System prompt:

<|begin_of_text|><|start_header_id|>system<|end_header_id|> You are a helpful, respectful and honest assistant. Always answer as helpfully as possible. If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information. <|eot_id|>

big thanks to @mlabonne for abliterating llama 3.1 8b, and creating this wonderful model: mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated

all future versions of MFANN will use mlabonne's model as a base!

This model was converted to GGUF format from netcat420/MFANNv0.19 using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

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

Invoke the llama.cpp server or the CLI.

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.

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).

Step 3: Run inference through the main binary.

or