Instructions to use shoibl/tinyllama-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use shoibl/tinyllama-onnx with Transformers:

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

pipe = pipeline("text-generation", model="shoibl/tinyllama-onnx")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("shoibl/tinyllama-onnx")
model = AutoModelForCausalLM.from_pretrained("shoibl/tinyllama-onnx", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use shoibl/tinyllama-onnx with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "shoibl/tinyllama-onnx"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shoibl/tinyllama-onnx",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/shoibl/tinyllama-onnx

SGLang

How to use shoibl/tinyllama-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 "shoibl/tinyllama-onnx" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shoibl/tinyllama-onnx",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "shoibl/tinyllama-onnx" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "shoibl/tinyllama-onnx",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use shoibl/tinyllama-onnx with Docker Model Runner:
```
docker model run hf.co/shoibl/tinyllama-onnx
```

tinyllama-onnx / quantize_config.json

shoibl

Upload folder using huggingface_hub

f4d0b26 verified over 2 years ago

Raw History Blame Contribute Delete

1.7 kB

{
    "per_channel": false,
    "reduce_range": false,
    "per_model_config": {
        "model": {
            "op_types": [
                "ReduceMean",
                "Sigmoid",
                "Reshape",
                "Neg",
                "Equal",
                "MatMul",
                "Squeeze",
                "Expand",
                "Pow",
                "Concat",
                "ConstantOfShape",
                "Unsqueeze",
                "Slice",
                "Gather",
                "Softmax",
                "Sqrt",
                "Transpose",
                "Range",
                "Div",
                "Constant",
                "Where",
                "Cast",
                "Less",
                "Shape",
                "Add",
                "Sub",
                "Mul"
            ],
            "weight_type": "QInt8"
        },
        "decoder_model": {
            "op_types": [
                "ReduceMean",
                "Sigmoid",
                "Reshape",
                "Neg",
                "Equal",
                "MatMul",
                "Squeeze",
                "Expand",
                "Pow",
                "Concat",
                "ConstantOfShape",
                "Unsqueeze",
                "Slice",
                "Gather",
                "Softmax",
                "Sqrt",
                "Transpose",
                "Range",
                "Div",
                "Constant",
                "Where",
                "Cast",
                "Less",
                "Shape",
                "Add",
                "Sub",
                "Mul"
            ],
            "weight_type": "QInt8"
        }
    }
}

	{
	"per_channel": false,
	"reduce_range": false,
	"per_model_config": {
	"model": {
	"op_types": [
	"ReduceMean",
	"Sigmoid",
	"Reshape",
	"Neg",
	"Equal",
	"MatMul",
	"Squeeze",
	"Expand",
	"Pow",
	"Concat",
	"ConstantOfShape",
	"Unsqueeze",
	"Slice",
	"Gather",
	"Softmax",
	"Sqrt",
	"Transpose",
	"Range",
	"Div",
	"Constant",
	"Where",
	"Cast",
	"Less",
	"Shape",
	"Add",
	"Sub",
	"Mul"
	],
	"weight_type": "QInt8"
	},
	"decoder_model": {
	"op_types": [
	"ReduceMean",
	"Sigmoid",
	"Reshape",
	"Neg",
	"Equal",
	"MatMul",
	"Squeeze",
	"Expand",
	"Pow",
	"Concat",
	"ConstantOfShape",
	"Unsqueeze",
	"Slice",
	"Gather",
	"Softmax",
	"Sqrt",
	"Transpose",
	"Range",
	"Div",
	"Constant",
	"Where",
	"Cast",
	"Less",
	"Shape",
	"Add",
	"Sub",
	"Mul"
	],
	"weight_type": "QInt8"
	}
	}
	}