Instructions to use authentrics/mixtral-expert-routing with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use authentrics/mixtral-expert-routing with Transformers:

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

pipe = pipeline("text-generation", model="authentrics/mixtral-expert-routing")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("authentrics/mixtral-expert-routing", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use authentrics/mixtral-expert-routing with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/authentrics/mixtral-expert-routing

SGLang

How to use authentrics/mixtral-expert-routing 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 "authentrics/mixtral-expert-routing" \
    --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": "authentrics/mixtral-expert-routing",
		"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 "authentrics/mixtral-expert-routing" \
        --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": "authentrics/mixtral-expert-routing",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use authentrics/mixtral-expert-routing with Docker Model Runner:
```
docker model run hf.co/authentrics/mixtral-expert-routing
```

Reading How a Mixture-of-Experts Model Routes Its Inputs

Using Authentrics to read how Mixtral's mixture-of-experts routes activations and how that structure emerges across training — interpretability without touching your weights remotely.

Authentrics is a high-performance neural-network analysis library (Python wheel over a C++ core). It audits and maintains model checkpoints: parameter/behavioral drift, compliant data removal without full retraining, and loss-driven optimization without backprop. Analysis runs locally on your machine — only project metadata (names, descriptions) is exchanged with Authentrics servers, never your model weights.

What this demo shows

activation_analysis — catch behavioral drift in intermediate activations.
correlation_analysis — see how strongly each layer influences a reference (usually output) layer.

Reproduce this analysis

The public code and outputs behind this demo live in https://github.com/Authentrics-ai/authentrics-model-analysis-experiments:

src/analysis/mistral_moe_expert_activation.py Outputs (JSON + Plotly HTML dashboards) are published under output/mistral_moe_expert_activation/.

Weights: Interpretability walkthrough on mistralai/Mixtral-8x7B-v0.1; no derived weights are published. Reproduce the analysis locally with the SDK below.

Reproduce it yourself

pip install authentrics            # Linux x86_64, Python 3.11–3.13
authrx init                        # paste API key (stored at ~/.local/state/authentrics/api_key)
# or, for CI / non-interactive:
export AUTHRX_API_KEY=<your_api_key>

Generate an API key and read the full docs at https://app.authentrics.ai/.

Produced with the Authentrics SDK v0.35.1 — checkpoint analysis that runs locally on your own hardware; only project metadata ever leaves your machine, never your weights.

Model tree for authentrics/mixtral-expert-routing

Base model

mistralai/Mixtral-8x7B-v0.1

Finetuned

(79)

this model

Collection including authentrics/mixtral-expert-routing

Reading How a Mixture-of-Experts Model Routes Its Inputs

Collection

Reading how Mixtral-8x7B routes activations, and how that structure emerges across training — without moving weights off your hardware. • 1 item • Updated about 23 hours ago

authentrics
/

mixtral-expert-routing

Reading How a Mixture-of-Experts Model Routes Its Inputs

What this demo shows

Reproduce this analysis

Reproduce it yourself

Links

Model tree for authentrics/mixtral-expert-routing

Collection including authentrics/mixtral-expert-routing

Reading How a Mixture-of-Experts Model Routes Its Inputs