Instructions to use CohereLabs/tiny-aya-earth with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CohereLabs/tiny-aya-earth with Transformers:

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

pipe = pipeline("text-generation", model="CohereLabs/tiny-aya-earth")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CohereLabs/tiny-aya-earth")
model = AutoModelForCausalLM.from_pretrained("CohereLabs/tiny-aya-earth")
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
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use CohereLabs/tiny-aya-earth with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CohereLabs/tiny-aya-earth"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CohereLabs/tiny-aya-earth",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CohereLabs/tiny-aya-earth

SGLang

How to use CohereLabs/tiny-aya-earth 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 "CohereLabs/tiny-aya-earth" \
    --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": "CohereLabs/tiny-aya-earth",
		"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 "CohereLabs/tiny-aya-earth" \
        --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": "CohereLabs/tiny-aya-earth",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CohereLabs/tiny-aya-earth with Docker Model Runner:
```
docker model run hf.co/CohereLabs/tiny-aya-earth
```

how can i test this model?

by devops724 - opened Feb 18

Discussion

devops724

Feb 18

Hi,
Thanks for this great model,
i found this space
https://huggingface.co/spaces/CohereLabs/tiny-aya
but i don't know which version of tiny-aya hosted,
i want find a place test tiny-aya-earth
best regards

alexrs

Cohere Labs org Feb 18

Hey @devops724

The space currently hosts https://huggingface.co/CohereLabs/tiny-aya-global. You can download the tiny-aya-earth and run them on your computer, either the full version, or the quantized version -- https://huggingface.co/models?other=base_model:quantized:CohereLabs/tiny-aya-earth

We might offer the earth and other variants in the space in the future. However, the global version hosted is almost as good on most languages and should give you close enough experience to what you can get with the earth variant!

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