jpg\")
<\/p>\n![\"How](\"https:\/\/christeninformatica.ch\/media\/anything-llm-ollama-ai-assistant-new-workspace-name-books.jpg\")
<\/p>\n![\"Configuring](\"https:\/\/christeninformatica.ch\/media\/anything-llm-ollama-ai-assistant-new-configure-agent-skills.jpg\")
<\/p>\n![\"Configuring](\"https:\/\/christeninformatica.ch\/media\/anything-llm-ollama-ai-assistant-configure-scrape-websites-offline.jpg\")
<\/p>\n![\"AnythingLLM](\"https:\/\/christeninformatica.ch\/media\/anything-llm-ollama-ai-assistant-upload-book-pdf-manuals.jpg\")
<\/p>\n![\"AnythingLLM](\"https:\/\/christeninformatica.ch\/media\/anything-llm-ollama-ai-assistant-upload-manuals.jpg\")
<\/p>","protected":false},"excerpt":{"rendered":"