Instructions to use Amu/spin-phi2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Amu/spin-phi2 with Transformers:

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

pipe = pipeline("text-generation", model="Amu/spin-phi2", 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("Amu/spin-phi2", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Amu/spin-phi2", 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 Amu/spin-phi2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Amu/spin-phi2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Amu/spin-phi2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Amu/spin-phi2

SGLang

How to use Amu/spin-phi2 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 "Amu/spin-phi2" \
    --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": "Amu/spin-phi2",
		"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 "Amu/spin-phi2" \
        --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": "Amu/spin-phi2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Amu/spin-phi2 with Docker Model Runner:
```
docker model run hf.co/Amu/spin-phi2
```

Please ad finetune / chat model tag

by ThiloteE - opened Mar 16, 2024

Discussion

ThiloteE

Mar 16, 2024

Is this not a finetune? Why does it have the "pretrained" tag?
Please consider changing the tag as people might get the wrong idea. If I understand SPIN right, then this is NOT a "pretrained" model as defined by the leaderboard with "new, base models, trained on a given text corpora using masked modelling", as SPIN involves a reward function derived from a finetuning dataset, which in this case is the ultrachat_200k dataset. Instead, the chat model tag might fit better.

Amu

Owner Mar 16, 2024

Is this not a finetune? Why does it have the "pretrained" tag?
Please consider changing the tag as people might get the wrong idea. If I understand SPIN right, then this is NOT a "pretrained" model as defined by the leaderboard with "new, base models, trained on a given text corpora using masked modelling", as SPIN involves a reward function derived from a finetuning dataset, which in this case is the ultrachat_200k dataset. Instead, the chat model tag might fit better.

Hi, thanks for your advice. Do you know how how to change the tag? I try to resubmit to the llm leaderboard to change the tag. But it said that 'This model has been already submitted.'.

ThiloteE

Mar 16, 2024

•

edited Mar 16, 2024

You can open a pull-request to your models submitted to the leaderboard by modifying the request file via the "contribute" button: https://huggingface.co/datasets/open-llm-leaderboard/requests/tree/main/amu

Amu

Owner Mar 16, 2024

•

edited Mar 16, 2024

You can open a pull-request to your models submitted to the leaderboard by modifying the request file via the "contribute" button: https://huggingface.co/datasets/open-llm-leaderboard/requests/tree/main/amu

https://huggingface.co/datasets/open-llm-leaderboard/requests/discussions/84 I has opened a pr for it. It seems ok. Thank you again!

Amu changed discussion status to closed Mar 16, 2024

ThiloteE

Mar 16, 2024

Thank you and you are welcome :-)

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