Instructions to use onnx-community/moondream2.text_model-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use onnx-community/moondream2.text_model-ONNX with Transformers.js:

// npm i @huggingface/transformers
import { pipeline } from '@huggingface/transformers';

// Allocate pipeline
const pipe = await pipeline('text-generation', 'onnx-community/moondream2.text_model-ONNX');

Transformers

How to use onnx-community/moondream2.text_model-ONNX with Transformers:

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

pipe = pipeline("text-generation", model="onnx-community/moondream2.text_model-ONNX")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("onnx-community/moondream2.text_model-ONNX")
model = AutoModelForCausalLM.from_pretrained("onnx-community/moondream2.text_model-ONNX", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use onnx-community/moondream2.text_model-ONNX with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "onnx-community/moondream2.text_model-ONNX"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "onnx-community/moondream2.text_model-ONNX",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/onnx-community/moondream2.text_model-ONNX

SGLang

How to use onnx-community/moondream2.text_model-ONNX 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 "onnx-community/moondream2.text_model-ONNX" \
    --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": "onnx-community/moondream2.text_model-ONNX",
		"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 "onnx-community/moondream2.text_model-ONNX" \
        --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": "onnx-community/moondream2.text_model-ONNX",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use onnx-community/moondream2.text_model-ONNX with Docker Model Runner:
```
docker model run hf.co/onnx-community/moondream2.text_model-ONNX
```

moondream2.text_model-ONNX / config.json

Xenova HF Staff

Transformers.js - Enable external data format in Node.js

5ffe156 verified over 1 year ago

Raw History Blame Contribute Delete

899 Bytes

	{
	"architectures": [
	"PhiForCausalLM"
	],
	"attention_dropout": 0.0,
	"bos_token_id": 1,
	"embd_pdrop": 0.0,
	"eos_token_id": 2,
	"hidden_act": "gelu_new",
	"hidden_size": 2048,
	"initializer_range": 0.02,
	"intermediate_size": 8192,
	"layer_norm_eps": 1e-05,
	"max_position_embeddings": 2048,
	"model_type": "phi",
	"num_attention_heads": 32,
	"num_hidden_layers": 24,
	"num_key_value_heads": 32,
	"partial_rotary_factor": 0.5,
	"qk_layernorm": false,
	"resid_pdrop": 0.0,
	"rope_scaling": null,
	"rope_theta": 10000.0,
	"tie_word_embeddings": false,
	"torch_dtype": "float32",
	"transformers_version": "4.46.1",
	"use_cache": true,
	"vocab_size": 51200,
	"transformers.js_config": {
	"kv_cache_dtype": {
	"q4f16": "float16",
	"fp16": "float16"
	},
	"use_external_data_format": {
	"model.onnx": true,
	"model_fp16.onnx": true
	}
	}
	}