license: llama3
language:

• tr
  pipeline_tag: text-generation
  base_model: Metin/LLaMA-3-8B-Instruct-Abliterated-TR
  tags:
• llama-cpp
• gguf-my-repo
  model-index:
• name: LLaMA-3-8B-Instruct-Abliterated-TR
  results:
  • task:
    type: multiple-choice
    dataset:
    name: MMLU_TR_V0.2
    type: multiple-choice
    metrics:
    • type: 5-shot
      value: 0.4908
      name: 5-shot
      verified: false
    • type: 0-shot
      value: 0.4962
      name: 0-shot
      verified: false
    • type: 25-shot
      value: 0.4377
      name: 25-shot
      verified: false
    • type: 10-shot
      value: 0.4486
      name: 10-shot
      verified: false
    • type: 5-shot
      value: 0.5323
      name: 5-shot
      verified: false
    • type: 5-shot
      value: 0.5513
      name: 5-shot
      verified: false

matrixportalx/LLaMA-3-8B-Instruct-Abliterated-TR-Q4_K_M-GGUF

This model was converted to GGUF format from Metin/LLaMA-3-8B-Instruct-Abliterated-TR 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 matrixportalx/LLaMA-3-8B-Instruct-Abliterated-TR-Q4_K_M-GGUF --hf-file llama-3-8b-instruct-abliterated-tr-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo matrixportalx/LLaMA-3-8B-Instruct-Abliterated-TR-Q4_K_M-GGUF --hf-file llama-3-8b-instruct-abliterated-tr-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 matrixportalx/LLaMA-3-8B-Instruct-Abliterated-TR-Q4_K_M-GGUF --hf-file llama-3-8b-instruct-abliterated-tr-q4_k_m.gguf -p "The meaning to life and the universe is"

or

./llama-server --hf-repo matrixportalx/LLaMA-3-8B-Instruct-Abliterated-TR-Q4_K_M-GGUF --hf-file llama-3-8b-instruct-abliterated-tr-q4_k_m.gguf -c 2048