Instructions to use aws-neuron/zephyr-7b-seqlen-2048-bs-4-cores-2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aws-neuron/zephyr-7b-seqlen-2048-bs-4-cores-2 with Transformers:

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

pipe = pipeline("text-generation", model="aws-neuron/zephyr-7b-seqlen-2048-bs-4-cores-2")
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-seqlen-2048-bs-4-cores-2")
model = AutoModelForCausalLM.from_pretrained("aws-neuron/zephyr-7b-seqlen-2048-bs-4-cores-2")
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 aws-neuron/zephyr-7b-seqlen-2048-bs-4-cores-2 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-seqlen-2048-bs-4-cores-2"
# 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-seqlen-2048-bs-4-cores-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aws-neuron/zephyr-7b-seqlen-2048-bs-4-cores-2

SGLang

How to use aws-neuron/zephyr-7b-seqlen-2048-bs-4-cores-2 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-seqlen-2048-bs-4-cores-2" \
    --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-seqlen-2048-bs-4-cores-2",
		"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-seqlen-2048-bs-4-cores-2" \
        --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-seqlen-2048-bs-4-cores-2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aws-neuron/zephyr-7b-seqlen-2048-bs-4-cores-2 with Docker Model Runner:
```
docker model run hf.co/aws-neuron/zephyr-7b-seqlen-2048-bs-4-cores-2
```

Neuronx model for Zephyr 7B β

This repository contains AWS Inferentia2 and neuronx compatible checkpoints for HuggingFaceH4/zephyr-7b-beta. You can find detailed information about the base model on its Model Card.

This model has been exported to the neuron format using specific input_shapes and compiler parameters detailed in the paragraphs below.

Please refer to the 🤗 optimum-neuron documentation for an explanation of these parameters.

Usage on Amazon SageMaker

coming soon

Usage with 🤗 `optimum-neuron`

from optimum.neuron import pipeline

pipe = pipeline('text-generation', 'aws-neuron/zephyr-7b-seqlen-2048-bs-4-cores-2')
# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
messages = [
    {
        "role": "system",
        "content": "You are a friendly chatbot who always responds in the style of a pirate",
    },
    {"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
]
prompt = pipe.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
outputs = pipe(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
print(outputs[0]["generated_text"])

This repository contains tags specific to versions of neuronx. When using with 🤗 optimum-neuron, use the repo revision specific to the version of neuronx you are using, to load the right serialized checkpoints.

Arguments passed during export

input_shapes

{
  "batch_size": 4,
  "sequence_length": 2048,
}

compiler_args

{
  "auto_cast_type": "fp16",
  "num_cores": 2,
}

Downloads last month: 32

Model tree for aws-neuron/zephyr-7b-seqlen-2048-bs-4-cores-2

Base model

mistralai/Mistral-7B-v0.1

Finetuned

(926)

this model

Datasets used to train aws-neuron/zephyr-7b-seqlen-2048-bs-4-cores-2

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

62.031
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

84.356
f1 score on Drop (3-Shot)
validation set Open LLM Leaderboard

9.662
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

57.449
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

12.737
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

61.070
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

77.743
win rate on AlpacaEval
source

0.906