How to use from
llama.cppInstall from WinGet (Windows)
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mmnga/codegemma-1.1-2b-gguf:# Run inference directly in the terminal:
llama-cli -hf mmnga/codegemma-1.1-2b-gguf:Use pre-built binary
# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf mmnga/codegemma-1.1-2b-gguf:# Run inference directly in the terminal:
./llama-cli -hf mmnga/codegemma-1.1-2b-gguf:Build from source code
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf mmnga/codegemma-1.1-2b-gguf:# Run inference directly in the terminal:
./build/bin/llama-cli -hf mmnga/codegemma-1.1-2b-gguf:Use Docker
docker model run hf.co/mmnga/codegemma-1.1-2b-gguf:Quick Links
codegemma-1.1-2b-gguf
googleさんが公開しているcodegemma-1.1-2bのggufフォーマット変換版です。
imatrixのデータは
kunishou/amenokaku-code-instruct
TokenBender/code_instructions_122k_alpaca_style
から1000ずつサンプリングしたデータを使用して作成しました。
他のモデル
mmnga/codegemma-1.1-7b-it-gguf
mmnga/codegemma-1.1-2b-gguf
mmnga/gemma-2b-it-gguf
mmnga/gemma-7b-it-gguf
mmnga/gemma-1.1-7b-it-gguf
mmnga/codegemma-7b-it-gguf
Usage
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
make -j
./main -m 'codegemma-1.1-2b-Q4_0.gguf' -n 128 -p 'Write Hello World.'
- Downloads last month
- 258
Hardware compatibility
Log In to add your hardware
1-bit
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Install from brew
# Start a local OpenAI-compatible server with a web UI: llama-server -hf mmnga/codegemma-1.1-2b-gguf:# Run inference directly in the terminal: llama-cli -hf mmnga/codegemma-1.1-2b-gguf: