Instructions to use hyper-accel/tiny-random-orion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hyper-accel/tiny-random-orion with Transformers:

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

pipe = pipeline("text-generation", model="hyper-accel/tiny-random-orion", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("hyper-accel/tiny-random-orion", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use hyper-accel/tiny-random-orion with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/hyper-accel/tiny-random-orion

SGLang

How to use hyper-accel/tiny-random-orion 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 "hyper-accel/tiny-random-orion" \
    --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": "hyper-accel/tiny-random-orion",
		"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 "hyper-accel/tiny-random-orion" \
        --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": "hyper-accel/tiny-random-orion",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use hyper-accel/tiny-random-orion with Docker Model Runner:
```
docker model run hf.co/hyper-accel/tiny-random-orion
```

tiny-random-orion / config.json

minho

Upload tiny-random orion model

b54e897 verified over 1 year ago

raw

history blame contribute delete

882 Bytes

	{
	"_attn_implementation_autoset": false,
	"_name_or_path": "OrionStarAI/Orion-14B-Base",
	"architectures": [
	"OrionForCausalLM"
	],
	"attention_bias": false,
	"auto_map": {
	"AutoConfig": "configuration_orion.OrionConfig",
	"AutoModelForCausalLM": "modeling_orion.OrionForCausalLM"
	},
	"bos_token_id": 1,
	"eos_token_id": 2,
	"hidden_act": "silu",
	"hidden_size": 512,
	"initializer_range": 0.02,
	"intermediate_size": 1536,
	"max_position_embeddings": 4096,
	"max_sequence_length": 4096,
	"model_type": "orion",
	"num_attention_heads": 4,
	"num_hidden_layers": 2,
	"num_key_value_heads": 4,
	"pad_token_id": 0,
	"pretraining_tp": 1,
	"rms_norm_eps": 1e-05,
	"rope_scaling": null,
	"rope_theta": 10000.0,
	"tie_word_embeddings": false,
	"torch_dtype": "float32",
	"transformers_version": "4.44.0",
	"use_cache": true,
	"vocab_size": 84608
	}