Instructions to use Jebadiah/Aria-ruby-v4-e with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jebadiah/Aria-ruby-v4-e with Transformers:

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

pipe = pipeline("text-generation", model="Jebadiah/Aria-ruby-v4-e", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Jebadiah/Aria-ruby-v4-e", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("Jebadiah/Aria-ruby-v4-e", trust_remote_code=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Jebadiah/Aria-ruby-v4-e with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jebadiah/Aria-ruby-v4-e"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jebadiah/Aria-ruby-v4-e",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Jebadiah/Aria-ruby-v4-e

SGLang

How to use Jebadiah/Aria-ruby-v4-e 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 "Jebadiah/Aria-ruby-v4-e" \
    --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": "Jebadiah/Aria-ruby-v4-e",
		"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 "Jebadiah/Aria-ruby-v4-e" \
        --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": "Jebadiah/Aria-ruby-v4-e",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Jebadiah/Aria-ruby-v4-e with Docker Model Runner:
```
docker model run hf.co/Jebadiah/Aria-ruby-v4-e
```

Aria-ruby-v4-e / README.md

Jebadiah

Upload folder using huggingface_hub

81e3af3 verified about 2 years ago

preview code

Raw

History Blame Contribute Delete

968 Bytes

	---
	base_model:
	- Jebadiah/Aria-ruby-v3
	- Jebadiah/Tess-coder-ruby-p7
	library_name: transformers
	tags:
	- mergekit
	- merge

	---
	# merge

	This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

	## Merge Details
	### Merge Method

	This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [Jebadiah/Aria-ruby-v3](https://huggingface.co/Jebadiah/Aria-ruby-v3) as a base.

	### Models Merged

	The following models were included in the merge:
	* [Jebadiah/Tess-coder-ruby-p7](https://huggingface.co/Jebadiah/Tess-coder-ruby-p7)

	### Configuration

	The following YAML configuration was used to produce this model:

	```yaml
	models:
	- model: Jebadiah/Tess-coder-ruby-p7
	parameters:
	density: 0.6
	weight: 0.5

	merge_method: dare_ties
	base_model: Jebadiah/Aria-ruby-v3
	parameters:
	normalize: false
	int8_mask: true
	dtype: float16
	```