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

Libraries

How to use aws-neuron/SOLAR-10.7B-v1.0-neuron with Transformers:

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

pipe = pipeline("text-generation", model="aws-neuron/SOLAR-10.7B-v1.0-neuron")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aws-neuron/SOLAR-10.7B-v1.0-neuron with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/aws-neuron/SOLAR-10.7B-v1.0-neuron

SGLang

How to use aws-neuron/SOLAR-10.7B-v1.0-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/SOLAR-10.7B-v1.0-neuron" \
    --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": "aws-neuron/SOLAR-10.7B-v1.0-neuron",
		"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 "aws-neuron/SOLAR-10.7B-v1.0-neuron" \
        --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": "aws-neuron/SOLAR-10.7B-v1.0-neuron",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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

jburtoft commited on Jan 16, 2024

Commit

7147c40

verified ·

1 Parent(s): d6f9388

Update README.md

Browse files

removed download requirement

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -80,7 +80,7 @@ from optimum.neuron import NeuronModelForCausalLM
 #num_cores should be changed based on the instance.  inf2.24xlarge has 6 neuron processors (they have two cores each) so 12 total
 input_shapes = {"batch_size": 1, "sequence_length": 4096}
 compiler_args = {"num_cores": 8, "auto_cast_type": 'fp16'}
-model = NeuronModelForCausalLM.from_pretrained("SOLAR-10.7B-v1.0", export=True, **compiler_args, **input_shapes)
 model.save_pretrained("SOLAR-10.7B-v1.0-neuron-24xlarge-2.16-8core-4096")
 from transformers import AutoTokenizer

 #num_cores should be changed based on the instance.  inf2.24xlarge has 6 neuron processors (they have two cores each) so 12 total
 input_shapes = {"batch_size": 1, "sequence_length": 4096}
 compiler_args = {"num_cores": 8, "auto_cast_type": 'fp16'}
+model = NeuronModelForCausalLM.from_pretrained("upstage/SOLAR-10.7B-v1.0", export=True, **compiler_args, **input_shapes)
 model.save_pretrained("SOLAR-10.7B-v1.0-neuron-24xlarge-2.16-8core-4096")
 from transformers import AutoTokenizer