Instructions to use asyafiqe/Merak-7B-v3-Mini-Orca-Indo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use asyafiqe/Merak-7B-v3-Mini-Orca-Indo with Transformers:

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

pipe = pipeline("text-generation", model="asyafiqe/Merak-7B-v3-Mini-Orca-Indo")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("asyafiqe/Merak-7B-v3-Mini-Orca-Indo")
model = AutoModelForCausalLM.from_pretrained("asyafiqe/Merak-7B-v3-Mini-Orca-Indo", device_map="auto")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use asyafiqe/Merak-7B-v3-Mini-Orca-Indo with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "asyafiqe/Merak-7B-v3-Mini-Orca-Indo"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "asyafiqe/Merak-7B-v3-Mini-Orca-Indo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/asyafiqe/Merak-7B-v3-Mini-Orca-Indo

SGLang

How to use asyafiqe/Merak-7B-v3-Mini-Orca-Indo 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 "asyafiqe/Merak-7B-v3-Mini-Orca-Indo" \
    --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": "asyafiqe/Merak-7B-v3-Mini-Orca-Indo",
		"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 "asyafiqe/Merak-7B-v3-Mini-Orca-Indo" \
        --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": "asyafiqe/Merak-7B-v3-Mini-Orca-Indo",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use asyafiqe/Merak-7B-v3-Mini-Orca-Indo with Docker Model Runner:
```
docker model run hf.co/asyafiqe/Merak-7B-v3-Mini-Orca-Indo
```

Update README.md

by Ichsan2895 - opened Aug 29, 2023

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

-1

Ichsan2895

Aug 29, 2023

•

edited Aug 29, 2023

Hello, thanks for your contribution for LLM's world.

I also appreciate that Merak get enthusiasm in the Indonesia.

Merak is licensed with cc-by-sa-nc-4.0. Which is mean, please publish it with the license same as original Merak (cc-by-sa-nc-4.0 = Creative Common-By Atribution-ShareAlike-Noncommercial). We hope you accept this condition.

Good luck for you too.

Update README.md545ba43a

asyafiqe changed pull request status to merged Aug 30, 2023

asyafiqe

Owner Aug 30, 2023

Ah sorry for my mistake.
I've already merged your PR.

Thanks!

Ichsan2895

Aug 30, 2023

Thank you for your understanding. :)

BTW congratulation, your model seems more lighter than mine.

Merak-Orca-7B has only 15 GB of pytorch_model.bin instead of 27 GB in Merak-7B-v3.

asyafiqe

Owner Sep 1, 2023

No problem.

Actually I didn't do anything for the reduction of filesize. It came straight out of the trainer. Initially I thought it was corrupted because the file is much smaller

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