Instructions to use google/gemma-1.1-2b-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use google/gemma-1.1-2b-it with Transformers:

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

pipe = pipeline("text-generation", model="google/gemma-1.1-2b-it")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("google/gemma-1.1-2b-it")
model = AutoModelForCausalLM.from_pretrained("google/gemma-1.1-2b-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/gemma-1.1-2b-it with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "google/gemma-1.1-2b-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-1.1-2b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/google/gemma-1.1-2b-it

SGLang

How to use google/gemma-1.1-2b-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-1.1-2b-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-1.1-2b-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-1.1-2b-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-1.1-2b-it",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use google/gemma-1.1-2b-it with Docker Model Runner:
```
docker model run hf.co/google/gemma-1.1-2b-it
```

testing streaming pipeline

#14

by not-lain - opened Apr 25, 2024

base: refs/heads/main

←

from: refs/pr/14

Discussion Files changed

+312

-8

testing streaming pipeline07397dce

not-lain

Apr 25, 2024

No description provided.

not-lain

Apr 25, 2024

how to use

import gradio as gr
from transformers import pipeline

pipe = pipeline("text-generation", model="google/gemma-1.1-2b-it", revision="refs/pr/14",trust_remote_code=True) # trust here

def talk(prompt,history=[]):
  yield from pipe(prompt,history=history,stream=True,max_new_tokens=50) # use yield from

demo = gr.ChatInterface(fn=talk,
    chatbot=gr.Chatbot(),
    examples=[["hi",[]]],
    cache_examples=False,
    title="Streaming")
demo.launch(debug=True)

else you can format the prompt outside and pass it to the pipeline

not-lain

Apr 25, 2024

examples without gradio

from transformers import pipeline

pipe = pipeline("text-generation", model="google/gemma-1.1-2b-it", revision="refs/pr/14",trust_remote_code=True) 
text  = "hello" # or you can apply your chat template and feed everything as a singleton parameter named prompt
s = pipe(prompt = text,stream=True,max_new_tokens=50)
for i in s : 
    print(i)

from transformers import pipeline

pipe = pipeline("text-generation", model="google/gemma-1.1-2b-it", revision="refs/pr/14",trust_remote_code=True) 
text = pipe(prompt,max_new_tokens=50)
print(text)

switch to builtin pipeline device parameter9d136f0c

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment