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 TheDrummer/Tiger-Gemma-9B-v2-GGUF:# Run inference directly in the terminal:
llama-cli -hf TheDrummer/Tiger-Gemma-9B-v2-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 TheDrummer/Tiger-Gemma-9B-v2-GGUF:# Run inference directly in the terminal:
./llama-cli -hf TheDrummer/Tiger-Gemma-9B-v2-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 TheDrummer/Tiger-Gemma-9B-v2-GGUF:# Run inference directly in the terminal:
./build/bin/llama-cli -hf TheDrummer/Tiger-Gemma-9B-v2-GGUF:Use Docker
docker model run hf.co/TheDrummer/Tiger-Gemma-9B-v2-GGUF:Quick Links
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
Tiger Gemma 9B v2
Decensored Gemma 9B. No refusals so far. No apparent brain damage.
Links
- Original: https://huggingface.co/TheDrummer/Tiger-Gemma-9B-v2
- GGUF: https://huggingface.co/TheDrummer/Tiger-Gemma-9B-v2-GGUF
What's New with v2?
It's a simple decensor but with a lighter touch, allowing it to be as Gemma as possible.
In memory of Tiger (the happy street cat on the right)
- Downloads last month
- 242
Hardware compatibility
Log In to add your hardware
2-bit
3-bit
4-bit
5-bit
6-bit
8-bit
16-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 TheDrummer/Tiger-Gemma-9B-v2-GGUF:# Run inference directly in the terminal: llama-cli -hf TheDrummer/Tiger-Gemma-9B-v2-GGUF: