Instructions to use microsoft/mistral-7b-instruct-v0.2-ONNX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use microsoft/mistral-7b-instruct-v0.2-ONNX with Transformers:

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

pipe = pipeline("text-generation", model="microsoft/mistral-7b-instruct-v0.2-ONNX", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("microsoft/mistral-7b-instruct-v0.2-ONNX", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use microsoft/mistral-7b-instruct-v0.2-ONNX with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "microsoft/mistral-7b-instruct-v0.2-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": "microsoft/mistral-7b-instruct-v0.2-ONNX",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/microsoft/mistral-7b-instruct-v0.2-ONNX

SGLang

How to use microsoft/mistral-7b-instruct-v0.2-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 "microsoft/mistral-7b-instruct-v0.2-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": "microsoft/mistral-7b-instruct-v0.2-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 "microsoft/mistral-7b-instruct-v0.2-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": "microsoft/mistral-7b-instruct-v0.2-ONNX",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use microsoft/mistral-7b-instruct-v0.2-ONNX with Docker Model Runner:
```
docker model run hf.co/microsoft/mistral-7b-instruct-v0.2-ONNX
```

it run colab cpu

by asdgad - opened Nov 15, 2025

Discussion

asdgad

Nov 15, 2025

from transformers import AutoTokenizer, pipeline
from optimum.onnxruntime import ORTModelForCausalLM
import os

Define the root local path where the full model repository was cloned

This should be the directory that contains the 'onnx' subfolder, config.json, etc.

local_repo_root = "/content/mistral-7b-instruct-v0.2-ONNX"

The specific subfolder within the local_repo_root where the ONNX model files are located

onnx_model_subfolder = "onnx/cpu_and_mobile/mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32-acc-level-4"

The specific ONNX file name

onnx_file_name = "mistral-7b-instruct-v0.2-cpu-int4-rtn-block-32-acc-level-4.onnx"

Ensure the root directory exists

if not os.path.exists(local_repo_root):
print(f"Error: Local repository root not found at {local_repo_root}")
else:
print(f"Loading model and tokenizer from local repository: {local_repo_root}")

Manually download the tokenizer.model file to the local_repo_root if it's not already there

tokenizer_model_path = os.path.join(local_repo_root, "tokenizer.model")
if not os.path.exists(tokenizer_model_path):
print(f"Downloading missing tokenizer.model to {local_repo_root}...")
os.system(f"wget -O {tokenizer_model_path} https://huggingface.co/microsoft/mistral-7b-instruct-v0.2-ONNX/resolve/main/tokenizer.model")
print("tokenizer.model downloaded.")

Load the ONNX model from the local repository, pointing to the subfolder

model = ORTModelForCausalLM.from_pretrained(
local_repo_root, # Point to the root of the cloned repository
subfolder=onnx_model_subfolder, # Specify the subfolder for the ONNX model
file_name=onnx_file_name,
use_io_binding=True,
local_files_only=True # Crucial: tells the library to only look locally
)

Load the Tokenizer from the local repository root

tokenizer = AutoTokenizer.from_pretrained(
local_repo_root, # Point to the root of the cloned repository for tokenizer files
local_files_only=True # Crucial: tells the library to only look locally
)

Create pipeline

pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

Test the model

result = pipe(
"Who is Napoleon Bonaparte?",
max_new_tokens=30,
do_sample=True,
temperature=0.7,
top_k=50,
top_p=0.9,
num_return_sequences=1
)

print(result)

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment