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

Libraries

How to use NexaAI/octo-net with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("NexaAI/octo-net", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("NexaAI/octo-net", trust_remote_code=True)
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

vLLM

How to use NexaAI/octo-net with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "NexaAI/octo-net"
# 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/octo-net",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/NexaAI/octo-net

SGLang

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

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

End-to-End code sample / setup with 'Routing LLM' and 'Specialist LLMs'

by christianweyer - opened May 7, 2024

Discussion

christianweyer

May 7, 2024

We should have a sample / setup that illustrates how the actual weaving and routing is done when the 'routing LLM' answers, then we need to delegate to the 'specialist LLM' and come back.

huggingfacess

May 8, 2024

We should have a sample / setup that illustrates how the actual weaving and routing is done when the 'routing LLM' answers, then we need to delegate to the 'specialist LLM' and come back.

This model cannot directly give a specific model. It generates parameters for calling this function and needs to be used with Octopus v2.

zackli4ai

Nexa AI org May 22, 2024

Hi @huggingfacess @christianweyer Thanks for point this out, we have github code here:
https://github.com/NexaAI/octopus-v4

To be specific, all domain-specific LLMs are implemented here
https://github.com/NexaAI/octopus-v4/tree/main/specialized_models

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