Instructions to use asedmammad/gemma-7b-it-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use asedmammad/gemma-7b-it-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="asedmammad/gemma-7b-it-GGUF",
	filename="gemma-7b-it.q2_K.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use asedmammad/gemma-7b-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 asedmammad/gemma-7b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf asedmammad/gemma-7b-it-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf asedmammad/gemma-7b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf asedmammad/gemma-7b-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 asedmammad/gemma-7b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf asedmammad/gemma-7b-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 asedmammad/gemma-7b-it-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf asedmammad/gemma-7b-it-GGUF:Q4_K_M

Use Docker

docker model run hf.co/asedmammad/gemma-7b-it-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use asedmammad/gemma-7b-it-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "asedmammad/gemma-7b-it-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "asedmammad/gemma-7b-it-GGUF",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/asedmammad/gemma-7b-it-GGUF:Q4_K_M

Ollama
How to use asedmammad/gemma-7b-it-GGUF with Ollama:
```
ollama run hf.co/asedmammad/gemma-7b-it-GGUF:Q4_K_M
```

Unsloth Studio new

How to use asedmammad/gemma-7b-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 asedmammad/gemma-7b-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 asedmammad/gemma-7b-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 asedmammad/gemma-7b-it-GGUF to start chatting

Docker Model Runner
How to use asedmammad/gemma-7b-it-GGUF with Docker Model Runner:
```
docker model run hf.co/asedmammad/gemma-7b-it-GGUF:Q4_K_M
```

Lemonade

How to use asedmammad/gemma-7b-it-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull asedmammad/gemma-7b-it-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma-7b-it-GGUF-Q4_K_M

List all available models

lemonade list

Google's Gemma-7b-it GGUF

These files are GGUF format model files for Google's Gemma-7b-it.

GGUF files are for CPU + GPU inference using llama.cpp and libraries and UIs which support this format, such as:

How to run in `llama.cpp`

I use the following command line, adjust for your tastes and needs:

./main -t 2 -ngl 28 -m gemma-7b-it.q4_K_M.gguf -p '<start_of_turn>user\nWhat is love?\n<end_of_turn>\n<start_of_turn>model\n' --no-penalize-nl -e --color --temp 0.95 -c 1024 -n 512 --repeat_penalty 1.2 --top_p 0.95 --top_k 50

Change -t 2 to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use -t 8.

Change -ngl 28 to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.

If you want to have a chat-style conversation, replace the -p <PROMPT> argument with -i -ins, you can use --interactive-first to start in interactive mode:

./main -t 2 -ngl 28 -m gemma-7b-it.q4_K_M.gguf --in-prefix '<start_of_turn>user\n' --in-suffix '<end_of_turn>\n<start_of_turn>model\n' -i -ins --no-penalize-nl -e --color --temp 0.95 -c 1024 -n 512 --repeat_penalty 1.2 --top_p 0.95 --top_k 50

Compatibility

I have uploded both the original llama.cpp quant methods (q4_0, q4_1, q5_0, q5_1, q8_0) as well as the k-quant methods (q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K).

Please refer to llama.cpp and TheBloke's GGUF models for further explanation.

How to run in `text-generation-webui`

Further instructions here: text-generation-webui/docs/llama.cpp-models.md.

Thanks

Thanks to Google for providing checkpoints of the model.

Thanks to Georgi Gerganov and all of the awesome people in the AI community.

Downloads last month: 142

GGUF

Model size

9B params

Architecture

gemma

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

Google's Gemma-7b-it GGUF

How to run in llama.cpp

Compatibility

How to run in text-generation-webui

Thanks

How to run in `llama.cpp`

How to run in `text-generation-webui`