Instructions to use AI-Engine/gemma-2-27b-it-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AI-Engine/gemma-2-27b-it-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="AI-Engine/gemma-2-27b-it-GGUF",
	filename="gemma-2-27b-it.IQ2_XS.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use AI-Engine/gemma-2-27b-it-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AI-Engine/gemma-2-27b-it-GGUF:IQ2_XS
# Run inference directly in the terminal:
llama-cli -hf AI-Engine/gemma-2-27b-it-GGUF:IQ2_XS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf AI-Engine/gemma-2-27b-it-GGUF:IQ2_XS
# Run inference directly in the terminal:
llama-cli -hf AI-Engine/gemma-2-27b-it-GGUF:IQ2_XS

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 AI-Engine/gemma-2-27b-it-GGUF:IQ2_XS
# Run inference directly in the terminal:
./llama-cli -hf AI-Engine/gemma-2-27b-it-GGUF:IQ2_XS

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 AI-Engine/gemma-2-27b-it-GGUF:IQ2_XS
# Run inference directly in the terminal:
./build/bin/llama-cli -hf AI-Engine/gemma-2-27b-it-GGUF:IQ2_XS

Use Docker

docker model run hf.co/AI-Engine/gemma-2-27b-it-GGUF:IQ2_XS

LM Studio
Jan
Ollama
How to use AI-Engine/gemma-2-27b-it-GGUF with Ollama:
```
ollama run hf.co/AI-Engine/gemma-2-27b-it-GGUF:IQ2_XS
```

Unsloth Studio

How to use AI-Engine/gemma-2-27b-it-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for AI-Engine/gemma-2-27b-it-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for AI-Engine/gemma-2-27b-it-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for AI-Engine/gemma-2-27b-it-GGUF to start chatting

Docker Model Runner
How to use AI-Engine/gemma-2-27b-it-GGUF with Docker Model Runner:
```
docker model run hf.co/AI-Engine/gemma-2-27b-it-GGUF:IQ2_XS
```

Lemonade

How to use AI-Engine/gemma-2-27b-it-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull AI-Engine/gemma-2-27b-it-GGUF:IQ2_XS

Run and chat with the model

lemonade run user.gemma-2-27b-it-GGUF-IQ2_XS

List all available models

lemonade list

AI-Engine commited on Jul 24, 2024

Commit

b7bcda5

verified ·

1 Parent(s): 0968947

Update README.md

Browse files

Files changed (1) hide show

README.md +20 -3

README.md CHANGED Viewed

@@ -1,3 +1,20 @@
----
-license: gemma
----

+---
+license: gemma
+base_model: google/gemma-2-27b-it
+---
+GGUF [llama.cpp](https://github.com/ggerganov/llama.cpp) quantized version of:
+- Original model: [gemma-2-27b-it](https://huggingface.co/google/gemma-2-27b-it)
+- Model creator: [Google](https://huggingface.co/google)
+- [License](https://www.kaggle.com/models/google/gemma/license/consent?verifyToken=CfDJ8OV3w-Vr_2dIpZxXY9wVZZnpWKdFS3kJvSU2XkwpfOZICBFcOxoYJFb12HJj1BQs9FHgrjqpbEoqYjxdMwgaew-eH8JJmsLOgj56rjNeDFWaxTA36ggVQ1RJsKmH0mbl74o1qgioqSV5ktl-J5ebL9ep3JmOojU1HdBDSScB6WyGDSIuAcw8MWuy9LEE74Ze)
+## Recommended Prompt Format (Gemma)
+```
+<start_of_turn>model
+Provide some context and/or instructions to the model.<end_of_turn>model
+<start_of_turn>user
+The user’s message goes here<end_of_turn>
+<start_of_turn>model
+AI message goes here<end_of_turn>model
+```
+Quant Version: [b3450](https://github.com/ggerganov/llama.cpp/releases/tag/b3450) with [imatrix](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384)