Instructions to use yassinsiouda/minimind-fr-router with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use yassinsiouda/minimind-fr-router with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf yassinsiouda/minimind-fr-router:F16
# Run inference directly in the terminal:
llama cli -hf yassinsiouda/minimind-fr-router:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf yassinsiouda/minimind-fr-router:F16
# Run inference directly in the terminal:
llama cli -hf yassinsiouda/minimind-fr-router:F16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf yassinsiouda/minimind-fr-router:F16
# Run inference directly in the terminal:
./llama-cli -hf yassinsiouda/minimind-fr-router:F16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf yassinsiouda/minimind-fr-router:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf yassinsiouda/minimind-fr-router:F16

Use Docker

docker model run hf.co/yassinsiouda/minimind-fr-router:F16

LM Studio
Jan
Ollama
How to use yassinsiouda/minimind-fr-router with Ollama:
```
ollama run hf.co/yassinsiouda/minimind-fr-router:F16
```
Unsloth Desktop

How to use yassinsiouda/minimind-fr-router with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf yassinsiouda/minimind-fr-router:F16

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "yassinsiouda/minimind-fr-router:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use yassinsiouda/minimind-fr-router with Docker Model Runner:
```
docker model run hf.co/yassinsiouda/minimind-fr-router:F16
```

Lemonade

How to use yassinsiouda/minimind-fr-router with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull yassinsiouda/minimind-fr-router:F16

Run and chat with the model

lemonade run user.minimind-fr-router-F16

List all available models

lemonade list

Hermes Agent

How to use yassinsiouda/minimind-fr-router with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf yassinsiouda/minimind-fr-router:F16

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default yassinsiouda/minimind-fr-router:F16

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use yassinsiouda/minimind-fr-router with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf yassinsiouda/minimind-fr-router:F16

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "yassinsiouda/minimind-fr-router:F16" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

minimind-fr-router

Orchestrator: classifies a query into one of creative / devops / coding / electronics / general / unsafe (emits a single word). ~64 M params (hidden_size=768, num_hidden_layers=8, dense), MiniMind architecture. SFT from minimind-fr-pretrain-enfr.

Round-1 prototype — fluent but small; treat outputs accordingly. Training framework: https://github.com/jingyaogong/minimind.

Files

file	format
`router_768.pth`	raw PyTorch `state_dict` (fp16) — load with `MiniMindForCausalLM(strict=False)`
`router-f16.gguf`	GGUF F16 — exported via `Qwen3ForCausalLM`, runs in `llama.cpp` / Ollama / LM Studio
`tokenizer.json`, `tokenizer_config.json`	byte-level BPE, `vocab_size=6400`, EN/FR

Config: num_attention_heads 8, num_key_value_heads 4, vocab_size 6400, max_position_embeddings 32768, rope_theta 1e6, tied embeddings, no MoE.

Training data

dataset	contribution
`yassinsiouda/minimind-fr-router-data`	packaged training file for this model
the four specialist SFT sets	user turns -> domain label, ~4k per domain
the base SFT mix (see the specialists)	`general` label, ~5k
`lmsys/toxic-chat`	`unsafe` label (rows flagged `toxicity`/`jailbreaking`), 272 in train

17,467 train rows + 2,567 held-out (router_eval.jsonl). {system (fixed FR routing prompt), user (query), assistant (one label word)}. Labels: creative / devops / coding / electronics / general / unsafe. Train counts: coding 3500, general 4500, creative 3500, electronics 3500, devops 2195, unsafe 272. Recipe: convert_router.py.

Run (GGUF)

llama-cli -m router-f16.gguf -p "..." -ngl 99

Limitations

64 M parameters; English domain data for the specialists (French comes from the bilingual base, so domain idiom is anglicised); agentic capability is SFT-only (short 2-4 step tool loops); safety limited to the router's thin unsafe bucket.

License

Apache-2.0 (weights). Upstream dataset licenses govern downstream use — see the dataset repo.

Downloads last month: 17

GGUF

Model size

63.9M params

Architecture

qwen3

Hardware compatibility

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for yassinsiouda/minimind-fr-router

Base model

yassinsiouda/minimind-fr-pretrain-enfr

Finetuned

(3)

this model

yassinsiouda
/

minimind-fr-router

minimind-fr-router

Files

Training data

Run (GGUF)

Limitations

License

Model tree for yassinsiouda/minimind-fr-router

Datasets used to train yassinsiouda/minimind-fr-router