Instructions to use IlyasMoutawwakil/tiny-random-Mistral4-FP8-static with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IlyasMoutawwakil/tiny-random-Mistral4-FP8-static with Transformers:

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

pipe = pipeline("image-text-to-text", model="IlyasMoutawwakil/tiny-random-Mistral4-FP8-static")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("IlyasMoutawwakil/tiny-random-Mistral4-FP8-static")
model = AutoModelForMultimodalLM.from_pretrained("IlyasMoutawwakil/tiny-random-Mistral4-FP8-static", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use IlyasMoutawwakil/tiny-random-Mistral4-FP8-static with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IlyasMoutawwakil/tiny-random-Mistral4-FP8-static"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IlyasMoutawwakil/tiny-random-Mistral4-FP8-static",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/IlyasMoutawwakil/tiny-random-Mistral4-FP8-static

SGLang

How to use IlyasMoutawwakil/tiny-random-Mistral4-FP8-static 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 "IlyasMoutawwakil/tiny-random-Mistral4-FP8-static" \
    --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": "IlyasMoutawwakil/tiny-random-Mistral4-FP8-static",
		"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 "IlyasMoutawwakil/tiny-random-Mistral4-FP8-static" \
        --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": "IlyasMoutawwakil/tiny-random-Mistral4-FP8-static",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use IlyasMoutawwakil/tiny-random-Mistral4-FP8-static with Docker Model Runner:
```
docker model run hf.co/IlyasMoutawwakil/tiny-random-Mistral4-FP8-static
```

tiny-random-Mistral4-FP8-static

A tiny random model for testing, shrunk from mistralai/Mistral-Small-4-119B-2603: the same architecture, quantization config and checkpoint layout at test sizes. Its key patterns, dtypes and tensor ranks match the real checkpoint's (scripts/extract_layout.py).

static per-tensor FP8 on every decoder linear and the stacked experts: e4m3, BF16 weight_scale_inv (0-dim, (E, 1, 1) on the experts) and calibrated BF16 activation_scale (0-dim, (E,) on the experts); the MLA attention and shared experts included, router, vision tower and projector bf16.

reference/ holds the same weights dequantized to bf16, under the unquantized model's keys: the reference to compare logits against, so a test measures what the load path and kernels add, not the quantization itself.

The weights are random; the outputs mean nothing. scripts/ rebuilds it from the real checkpoint's config.json.

Downloads last month: 510

Safetensors

Model size

7.8M params

Tensor type

BF16

F8_E4M3