metadata

tags:
  - merge
  - mergekit
  - lazymergekit
  - zhengr/MixTAO-7Bx2-MoE-v8.1
  - jsfs11/MixtureofMerges-MoE-2x7b-v6
  - llama-cpp
  - gguf-my-repo
base_model:
  - zhengr/MixTAO-7Bx2-MoE-v8.1
  - jsfs11/MixtureofMerges-MoE-2x7b-v6

jsfs11/MixtureofMerges-MoE-2x7b-SLERPv0.9b-GGUF

This model was converted to GGUF format from jsfs11/MixtureofMerges-MoE-2x7b-SLERPv0.9b using llama.cpp via the ggml.ai's GGUF-my-repo space.
Refer to the original model card for more details on the model.
Imatrix quants done manually, imatrix.dat provided.

Use with llama.cpp

Install llama.cpp through brew.

brew install ggerganov/ggerganov/llama.cpp

Invoke the llama.cpp server or the CLI.

CLI:

llama-cli --hf-repo jsfs11/MixtureofMerges-MoE-2x7b-SLERPv0.9b-Q4_K_M-GGUF --model mixtureofmerges-moe-2x7b-slerpv0.9b.Q4_K_M.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo jsfs11/MixtureofMerges-MoE-2x7b-SLERPv0.9b-Q4_K_M-GGUF --model mixtureofmerges-moe-2x7b-slerpv0.9b.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.

git clone https://github.com/ggerganov/llama.cpp &&             cd llama.cpp &&             make &&             ./main -m mixtureofmerges-moe-2x7b-slerpv0.9b.Q4_K_M.gguf -n 128