Instructions to use Wanclouds/Mistral-7b-doc-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Wanclouds/Mistral-7b-doc-ONNX with Transformers:

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

pipe = pipeline("text-generation", model="Wanclouds/Mistral-7b-doc-ONNX")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Wanclouds/Mistral-7b-doc-ONNX")
model = AutoModelForCausalLM.from_pretrained("Wanclouds/Mistral-7b-doc-ONNX")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Wanclouds/Mistral-7b-doc-ONNX with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Wanclouds/Mistral-7b-doc-ONNX"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Wanclouds/Mistral-7b-doc-ONNX",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Wanclouds/Mistral-7b-doc-ONNX

SGLang

How to use Wanclouds/Mistral-7b-doc-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 "Wanclouds/Mistral-7b-doc-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": "Wanclouds/Mistral-7b-doc-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 "Wanclouds/Mistral-7b-doc-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": "Wanclouds/Mistral-7b-doc-ONNX",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Wanclouds/Mistral-7b-doc-ONNX with Docker Model Runner:
```
docker model run hf.co/Wanclouds/Mistral-7b-doc-ONNX
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

-------------------------------------------------------------------------

Copyright (c) Microsoft Corporation. All rights reserved.

Licensed under the MIT License.

--------------------------------------------------------------------------

import os from pathlib import Path

import torch import torch.distributed as dist from optimum.onnxruntime import ORTModelForCausalLM from transformers import AutoConfig, AutoTokenizer, GenerationConfig

device_id = 0 device = torch.device(f"cuda:{device_id}") # Change to torch.device("cpu") if running on CPU

ep = "CUDAExecutionProvider" # change to CPUExecutionProvider if running on CPU ep_options = {"device_id": device_id}

model_id = "mistralai/Mistral-7B-Instruct-v0.2" model_path = "./Olive/examples/llama2/models/qlora/qlora-conversion-transformers_optimization-bnb_quantization/gpu-cuda_model"

model_path = Path(model_path)

if not (model_path / "config.json").exists(): config = AutoConfig.from_pretrained(model_id) config.save_pretrained(model_path) else: config = AutoConfig.from_pretrained(model_path)

if not (model_path / "generation_config.json").exists(): gen_config = GenerationConfig.from_pretrained(model_id) gen_config.save_pretrained(model_path) else: gen_config = GenerationConfig.from_pretrained(model_path)

tokenizer = AutoTokenizer.from_pretrained(model_id)

model = ORTModelForCausalLM.from_pretrained( model_path, config=config, generation_config=gen_config, use_io_binding=True, # provider="CUDAExecutionProvider", provider=ep, provider_options={"device_id": device_id} # provider_options={"device_id": str(rank)}, )

Downloads last month: 4