Google released their Gemma 2 language model, which has a 2B version that can run on basic home computing hardware. This video shows a test of the fine-tuned version called 2B_OR_NOT_2B. This has 2 billion parameters and removes some of the censorship from the original Gemma 2 model.
DOWNLOADS:
SicariusSicariiStuff 2B_OR_NOT_2B: https://huggingface.co/SicariusSicari...
mradermacher GGUF Quantized: https://huggingface.co/mradermacher/2...
bartowski GGUF Quantized: https://huggingface.co/bartowski/2B_o...
Original Gemma 2 2B: • Google Releases Gemma 2 2B LLM That Can Ru...
Run AI Locally On a Mac: • Unlock Ollama's Hidden Powers: Turn Your M...
INSTRUCTIONS:
Instructions to Run text-generation-webui on Linux: • How to Chat with Any Large Language Model ...
Instructions to Install and Run Ollama on Linux: • How to Run Local AI Chat On Linux Using Ol...
Instructions to Run LLM In the Cloud with Encryption and Password Protection: • How to Chat with LLM on Cloud GPU Using Ru...
Follow me on Twitter / X for Exclusive content, more LLM tests and my random thoughts about AI: https://x.com/vectro
Follow me on X for exclusive content: https://x.com/vectro