metadata

language:
  - multilingual
license: mit
tags:
  - nlp
  - code
  - llama-cpp
  - gguf-my-repo
base_model: failspy/Phi-3-mini-4k-geminified
license_link: https://huggingface.co/microsoft/Phi-3-medium-4k-instruct/resolve/main/LICENSE
pipeline_tag: text-generation
inference:
  parameters:
    temperature: 0.7
widget:
  - messages:
      - role: user
        content: What's the difference between a banana and a strawberry?

v8karlo/Phi-3-mini-4k-geminified-Q4_K_M-GGUF

This model was converted to GGUF format from failspy/Phi-3-mini-4k-geminified using llama.cpp via the ggml.ai's GGUF-my-repo space. Refer to the original model card for more details on the model.

Convert Safetensors to GGUF . https://huggingface.co/spaces/ggml-org/gguf-my-repo .

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 --hf-repo v8karlo/Phi-3-mini-4k-geminified-Q4_K_M-GGUF --hf-file phi-3-mini-4k-geminified-q4_k_m.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo v8karlo/Phi-3-mini-4k-geminified-Q4_K_M-GGUF --hf-file phi-3-mini-4k-geminified-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.

./main --hf-repo v8karlo/Phi-3-mini-4k-geminified-Q4_K_M-GGUF --hf-file phi-3-mini-4k-geminified-q4_k_m.gguf -p "The meaning to life and the universe is"

./server --hf-repo v8karlo/Phi-3-mini-4k-geminified-Q4_K_M-GGUF --hf-file phi-3-mini-4k-geminified-q4_k_m.gguf -c 2048