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

Libraries

How to use google/gemma-2-27b-it with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("google/gemma-2-27b-it")
model = AutoModelForCausalLM.from_pretrained("google/gemma-2-27b-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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use google/gemma-2-27b-it with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/google/gemma-2-27b-it

SGLang

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

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

Build Real-Time Conversational Agents with 56+ Models via NexaAPI (Gemini Flash Alternative)

#44

by nickyni - opened Mar 26

Discussion

nickyni

Mar 26

Build Real-Time Conversational Agents with 56+ Models via NexaAPI

Inspired by Google's Gemini 2.5 Flash Live API launch — here's how to build the same real-time conversational agent with access to GPT-4o, Claude, Llama, and 56+ models via one unified API.

Quick Start

from openai import OpenAI

# One line change from OpenAI SDK — same code, 56+ models
client = OpenAI(
    api_key="YOUR_NEXA_API_KEY",
    base_url="https://api.nexaapi.com/v1"
)

# Streaming conversational agent
stream = client.chat.completions.create(
    model="gpt-4o",  # swap: claude-3-5-sonnet, llama-3.3-70b, mistral-large...
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello! Tell me about real-time AI."}
    ],
    stream=True,
    max_tokens=300
)

for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="", flush=True)

Model Switcher — One Line Change

# Try different models with identical code:
for model in ["gpt-4o", "claude-3-5-sonnet-20241022", "llama-3.3-70b-instruct"]:
    response = client.chat.completions.create(
        model=model,  # ← only this line changes
        messages=[{"role": "user", "content": "What makes a great conversational AI?"}],
        max_tokens=100
    )
    print(f"{model}: {response.choices[0].message.content[:150]}")

Pricing Comparison

Provider	GPT-4o	Claude 3.5	Llama 3.3
Official	$2.50/M tokens	$3.00/M tokens	N/A
NexaAPI	Up to 5× cheaper	Up to 5× cheaper	Cheapest

Resources

🌐 NexaAPI: https://nexa-api.com (free tier, no credit card)
🐙 GitHub: https://github.com/diwushennian4955/realtime-conversational-agent-nexaapi
📖 Blog: https://nexa-api.com/blog/gemini-live-conversational-agent-nexaapi
📓 Colab: Full notebook with model comparison and cost estimator

sonali-kumari11

Google org Apr 7

Hi @nickyni -

Thank you for sharing this with the community. This is a well-structured and practical showcase, and the unified API approach is particularly compelling.

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