this is the bugfix release to MFANNv0.22 which had errors involving refusing to generate a response to certain questions, usually by asking you what you would like to do and ignoring your question, along with some perplexity issues. i suspect this has to do with the DARE-TIES merging i have been doing, which up until now has actually proven to work well but i guess after a good bit of iterations pass, degradation appears to show up. so for the time being im sticking to this new SLERP merging routine i have planned.

designed to be a generally intelligent chain of thought reasoner model. this model is currently still in pre release v0.x beta, and may produce responses not suitable for all audiences due to its uncensored nature.

Thank you so much to @mlabonne for creating the base model mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated for this experiment! please go show him some love too!

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.<|eot_id|>

netcat420/MFANNv0.22.1-Q8_0-GGUF

This model was converted to GGUF format from netcat420/MFANNv0.22.1 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 netcat420/MFANNv0.22.1-Q8_0-GGUF --hf-file mfannv0.22.1-q8_0.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo netcat420/MFANNv0.22.1-Q8_0-GGUF --hf-file mfannv0.22.1-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 netcat420/MFANNv0.22.1-Q8_0-GGUF --hf-file mfannv0.22.1-q8_0.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo netcat420/MFANNv0.22.1-Q8_0-GGUF --hf-file mfannv0.22.1-q8_0.gguf -c 2048