cognitivecomputations

/

Wizard-Vicuna-30B-Uncensored

like 147

Follow

Cognitive Computations 846

This is a very old model but to use ollama, or any other llama.cpp base, you'll need to use a GGUF.

You might be better off with:

• dolphin-2.7-mixtral-8x7b
• laserxtral (4x7B ~= 24B)
• dolphin-2.6-mistral-7b-dpo-laser

You can search for -GGUF versions of most models to find what you're looking for.

In regards to this model specifically, this would be the GGUF version:

• Wizard-Vicuna-30B-Uncensored-GGUF

--- [edit] ---
Ollama has some of these already built-in to their library:

• dolphin-mixtral (8x7B)
• dolphin-mistral (7B)

However, you can build your own:

• https://github.com/ollama/ollama/blob/main/docs/modelfile.md

This is a very old model but to use ollama, or any other llama.cpp base, you'll need to use a GGUF.

You might be better off with:

• dolphin-2.7-mixtral-8x7b
• laserxtral (4x7B ~= 24B)
• dolphin-2.6-mistral-7b-dpo-laser

You can search for -GGUF versions of most models to find what you're looking for.

In regards to this model specifically, this would be the GGUF version:

• Wizard-Vicuna-30B-Uncensored-GGUF

--- [edit] ---
Ollama has some of these already built-in to their library:

• dolphin-mixtral (8x7B)
• dolphin-mistral (7B)

However, you can build your own:

• https://github.com/ollama/ollama/blob/main/docs/modelfile.md

Thanks a lot for the suggestions. When I'm looking at the pages for these models your recommend, where would I find this GGUF phrase to install them?

Thanks a lot for the suggestions. When I'm looking at the pages for these models your recommend, where would I find this GGUF phrase to install them?

If you want to use ollama with the existing models then just type ollama run dolphin-mistral but if you want to use another then you may want to join their discord if you have trouble reading their documentation.