This is just a personal quant I made for myself from a model that Sao10K had on the horde a while back. I really REALLY like this one lmao.

Works great with just normal llama3 settings and such. I usually have it around 1.1 temp. I feel like this was just an experiment that Sao made on a whim, but it just particularly stood out to me. :D

Razrien/L3-8B-Tamamo-v1-Q8_0-GGUF

This model was converted to GGUF format from Sao10K/L3-8B-Tamamo-v1 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 Razrien/L3-8B-Tamamo-v1-Q8_0-GGUF --hf-file l3-8b-tamamo-v1-q8_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Razrien/L3-8B-Tamamo-v1-Q8_0-GGUF --hf-file l3-8b-tamamo-v1-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 Razrien/L3-8B-Tamamo-v1-Q8_0-GGUF --hf-file l3-8b-tamamo-v1-q8_0.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo Razrien/L3-8B-Tamamo-v1-Q8_0-GGUF --hf-file l3-8b-tamamo-v1-q8_0.gguf -c 2048