Instructions to use WiseIntelligence/open_llama_3b_v2-Optimum-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WiseIntelligence/open_llama_3b_v2-Optimum-ONNX with Transformers:

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

pipe = pipeline("text-generation", model="WiseIntelligence/open_llama_3b_v2-Optimum-ONNX")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WiseIntelligence/open_llama_3b_v2-Optimum-ONNX")
model = AutoModelForCausalLM.from_pretrained("WiseIntelligence/open_llama_3b_v2-Optimum-ONNX")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use WiseIntelligence/open_llama_3b_v2-Optimum-ONNX with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WiseIntelligence/open_llama_3b_v2-Optimum-ONNX"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WiseIntelligence/open_llama_3b_v2-Optimum-ONNX",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/WiseIntelligence/open_llama_3b_v2-Optimum-ONNX

SGLang

How to use WiseIntelligence/open_llama_3b_v2-Optimum-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 "WiseIntelligence/open_llama_3b_v2-Optimum-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": "WiseIntelligence/open_llama_3b_v2-Optimum-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 "WiseIntelligence/open_llama_3b_v2-Optimum-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": "WiseIntelligence/open_llama_3b_v2-Optimum-ONNX",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use WiseIntelligence/open_llama_3b_v2-Optimum-ONNX with Docker Model Runner:
```
docker model run hf.co/WiseIntelligence/open_llama_3b_v2-Optimum-ONNX
```

open_llama_3b_v2-Optimum-ONNX / decoder_model.onnx_data

WiseIntelligence

Upload decoder_model.onnx_data with huggingface_hub

7dfc190 over 2 years ago

download

history blame contribute delete

13.7 GB

This file is stored with Xet . It is too big to display, but you can still download it.

Xet Pointer Details

( Raw pointer file )

Xet hash:: 518ba38f1fd3acf5887b277f9e99c54af60f9ec04881f7d5e19672a88dd59327
Size of remote file:: 13.7 GB
SHA256:: bf181e328d62878086996201052a486a993942b5a191d064e98ee61b878a6c9e

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.