Instructions to use kazssym/stablelm-3b-4e1t-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use kazssym/stablelm-3b-4e1t-onnx with Transformers:

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

pipe = pipeline("text-generation", model="kazssym/stablelm-3b-4e1t-onnx")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("kazssym/stablelm-3b-4e1t-onnx")
model = AutoModelForCausalLM.from_pretrained("kazssym/stablelm-3b-4e1t-onnx")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use kazssym/stablelm-3b-4e1t-onnx with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "kazssym/stablelm-3b-4e1t-onnx"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "kazssym/stablelm-3b-4e1t-onnx",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/kazssym/stablelm-3b-4e1t-onnx

SGLang

How to use kazssym/stablelm-3b-4e1t-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 "kazssym/stablelm-3b-4e1t-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": "kazssym/stablelm-3b-4e1t-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 "kazssym/stablelm-3b-4e1t-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": "kazssym/stablelm-3b-4e1t-onnx",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use kazssym/stablelm-3b-4e1t-onnx with Docker Model Runner:
```
docker model run hf.co/kazssym/stablelm-3b-4e1t-onnx
```

Description

This is an ONNX model for our test scripts. It was exported from stabilityai/stablelm-3b-4e1t to ONNX with a modified version of Hugging Face Optimum. It is quite possible to have problems.

Exporting

This model was exported with our test scripts.

The source model requires Transformers 4.38 or later to export.

Downloads last month: 8