Instructions to use aws-neuron/zephyr-7b-beta-neuron with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aws-neuron/zephyr-7b-beta-neuron with Transformers:

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

pipe = pipeline("text-generation", model="aws-neuron/zephyr-7b-beta-neuron")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aws-neuron/zephyr-7b-beta-neuron")
model = AutoModelForCausalLM.from_pretrained("aws-neuron/zephyr-7b-beta-neuron")
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 aws-neuron/zephyr-7b-beta-neuron with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aws-neuron/zephyr-7b-beta-neuron"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aws-neuron/zephyr-7b-beta-neuron",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aws-neuron/zephyr-7b-beta-neuron

SGLang

How to use aws-neuron/zephyr-7b-beta-neuron 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 "aws-neuron/zephyr-7b-beta-neuron" \
    --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": "aws-neuron/zephyr-7b-beta-neuron",
		"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 "aws-neuron/zephyr-7b-beta-neuron" \
        --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": "aws-neuron/zephyr-7b-beta-neuron",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aws-neuron/zephyr-7b-beta-neuron with Docker Model Runner:
```
docker model run hf.co/aws-neuron/zephyr-7b-beta-neuron
```

ritikk commited on Jan 10, 2024

Commit

0fd11b5

1 Parent(s): eef9145

updated to use huggingface-cli

Browse files

Files changed (1) hide show

README.md +6 -4

README.md CHANGED Viewed

@@ -56,12 +56,14 @@ If you want to run a quick test or if the exact model you want to use is [Huggin
 First, you will need a local copy of the library.  This is because one of the nice things that the Hugging Face optimum library does is abstract local loads from repository loads.  However, Mistral inference isn't supported yet.
-From python:
 ```
-# using python instead of git clone because I know this supports lfs on the DLAMI image
-from huggingface_hub import Repository
-repo = Repository(local_dir="zephyr-7b-beta-neuron", clone_from="ritikk/zephyr-7b-beta-neuron")
 ```

 First, you will need a local copy of the library.  This is because one of the nice things that the Hugging Face optimum library does is abstract local loads from repository loads.  However, Mistral inference isn't supported yet.
 ```
+# To speed up downloads we can use hf_transfer
+pip install hf_transfer
+HF_HUB_ENABLE_HF_TRANSFER=1
+# use huggingface-cli to download model to local dir
+huggingface-cli download ritikk/zephyr-7b-beta-neuron --local-dir zephyr-7b-beta-neuron
 ```