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

Libraries

How to use aws-neuron/Mistral-neuron with Transformers:

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

pipe = pipeline("text-generation", model="aws-neuron/Mistral-neuron")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aws-neuron/Mistral-neuron")
model = AutoModelForCausalLM.from_pretrained("aws-neuron/Mistral-neuron")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use aws-neuron/Mistral-neuron with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aws-neuron/Mistral-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/Mistral-neuron",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/aws-neuron/Mistral-neuron

SGLang

How to use aws-neuron/Mistral-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/Mistral-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/Mistral-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/Mistral-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/Mistral-neuron",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use aws-neuron/Mistral-neuron with Docker Model Runner:
```
docker model run hf.co/aws-neuron/Mistral-neuron
```

jburtoft commited on Jan 3, 2024

Commit

93c4487

1 Parent(s): 676a38b

c0a45033090c34ed8366c605b008f075e04fb5c70d5cfc607d85b1f567575a24

Browse files

Files changed (4) hide show

pytorch_model.bin/p96.model.layers.10.mlp.up_proj.weight +3 -0
pytorch_model.bin/p97.model.layers.10.mlp.down_proj.weight +3 -0
pytorch_model.bin/p98.model.layers.10.input_layernorm.weight +3 -0
pytorch_model.bin/p99.model.layers.10.post_attention_layernorm.weight +3 -0

pytorch_model.bin/p96.model.layers.10.mlp.up_proj.weight ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d592447f3143d50a54c107ac8cc5f8352fc0f3978db5b204047e83358d500225
+size 234881907

pytorch_model.bin/p97.model.layers.10.mlp.down_proj.weight ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:3ea33a66c3594aec6fb42940b55fdd594d899644e68bfee339382c143767d4f9
+size 234881913

pytorch_model.bin/p98.model.layers.10.input_layernorm.weight ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:02e4da32e05d054bd833e8529e97dc747aefbaa0ac17240b662eeebc6cfa1632
+size 17279

pytorch_model.bin/p99.model.layers.10.post_attention_layernorm.weight ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:4ac73b2bf0d936b3ebc4d95503e64f36c478325ae909e68a4ad5abe0d0dbac09
+size 17306