Braina 2.9 - LLM Options and download GGUF models directly from Hugging Face

New features and improvements made in Braina version 2.9 are as follows:

Claude 3.5 Sonnet now supports image input (vision)
LLM Options
You can now access various advanced LLM options for the currently selected LLM like context length, system prompt, temperature etc. by pressing Ctrl+O keyboard shortcut or by clicking on the LLM options Icon available on the right side of the Advanced AI Chat/LLM selection dropdown menu on the status-bar.
Download and Use GGUF Models from Hugging Face
To download any GGUF model directly from the Hugging Face Hub for use in Braina, follow these steps:
1. Navigate to the specific model page on Hugging Face that you wish to use.
2. Copy both the username and the repository name associated with the model.
3. Under the “Manage Local Models” section in Braina, input the tag in this format: hf.co/{username}/{repository}. For example:
  
  hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF
  
  For downloading a quantized version of the model, specify the tag with the desired quantization level appended to the repository name in this format: hf.co/{username}/{repository}:{quantization}, For e.g.:
  
  hf.co/bartowski/Llama-3.2-1B-Instruct-GGUF:Q5_K_M
  
  Tip: You can search for GGUF models on Hugging Face using this link: https://huggingface.co/models?library=gguf. Ensure that you select a language model rather than a text-to-image model.
  
  For more information on running LLM locally on your computer, please refer: Run Local LLM on your computer
4. Click “Download Model” button.

Braina 2.9 – LLM Options and download GGUF models directly from Hugging Face