metadata

base_model: google/gemma-2-2b-it
library_name: transformers
license: gemma
pipeline_tag: text-generation
tags:
  - conversational
  - llama-cpp
  - gguf-my-repo
extra_gated_heading: Access Gemma on Hugging Face
extra_gated_prompt: >-
  To access Gemma on Hugging Face, you’re required to review and agree to
  Google’s usage license. To do this, please ensure you’re logged in to Hugging
  Face and click below. Requests are processed immediately.
extra_gated_button_content: Acknowledge license

hellork/gemma-2-2b-it-IQ4_NL-GGUF

This model was converted to GGUF format from google/gemma-2-2b-it 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 hellork/gemma-2-2b-it-IQ4_NL-GGUF --hf-file gemma-2-2b-it-iq4_nl-imat.gguf -p "The meaning to life and the universe is"

Server:

llama-server --hf-repo hellork/gemma-2-2b-it-IQ4_NL-GGUF --hf-file gemma-2-2b-it-iq4_nl-imat.gguf -c 2048

The Ship's Computer:

whisper_dictation

Interact with this model by speaking to it. Lean, fast, & private, networked speech to text, AI images, multi-modal voice chat, control apps, webcam, and sound with less than 4GiB of VRAM.

git clone -b main --single-branch https://github.com/themanyone/whisper_dictation.git
pip install -r whisper_dictation/requirements.txt

git clone https://github.com/ggerganov/whisper.cpp
cd whisper.cpp
GGML_CUDA=1 make -j # assuming CUDA is available. see docs
ln -s server ~/.local/bin/whisper_cpp_server # (just put it somewhere in $PATH)

whisper_cpp_server -l en -m models/ggml-tiny.en.bin --port 7777
cd whisper_dictation
./whisper_cpp_client.py

See the docs for tips on integrating with llama.cpp server, enabling the computer to talk back, draw AI images, carry out voice commands, and other features.

Install Llama.cpp via git:

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 hellork/gemma-2-2b-it-IQ4_NL-GGUF --hf-file gemma-2-2b-it-iq4_nl-imat.gguf -p "The meaning to life and the universe is"

./llama-server --hf-repo hellork/gemma-2-2b-it-IQ4_NL-GGUF --hf-file gemma-2-2b-it-iq4_nl-imat.gguf -c 2048