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

Libraries

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

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

pipe = pipeline("text-generation", model="SceneWorks/gemma-2-2b-it")
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("SceneWorks/gemma-2-2b-it")
model = AutoModelForCausalLM.from_pretrained("SceneWorks/gemma-2-2b-it", 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 SceneWorks/gemma-2-2b-it with vLLM:

Install from pip and serve model

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

Use Docker

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

SGLang

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

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

gemma-2-2b-it / NOTICE

SceneWorks

sc-8025: non-gated mirror of stock google/gemma-2-2b-it (PiD caption encoder) — Gemma Terms + Prohibited Use Policy shipped; README de-gated

684c553 verified 4 months ago

Raw History Blame Contribute Delete

1.09 kB

Gemma is provided under and subject to the Gemma Terms of Use found at
ai.google.dev/gemma/terms

----------------------------------------------------------------------
Gemma 2 2B IT — original model: Google (https://huggingface.co/google/gemma-2-2b-it)
Base model: google/gemma-2-2b
Copyright (c) Google LLC. All rights reserved.

This repository (SceneWorks/gemma-2-2b-it) is a NON-GATED MIRROR of the stock
google/gemma-2-2b-it weights, redistributed UNMODIFIED (no conversion, no
fine-tuning) under Gemma Terms of Use Section 3.1. It re-hosts the model solely
so the SceneWorks PiD pixel-diffusion decoder can provision its Gemma-2 caption
encoder in-app without a Gemma-gated download token.

Use and distribution of these weights and any Model Derivatives are subject to
the Gemma Terms of Use (LICENSE) and the use restrictions in Section 3.2 thereof,
including the Gemma Prohibited Use Policy (PROHIBITED_USE_POLICY.md). These
restrictions flow to downstream recipients: any further distribution must include
a copy of the Agreement and bind recipients to the same use restrictions.

	Gemma is provided under and subject to the Gemma Terms of Use found at
	ai.google.dev/gemma/terms

	----------------------------------------------------------------------
	Gemma 2 2B IT — original model: Google (https://huggingface.co/google/gemma-2-2b-it)
	Base model: google/gemma-2-2b
	Copyright (c) Google LLC. All rights reserved.

	This repository (SceneWorks/gemma-2-2b-it) is a NON-GATED MIRROR of the stock
	google/gemma-2-2b-it weights, redistributed UNMODIFIED (no conversion, no
	fine-tuning) under Gemma Terms of Use Section 3.1. It re-hosts the model solely
	so the SceneWorks PiD pixel-diffusion decoder can provision its Gemma-2 caption
	encoder in-app without a Gemma-gated download token.

	Use and distribution of these weights and any Model Derivatives are subject to
	the Gemma Terms of Use (LICENSE) and the use restrictions in Section 3.2 thereof,
	including the Gemma Prohibited Use Policy (PROHIBITED_USE_POLICY.md). These
	restrictions flow to downstream recipients: any further distribution must include
	a copy of the Agreement and bind recipients to the same use restrictions.