Instructions to use Thytu/phi-2-audio-super with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Thytu/phi-2-audio-super with Transformers:

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

pipe = pipeline("text-generation", model="Thytu/phi-2-audio-super", 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("Thytu/phi-2-audio-super", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Thytu/phi-2-audio-super", 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 Settings

vLLM

How to use Thytu/phi-2-audio-super with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Thytu/phi-2-audio-super"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Thytu/phi-2-audio-super",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Thytu/phi-2-audio-super

SGLang

How to use Thytu/phi-2-audio-super 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 "Thytu/phi-2-audio-super" \
    --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": "Thytu/phi-2-audio-super",
		"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 "Thytu/phi-2-audio-super" \
        --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": "Thytu/phi-2-audio-super",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Thytu/phi-2-audio-super with Docker Model Runner:
```
docker model run hf.co/Thytu/phi-2-audio-super
```

phi-2-audio-super

Commit History

Upload tokenizer

a150852
verified

Thytu commited on Mar 31, 2024

Upload PhiForCausalLM

54e82d8
verified

Thytu commited on Mar 31, 2024

Upload tokenizer

7f65600
verified

Thytu commited on Mar 30, 2024

Upload PhiForCausalLM

8852749
verified

Thytu commited on Mar 30, 2024

Upload tokenizer

621a1e9
verified

Thytu commited on Mar 30, 2024

Upload PhiForCausalLM

88a34e2
verified

Thytu commited on Mar 30, 2024

Upload tokenizer

806c9c4
verified

Thytu commited on Mar 29, 2024

Upload PhiForCausalLM

f6bc454
verified

Thytu commited on Mar 29, 2024

Upload tokenizer

4a68d70
verified

Thytu commited on Mar 15, 2024

Upload PhiForCausalLM

de9387e
verified

Thytu commited on Mar 15, 2024

Update README.md

b599b90
verified

Thytu commited on Mar 14, 2024

Upload tokenizer

ba088cb
verified

Thytu commited on Mar 14, 2024