Instructions to use unsloth/gemma-2-27b-it-bnb-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/gemma-2-27b-it-bnb-4bit with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/gemma-2-27b-it-bnb-4bit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/gemma-2-27b-it-bnb-4bit")
model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-2-27b-it-bnb-4bit", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use unsloth/gemma-2-27b-it-bnb-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/gemma-2-27b-it-bnb-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/gemma-2-27b-it-bnb-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/gemma-2-27b-it-bnb-4bit

SGLang

How to use unsloth/gemma-2-27b-it-bnb-4bit 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 "unsloth/gemma-2-27b-it-bnb-4bit" \
    --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": "unsloth/gemma-2-27b-it-bnb-4bit",
		"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 "unsloth/gemma-2-27b-it-bnb-4bit" \
        --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": "unsloth/gemma-2-27b-it-bnb-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio

How to use unsloth/gemma-2-27b-it-bnb-4bit 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 unsloth/gemma-2-27b-it-bnb-4bit 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 unsloth/gemma-2-27b-it-bnb-4bit to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/gemma-2-27b-it-bnb-4bit to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="unsloth/gemma-2-27b-it-bnb-4bit",
    max_seq_length=2048,
)

Docker Model Runner
How to use unsloth/gemma-2-27b-it-bnb-4bit with Docker Model Runner:
```
docker model run hf.co/unsloth/gemma-2-27b-it-bnb-4bit
```

How to create gguf fromm this

by DerErnst - opened Aug 10, 2024

Discussion

DerErnst

Aug 10, 2024

Hi there, how can irun this llm in ollama Server? Tried to convert it to gguf with llama.cpp without success. How can i use it? Thanks in advance

gghfez

Aug 10, 2024

This is a special 4-bit quant for finetuning with unsloth. If you just want to run gemma-2-27b-it in ollama, you'd probably just do this and let ollama download it from their repository for you:

ollama run gemma2:27b

If you do in fact want to build your own .gguf file locally with llamacpp, use this one instead:
https://huggingface.co/unsloth/gemma-2-27b-it

That being said, you can also just get a gguf someone else has made
https://huggingface.co/bartowski/gemma-2-27b-it-GGUF

One final option is to have huggingface built you a gguff file:
https://huggingface.co/spaces/ggml-org/gguf-my-repo

DerErnst

Aug 10, 2024

Thanks a lot for your reply.
I´m heaving trouble runnig the normal gemma2-27b. it is realy slow... so i found this model. A read that is is faster than the normal on? Or i sonly the training faster with unsloth? I do not need extra training at the moment.. just want to run the 27b in higher speed with more token/s than now...

Thanks so much.

shimmyshimmer

Unsloth AI org Aug 10, 2024

Thanks a lot for your reply.
I´m heaving trouble runnig the normal gemma2-27b. it is realy slow... so i found this model. A read that is is faster than the normal on? Or i sonly the training faster with unsloth? I do not need extra training at the moment.. just want to run the 27b in higher speed with more token/s than now...

Thanks so much.

It's only faster because it is 4bit quantized which is unrelated to unsloth. GGUF cannot be in 4bit so the best option you have is to use Bartowski's upload.

We do make training and inference of models faster however but currently our inference only works with GPUs.

DerErnst

Aug 11, 2024

Ok, thanks for making things clear to me :) i'll give an other ready to use gguff with 4 bit quant a chance.

shimmyshimmer

Unsloth AI org Aug 11, 2024

Ok, thanks for making things clear to me :) i'll give an other ready to use gguff with 4 bit quant a chance.

When you finetune a model with Unsloth remember you can also directly export it to GGUF using Unsloth!

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