Instructions to use rockmatrix-ai/EdgeRock-4B-NF4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rockmatrix-ai/EdgeRock-4B-NF4 with Transformers:

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

pipe = pipeline("text-generation", model="rockmatrix-ai/EdgeRock-4B-NF4", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("rockmatrix-ai/EdgeRock-4B-NF4", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use rockmatrix-ai/EdgeRock-4B-NF4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rockmatrix-ai/EdgeRock-4B-NF4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "rockmatrix-ai/EdgeRock-4B-NF4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rockmatrix-ai/EdgeRock-4B-NF4

SGLang

How to use rockmatrix-ai/EdgeRock-4B-NF4 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 "rockmatrix-ai/EdgeRock-4B-NF4" \
    --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": "rockmatrix-ai/EdgeRock-4B-NF4",
		"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 "rockmatrix-ai/EdgeRock-4B-NF4" \
        --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": "rockmatrix-ai/EdgeRock-4B-NF4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rockmatrix-ai/EdgeRock-4B-NF4 with Docker Model Runner:
```
docker model run hf.co/rockmatrix-ai/EdgeRock-4B-NF4
```

docs: add bilingual whitepaper and refresh model introduction

by hkust-aaron - opened 9 days ago

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

-0

hkust-aaron

9 days ago

Update the bilingual introduction and add English/Chinese Rock Matrix whitepaper links. The main model repository also receives the published PDFs. Preserve model weights, runtime code, benchmark tables, installation commands, licenses, and package-specific validation scope. SiliconRock's one-million-token/s figure is a roadmap target, separate from EdgeRock's reported results.

docs: add bilingual whitepaper and refresh model introduction7e618727

rockmatrix-ai changed pull request status to merged 8 days ago

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