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

Libraries

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

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

tokenizer_config.json is different from gemma-2-2b-it

by dahara1 - opened Oct 4, 2024

Discussion

dahara1

Oct 4, 2024

Hello! Thank you for the great model.

By the way, regarding the title, I'm particularly concerned that the following doesn't exist. Is this okay?

"additional_special_tokens": [
"<start_of_turn>",
"<end_of_turn>"
],

ArthurZ

Oct 4, 2024

Don't worry, info about special tokens is stored at the AddedToken level itself, can be ignored!

dahara1

Oct 10, 2024

Thank you for checking, it worked.
Thanks to you, I was able to release a finetuned model for translation tasks. The quality varies greatly depending on the writing style, but I feel that the performance is close to that of the 7B model from a year ago.

https://huggingface.co/webbigdata/gemma-2-2b-jpn-it-translate

dahara1 changed discussion status to closed Oct 16, 2024

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