Instructions to use typhoon-ai/llama3.1-typhoon2-audio-8b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use typhoon-ai/llama3.1-typhoon2-audio-8b-instruct with Transformers:

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

pipe = pipeline("text-generation", model="typhoon-ai/llama3.1-typhoon2-audio-8b-instruct", trust_remote_code=True)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("typhoon-ai/llama3.1-typhoon2-audio-8b-instruct", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use typhoon-ai/llama3.1-typhoon2-audio-8b-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "typhoon-ai/llama3.1-typhoon2-audio-8b-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "typhoon-ai/llama3.1-typhoon2-audio-8b-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/typhoon-ai/llama3.1-typhoon2-audio-8b-instruct

SGLang

How to use typhoon-ai/llama3.1-typhoon2-audio-8b-instruct 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 "typhoon-ai/llama3.1-typhoon2-audio-8b-instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "typhoon-ai/llama3.1-typhoon2-audio-8b-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "typhoon-ai/llama3.1-typhoon2-audio-8b-instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "typhoon-ai/llama3.1-typhoon2-audio-8b-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use typhoon-ai/llama3.1-typhoon2-audio-8b-instruct with Docker Model Runner:
```
docker model run hf.co/typhoon-ai/llama3.1-typhoon2-audio-8b-instruct
```

ImportError: cannot import name 'is_quanto_available' from 'transformers.generation.utils'

by tzsoulcap - opened Jan 2, 2025

Discussion

tzsoulcap

Jan 2, 2025

Please help, I found error when i load model

ImportError: cannot import name 'is_quanto_available' from 'transformers.generation.utils'

my venv
python=3.11.9
transformers=4.47.1

tzsoulcap

Jan 2, 2025

i try downgrade transformers to 4.46.3 its work!

kunato

Typhoon org Jan 6, 2025

Thank you for pointing that out.
We have not specified the version of transformers we used.
It's now added to the readme.

kunato changed discussion status to closed Jan 6, 2025

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