Downloads · 30 days
17
32% of all-time downloads
minimind-fr-router
yassinsiouda/minimind-fr-router
minimind-fr-router is a machine learning model from yassinsiouda. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as apache-2.0.
Orchestrator: classifies a query into one of creative / devops / coding / electronics / general / unsafe (emits a single word). ~64 M params (hiddensize=768, numhiddenlayers=8, dense), MiniMind architecture. SFT from…
All-time downloads
53
Public
Repo size
266 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pth138 MB · 52%
At a glance
- Library
- pytorch
- License
- apache-2.0
- Access
- Public
- Created
- Sep 3, 2026
- Updated
- Sep 3, 2026
- SHA
- 1d19959d
Base models
Model card
From the Hugging Face model README
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.
- Library
- pytorch
- License
- apache-2.0
- Languages
- fr, en
- Created
- Sep 3, 2026
- Updated
- Sep 3, 2026