Instructions to use google/datagemma-rig-27b-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use google/datagemma-rig-27b-it with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("google/datagemma-rig-27b-it")
model = AutoModelForCausalLM.from_pretrained("google/datagemma-rig-27b-it")
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

vLLM

How to use google/datagemma-rig-27b-it with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/google/datagemma-rig-27b-it

SGLang

How to use google/datagemma-rig-27b-it 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 "google/datagemma-rig-27b-it" \
    --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": "google/datagemma-rig-27b-it",
		"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 "google/datagemma-rig-27b-it" \
        --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": "google/datagemma-rig-27b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use google/datagemma-rig-27b-it with Docker Model Runner:
```
docker model run hf.co/google/datagemma-rig-27b-it
```

Why the example prompt doesn't include prompt format?

by fahadh4ilyas - opened Oct 2, 2024

Discussion

fahadh4ilyas

Oct 2, 2024

From the example here:

from transformers import AutoTokenizer, AutoModelForCausalLM
import torch

model_id = 'google/datagemma-rig-27b-it'
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map='auto',
    torch_dtype=torch.bfloat16,
)

input_text = 'What are some interesting trends in Sunnyvale spanning gender, age, race, immigration, health conditions, economic conditions, crime and education?'
inputs = tokenizer(input_text, return_tensors='pt').to('cuda')

outputs = model.generate(**inputs, max_new_tokens=4096)
answer = tokenizer.batch_decode(outputs[:, inputs['input_ids'].shape[1]:], skip_special_tokens=True)[0].strip()
print(answer)

The input_text has no format. I thought it should be

input_text = '<bos><start_of_turn>user\nWhat are some interesting trends in Sunnyvale spanning gender, age, race, immigration, health conditions, economic conditions, crime and education?<end_of_turn>\n<start_of_turn>model\n'

So, what is the right input_text?

GopiUppari

Google org Oct 3, 2024

Hi @fahadh4ilyas ,

Without a Chat Template: This approach involves tokenizing the input text directly, without adding any context about roles or conversation structure. It’s simply a plain string without any explicit interaction framework.

With a Chat Template: This approach uses a chat template to assign roles and create a structured conversational context for the input. You can ensure the correct chat template is applied by using the tokenizer.apply_chat_template method.

Here’s an example that demonstrates the usage:

This ensures that the input is formatted according to the expected conversational structure when using models like instruction-tuned ones.

Thank you.

fahadh4ilyas

Oct 3, 2024

Will the response be different between input without chat template vs input with chat template? Which one is recommended to use?

GopiUppari

Google org Oct 3, 2024

Hi @fahadh4ilyas ,

Response is different. Go with chat template approach because it is more sophisticated and designed for conversations and tasks where roles and multi-turn dialogues are needed, while the standard tokenization is a basic approach suitable for one-off instructions. Could you please refer to this gist

Thank you.

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