Instructions to use unsloth/gemma-7b-bnb-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/gemma-7b-bnb-4bit with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/gemma-7b-bnb-4bit", device_map="auto")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/gemma-7b-bnb-4bit")
model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-7b-bnb-4bit", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use unsloth/gemma-7b-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-7b-bnb-4bit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/gemma-7b-bnb-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/unsloth/gemma-7b-bnb-4bit

SGLang

How to use unsloth/gemma-7b-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-7b-bnb-4bit" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/gemma-7b-bnb-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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-7b-bnb-4bit" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/gemma-7b-bnb-4bit",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio

How to use unsloth/gemma-7b-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-7b-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-7b-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-7b-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-7b-bnb-4bit",
    max_seq_length=2048,
)

Docker Model Runner
How to use unsloth/gemma-7b-bnb-4bit with Docker Model Runner:
```
docker model run hf.co/unsloth/gemma-7b-bnb-4bit
```

No module named 'triton'

by NeelM0906 - opened Sep 13, 2024

Discussion

NeelM0906

Sep 13, 2024

Hi! Was loading up unsloth/gemma-7b-bnb-4bit and came across the following:

"""
ModuleNotFoundError Traceback (most recent call last)
in <cell line: 1>()
----> 1 from unsloth import FastLanguageModel
2 import torch
3 max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!
4 dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+
5 load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.

/usr/local/lib/python3.10/dist-packages/unsloth/init.py in
99 if "SPACE_AUTHOR_NAME" not in os.environ and "SPACE_REPO_NAME" not in os.environ:
100
--> 101 import triton
102 libcuda_dirs = lambda: None
103 if Version(triton.version) >= Version("3.0.0"):

ModuleNotFoundError: No module named 'triton'
"""

Was solved by:

"""
!pip install --no-deps xformers "trl<0.9.0" peft accelerate bitsandbytes triton
"""

danielhanchen

Unsloth AI org Sep 13, 2024

Oh sorry on the issue - we updated the installation instructions:

%%capture
# Installs Unsloth, Xformers (Flash Attention) and all other packages!
!pip install "unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git"

# We have to check which Torch version for Xformers (2.3 -> 0.0.27)
from torch import __version__; from packaging.version import Version as V
xformers = "xformers==0.0.27" if V(__version__) < V("2.4.0") else "xformers"
!pip install --no-deps {xformers} trl peft accelerate bitsandbytes triton

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