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

Libraries

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

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

pipe = pipeline("text-generation", model="rubra-ai/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("rubra-ai/gemma-1.1-2b-it")
model = AutoModelForCausalLM.from_pretrained("rubra-ai/gemma-1.1-2b-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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

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

Use Docker

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

SGLang

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

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

sanjay920 commited on Jun 30, 2024

Commit

297e4fe

verified ·

1 Parent(s): 19f1f63

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -61,10 +61,10 @@ language:
 # Gemma-1.1-2B-IT
 ## Model Description
-Gemma-1.1-2B-IT is the result of post-training on the base model [google/gemma-1.1-2b-it](https://huggingface.co/google/gemma-1.1-2b-it). This model excels in various instruct tasks, including function calling and complex chat scenarios.
-## Training
-The model was further trained using a proprietary dataset that includes diverse instruction-following, function calling, and conversational data. This post-training enhances its capabilities in tool integration and complex interactions.
 ## How to Use

 # Gemma-1.1-2B-IT
 ## Model Description
+Gemma-1.1-2B-IT is the result of post-training on the base model [google/gemma-1.1-2b-it](https://huggingface.co/google/gemma-1.1-2b-it). This model is designed for high performance in various instruction-following tasks and complex interactions, including multi-turn function calling and detailed conversations.
+## Training Data
+The model underwent additional training on a proprietary dataset encompassing diverse instruction-following, chat, and function calling data. This post-training process enhances the model's ability to integrate tools and manage complex interaction scenarios effectively.
 ## How to Use