Magnum_Smaug_34b-Q8_0-GGUF

Can be shy, will refuse a lot of stuff and can be prude.

Can be super creative and original if you egg it on.

At first glance and if you don't dig deep it might appear bland and boring.

Can start hallucinating towards the end of the answer.

SzilviaB/Magnum_Smaug_34b-Q8_0-GGUF

Slerp merge of:

anthracite-org/magnum-v3-34b (base)

abacusai/Smaug-34B-v0.1

SzilviaB/mergekit-slerp-xirdwrw-Q8_0-GGUF

This model was converted to GGUF format from mergekit-community/mergekit-slerp-xirdwrw using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Use with llama.cpp

Install llama.cpp through brew (works on Mac and Linux)

brew install llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo SzilviaB/mergekit-slerp-xirdwrw-Q8_0-GGUF --hf-file mergekit-slerp-xirdwrw-q8_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo SzilviaB/mergekit-slerp-xirdwrw-Q8_0-GGUF --hf-file mergekit-slerp-xirdwrw-q8_0.gguf -c 2048

Note: You can also use this checkpoint directly through the usage steps listed in the Llama.cpp repo as well.

Step 1: Clone llama.cpp from GitHub.

git clone https://github.com/ggerganov/llama.cpp

Step 2: Move into the llama.cpp folder and build it with LLAMA_CURL=1 flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).

cd llama.cpp && LLAMA_CURL=1 make

Step 3: Run inference through the main binary.

./llama-cli --hf-repo SzilviaB/mergekit-slerp-xirdwrw-Q8_0-GGUF --hf-file mergekit-slerp-xirdwrw-q8_0.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo SzilviaB/mergekit-slerp-xirdwrw-Q8_0-GGUF --hf-file mergekit-slerp-xirdwrw-q8_0.gguf -c 2048