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

Libraries

How to use bartowski/gemma-2-27b-it-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="bartowski/gemma-2-27b-it-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("bartowski/gemma-2-27b-it-GGUF", device_map="auto")

llama-cpp-python

How to use bartowski/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="bartowski/gemma-2-27b-it-GGUF",
	filename="gemma-2-27b-it-IQ2_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

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

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bartowski/gemma-2-27b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/gemma-2-27b-it-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf bartowski/gemma-2-27b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf bartowski/gemma-2-27b-it-GGUF:Q4_K_M

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 bartowski/gemma-2-27b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf bartowski/gemma-2-27b-it-GGUF:Q4_K_M

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 bartowski/gemma-2-27b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf bartowski/gemma-2-27b-it-GGUF:Q4_K_M

Use Docker

docker model run hf.co/bartowski/gemma-2-27b-it-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use bartowski/gemma-2-27b-it-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bartowski/gemma-2-27b-it-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bartowski/gemma-2-27b-it-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/bartowski/gemma-2-27b-it-GGUF:Q4_K_M

SGLang

How to use bartowski/gemma-2-27b-it-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "bartowski/gemma-2-27b-it-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bartowski/gemma-2-27b-it-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "bartowski/gemma-2-27b-it-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bartowski/gemma-2-27b-it-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use bartowski/gemma-2-27b-it-GGUF with Ollama:
```
ollama run hf.co/bartowski/gemma-2-27b-it-GGUF:Q4_K_M
```

Unsloth Studio

How to use bartowski/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 bartowski/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 bartowski/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 bartowski/gemma-2-27b-it-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use bartowski/gemma-2-27b-it-GGUF with Docker Model Runner:
```
docker model run hf.co/bartowski/gemma-2-27b-it-GGUF:Q4_K_M
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull bartowski/gemma-2-27b-it-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma-2-27b-it-GGUF-Q4_K_M

List all available models

lemonade list

'LlamaCppModel' object has no attribute 'model'

by DrNicefellow - opened Jun 28, 2024

Discussion

DrNicefellow

Jun 28, 2024

01:36:46-515173 ERROR Failed to load the model.
Traceback (most recent call last):
File "/workspace/text-generation-webui/modules/ui_model_menu.py", line 245, in load_model_wrapper
shared.model, shared.tokenizer = load_model(selected_model, loader)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/text-generation-webui/modules/models.py", line 94, in load_model
output = load_func_maploader
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/text-generation-webui/modules/models.py", line 272, in llamacpp_loader
model, tokenizer = LlamaCppModel.from_pretrained(model_file)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/workspace/text-generation-webui/modules/llamacpp_model.py", line 103, in from_pretrained
result.model = Llama(**params)
^^^^^^^^^^^^^^^
File "/workspace/text-generation-webui/installer_files/env/lib/python3.11/site-packages/llama_cpp_cuda/llama.py", line 358, in init
self._model = self._stack.enter_context(contextlib.closing(_LlamaModel(
^^^^^^^^^^^^
File "/workspace/text-generation-webui/installer_files/env/lib/python3.11/site-packages/llama_cpp_cuda/_internals.py", line 54, in init
raise ValueError(f"Failed to load model from file: {path_model}")
ValueError: Failed to load model from file: models/gemma-2-27b-it-Q4_K_M.gguf

Exception ignored in: <function LlamaCppModel.__del__ at 0x7f1d67294c20>
Traceback (most recent call last):
File "/workspace/text-generation-webui/modules/llamacpp_model.py", line 58, in del
del self.model
^^^^^^^^^^
AttributeError: 'LlamaCppModel' object has no attribute 'model'

bartowski

Owner Jun 28, 2024

support for this model was officially added to llama.cpp ~1 hour ago at the time of writing, so you may need to update after llama-cpp-python updates

Rotating

Jun 28, 2024

•

edited Jun 28, 2024

edit: i had a bad download

millionwords

Jun 28, 2024

I'm getting the same error with the latest version of llama-cpp-python.

llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'gemma2'
llama_load_model_from_file: failed to load model

salvik

Jun 28, 2024

Same for me using llama.cpp:

llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'gemma2'  
llama_load_model_from_file: failed to load model

I've also checked-out on the b3259 branch/tag:

salvik

Jun 28, 2024

•

edited Jun 28, 2024

Same for me using llama.cpp:

llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'gemma2'  
llama_load_model_from_file: failed to load model

I've also checked-out on the b3259 branch/tag:

The llama.cpp package has changed, now you have to use ./llama-cli instead of the main binary.
Now it works correctly.

millionwords

Jun 28, 2024

•

edited Jun 28, 2024

I ran the ./llama-cli getting same error.

Can you provide some instructions on how you are doing it?

salvik

Jun 28, 2024

I ran the ./llama-cli getting same error.

Do you have the up-to-date version of llama.cpp? The Gemma2 support was added few hours ago

millionwords

Jun 28, 2024

I do. It doesn't work for me :(

eamag

Jun 28, 2024

Try to do git pull make clean and rebuild your llama.cpp. I think you're using the old version

bartowski

Owner Jun 28, 2024

Yeah it's working for me with llama.cpp ./llama-cli so something must be broken in your local set up D:

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment