Instructions to use jburtoft/SOLAR-10.7B-v1.0-neuron-24xlarge-4096 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jburtoft/SOLAR-10.7B-v1.0-neuron-24xlarge-4096 with Transformers:

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

pipe = pipeline("text-generation", model="jburtoft/SOLAR-10.7B-v1.0-neuron-24xlarge-4096")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("jburtoft/SOLAR-10.7B-v1.0-neuron-24xlarge-4096")
model = AutoModelForCausalLM.from_pretrained("jburtoft/SOLAR-10.7B-v1.0-neuron-24xlarge-4096", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use jburtoft/SOLAR-10.7B-v1.0-neuron-24xlarge-4096 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "jburtoft/SOLAR-10.7B-v1.0-neuron-24xlarge-4096"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jburtoft/SOLAR-10.7B-v1.0-neuron-24xlarge-4096",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/jburtoft/SOLAR-10.7B-v1.0-neuron-24xlarge-4096

SGLang

How to use jburtoft/SOLAR-10.7B-v1.0-neuron-24xlarge-4096 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 "jburtoft/SOLAR-10.7B-v1.0-neuron-24xlarge-4096" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jburtoft/SOLAR-10.7B-v1.0-neuron-24xlarge-4096",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "jburtoft/SOLAR-10.7B-v1.0-neuron-24xlarge-4096" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jburtoft/SOLAR-10.7B-v1.0-neuron-24xlarge-4096",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use jburtoft/SOLAR-10.7B-v1.0-neuron-24xlarge-4096 with Docker Model Runner:
```
docker model run hf.co/jburtoft/SOLAR-10.7B-v1.0-neuron-24xlarge-4096
```

Neuronx model for upstage/SOLAR-10.7B-v1.0

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

This model card also includes instructions for how to compile other SOLAR models with other settings if this combination isn't quite what you are looking for.

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

It has been compiled to run on an inf2.24xlarge instance on AWS.

This has been compiled using version 2.16 of the Neuron SDK. Make sure your environment has version 2.16 installed

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

Set up the environment

First, use the DLAMI image from Hugging Face. It has most of the utilities and drivers preinstalled. However, you may need to update to version 2.16 to use these binaries.

sudo apt-get update -y \
 && sudo apt-get install -y --no-install-recommends \
    aws-neuronx-dkms=2.15.9.0 \
    aws-neuronx-collectives=2.19.7.0-530fb3064 \
    aws-neuronx-runtime-lib=2.19.5.0-97e2d271b \
    aws-neuronx-tools=2.16.1.0 

pip3 install --upgrade \
    neuronx-cc==2.12.54.0 \
    torch-neuronx==1.13.1.1.13.0 \
    transformers-neuronx==0.9.474 \
    --extra-index-url=https://pip.repos.neuron.amazonaws.com

pip3 install git+https://github.com/huggingface/optimum-neuron.git

Running inference from this repository

from optimum.neuron import pipeline
p = pipeline('text-generation', 'jburtoft/SOLAR-10.7B-v1.0-neuron-24xlarge-4096')
p("import socket\n\ndef ping_exponential_backoff(host: str):",
    do_sample=True,
    top_k=10,
    temperature=0.1,
    top_p=0.95,
    num_return_sequences=1,
    max_length=200,
)

[{generated text here}]

##Compiling for different instances or settings

If this repository doesn't have the exact version or settings, you can compile your own.

(to be added)

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": 1,
  "sequence_length": 4096,
}

compiler_args

{
  "auto_cast_type": "fp16",
  "num_cores": 12,
}

Downloads last month: 4