Instructions to use NexaAI/Octopus-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NexaAI/Octopus-v2 with Transformers:

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

pipe = pipeline("text-generation", model="NexaAI/Octopus-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NexaAI/Octopus-v2")
model = AutoModelForCausalLM.from_pretrained("NexaAI/Octopus-v2")
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 NexaAI/Octopus-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NexaAI/Octopus-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "NexaAI/Octopus-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NexaAI/Octopus-v2

SGLang

How to use NexaAI/Octopus-v2 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 "NexaAI/Octopus-v2" \
    --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": "NexaAI/Octopus-v2",
		"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 "NexaAI/Octopus-v2" \
        --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": "NexaAI/Octopus-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use NexaAI/Octopus-v2 with Docker Model Runner:
```
docker model run hf.co/NexaAI/Octopus-v2
```

execute in the video demo

#13

by AcceleratedNpc - opened Apr 12, 2024

Discussion

AcceleratedNpc

Apr 12, 2024

Glad to see such an amazing work!
Wanna know whether the execute script in video demo will be released.
Some other detailed code is also expected.
Will you release more example code for use on Android device. If so, when?
Thanks again for your wonderful work.

AcceleratedNpc

Apr 12, 2024

I have tried the example provided by the team and got a result with a latency 20.7s.
Wanna know the latency examed on your device so that the accerated model inference mentioned in paper can be felt directly.
Looking forward to your reply.

alexchen4ai

Nexa AI org Apr 13, 2024

Language model has many optimizations like KV cache, quantization, model pruning, specific memory access pattern, etc... Try to use these tricks

Or, you can join our waitlist: https://www.nexa4ai.com/contact, and we will give solutions for the above.

zackli4ai

Nexa AI org May 6, 2024

•

edited May 6, 2024

@AcceleratedNpc Which GPU are you using? Also, please implement early stopping criteria. Once you observe , the inference can stop

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