Instructions to use HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1 with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1")
model = AutoModelForMultimodalLM.from_pretrained("HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1")
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 HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1

SGLang

How to use HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1 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 "HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1" \
    --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": "HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1",
		"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 "HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1" \
        --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": "HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1 with Docker Model Runner:
```
docker model run hf.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1
```

Prompt format

by sam-paech - opened Apr 12, 2024

Discussion

sam-paech

Apr 12, 2024

Was this trained with a specific prompt format?

mrjackspade

Apr 12, 2024

<|system|>
You are a helpful assistant.</s>
<|user|>
Hello, how are you?</s>
<|assistant|>
I'm doing great. How can I help you today?</s>
<|user|>
Show me how to build a website in 10 simple steps</s>
<|assistant|>

sam-paech

Apr 12, 2024

Thanks!

lewtun

Hugging Face H4 org Apr 12, 2024

The Jinja chat template is also part of the tokenizer if you need it: https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1/blob/4e5568b3b7428916cc30b38c94b282707ee5a48e/tokenizer_config.json#L32

sam-paech

Apr 12, 2024

The Jinja chat template is also part of the tokenizer if you need it: https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1/blob/4e5568b3b7428916cc30b38c94b282707ee5a48e/tokenizer_config.json#L32

Does the text-generation pipeline automatically apply the tokenizer's chat template when used as per the example code?

I thought it needed to be applied with tokenizer.apply_chat_template, but maybe I missed the memo.

lewtun

Hugging Face H4 org Apr 12, 2024

Yeah the pipeline now does this automatically! https://github.com/huggingface/transformers/blob/caa5c65db1f4db617cdac2ad667ba62edf94dd98/src/transformers/pipelines/text_generation.py#L253

Rocketknight1

Hugging Face H4 org Apr 13, 2024

To be specific, a chat template is applied if the input looks like a chat in the style of the OpenAI API (i.e. a list of dicts with role and content keys). If you pass a single string, the pipeline won't try to apply a chat template to it.

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