Instructions to use apple/OpenELM-270M-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use apple/OpenELM-270M-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="apple/OpenELM-270M-Instruct", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("apple/OpenELM-270M-Instruct", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use apple/OpenELM-270M-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "apple/OpenELM-270M-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "apple/OpenELM-270M-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/apple/OpenELM-270M-Instruct

SGLang

How to use apple/OpenELM-270M-Instruct 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 "apple/OpenELM-270M-Instruct" \
    --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": "apple/OpenELM-270M-Instruct",
		"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 "apple/OpenELM-270M-Instruct" \
        --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": "apple/OpenELM-270M-Instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use apple/OpenELM-270M-Instruct with Docker Model Runner:
```
docker model run hf.co/apple/OpenELM-270M-Instruct
```

Android + OpenCL implementation — runs on-device on non-flagship phones (Adreno 6xx)

by a8nova - opened 6 days ago

Discussion

a8nova

6 days ago

Hi! I wanted to share an Android + OpenCL implementation of OpenELM-270M-Instruct, in case anyone wants to run it on a phone:

Try it: Edgi on Google Play — runs fully on-device, no cloud.
Open source: the app is built on top of the open-source adreno-llms inference engine — https://github.com/a8nova/adreno-llms — pure C++/OpenCL with hand-written kernels tuned for Adreno.

It's tuned and tested on Adreno 6xx GPUs — the GPU class in mid-range and older Android phones (verified on a 2020 Motorola Razr / Adreno 620) — and should run on most arm64 Android phones with OpenCL, though the optimizations are Adreno-specific. On the Adreno 620 it decodes at ~14.7 tok/s in fp16, ~79% of the measured bandwidth ceiling. (Weights are fetched from Apple's HF repo at build time — nothing is redistributed.)

Hope it's useful — happy to answer questions!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment