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

Libraries

How to use ModelCloud/gemma-2-27b-it-gptq-4bit with Transformers:

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

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

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ModelCloud/gemma-2-27b-it-gptq-4bit")
model = AutoModelForCausalLM.from_pretrained("ModelCloud/gemma-2-27b-it-gptq-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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ModelCloud/gemma-2-27b-it-gptq-4bit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ModelCloud/gemma-2-27b-it-gptq-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": "ModelCloud/gemma-2-27b-it-gptq-4bit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ModelCloud/gemma-2-27b-it-gptq-4bit

SGLang

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

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

This model has been quantized using GPTQModel.

bits: 4
group_size: 128
desc_act: true
static_groups: false
sym: true
lm_head: false
damp_percent: 0.01
true_sequential: true
model_name_or_path: ""
model_file_base_name: "model"
quant_method: "gptq"
checkpoint_format: "gptq"
meta：
- quantizer: "gptqmodel:0.9.9-dev0"

Currently, only vllm can load the quantized gemma2-27b for proper inference. Here is an example:

import os
# Gemma-2 use Flashinfer backend for models with logits_soft_cap. Otherwise, the output might be wrong.
os.environ['VLLM_ATTENTION_BACKEND'] = 'FLASHINFER'

from transformers import AutoTokenizer
from gptqmodel import BACKEND, GPTQModel

model_name = "ModelCloud/gemma-2-27b-it-gptq-4bit"

prompt = [{"role": "user", "content": "I am in Shanghai, preparing to visit the natural history museum. Can you tell me the best way to"}]

tokenizer = AutoTokenizer.from_pretrained(model_name)

model = GPTQModel.from_quantized(
            model_name,
            backend=BACKEND.VLLM,
        )

inputs = tokenizer.apply_chat_template(prompt, tokenize=False, add_generation_prompt=True)
outputs = model.generate(prompts=inputs, temperature=0.95, max_length=128)
print(outputs[0].outputs[0].text)

Downloads last month: 89

Safetensors

Model size

28B params

Tensor type

I32

BF16