metadata

base_model: SzilviaB/Guanaco-Frank-Jordan-13B-uncensored
library_name: transformers
tags:
  - mergekit
  - merge
  - llama-cpp
  - gguf-my-repo

Triangle104/Guanaco-Frank-Jordan-13B-uncensored-Q4_K_M-GGUF

This model was converted to GGUF format from SzilviaB/Guanaco-Frank-Jordan-13B-uncensored using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Model details:

This is a merge of pre-trained language models created using mergekit.

Merge Method

This model was merged using the TIES merge method using Fredithefish/Guanaco-13B-Uncensored as a base. Models Merged

The following models were included in the merge:

ajibawa-2023/Uncensored-Jordan-13B
ajibawa-2023/Uncensored-Frank-13B

Configuration

The following YAML configuration was used to produce this model:

models:

model: Fredithefish/Guanaco-13B-Uncensored #no parameters necessary for base model
model: ajibawa-2023/Uncensored-Frank-13B parameters: density: 0.5 weight: 0.5
model: ajibawa-2023/Uncensored-Jordan-13B parameters: density: 0.5 weight: 0.5

merge_method: ties base_model: Fredithefish/Guanaco-13B-Uncensored parameters: normalize: false int8_mask: true dtype: float16

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 Triangle104/Guanaco-Frank-Jordan-13B-uncensored-Q4_K_M-GGUF --hf-file guanaco-frank-jordan-13b-uncensored-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo Triangle104/Guanaco-Frank-Jordan-13B-uncensored-Q4_K_M-GGUF --hf-file guanaco-frank-jordan-13b-uncensored-q4_k_m.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 Triangle104/Guanaco-Frank-Jordan-13B-uncensored-Q4_K_M-GGUF --hf-file guanaco-frank-jordan-13b-uncensored-q4_k_m.gguf -p "The meaning to life and the universe is"

./llama-server --hf-repo Triangle104/Guanaco-Frank-Jordan-13B-uncensored-Q4_K_M-GGUF --hf-file guanaco-frank-jordan-13b-uncensored-q4_k_m.gguf -c 2048