Downloads · 30 days
25
35% of all-time downloads
minimind-fr-pretrain-enfr
yassinsiouda/minimind-fr-pretrain-enfr
minimind-fr-pretrain-enfr 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.
Bilingual en/fr base (next-token lm), ~64m, minimind arch. ~64 M params (hiddensize=768, numhiddenlayers=8, dense), MiniMind architecture. trained from scratch.
All-time downloads
72
Public
Repo size
266 MB
Likes
1
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
- 33e69e76
Model card
From the Hugging Face model README
minimind-fr-pretrain-enfr
Bilingual en/fr base (next-token lm), ~64m, minimind arch. ~64 M params (hidden_size=768, num_hidden_layers=8, dense),
MiniMind architecture. trained from scratch.
Round-1 prototype — fluent but small; treat outputs accordingly. Training framework: https://github.com/jingyaogong/minimind.
Files
| file | format |
|---|---|
pretrain-enfr_768.pth | raw PyTorch state_dict (fp16) — load with MiniMindForCausalLM(strict=False) |
pretrain-enfr-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-pretrain-enfr-data | packaged training file for this model |
allenai/c4 | configs en + fr, ~2 GB raw text each, prose-filtered, split into <=1000-char chunks, shuffled |
5,315,952 lines (2,549,541 fr / 2,766,411 en, ~48% French). The byte-level BPE-6400 tokenizer bundled here was retrained on this mix. Recipe: build_c4_enfr.py.
Run (GGUF)
llama-cli -m pretrain-enfr-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