---
language:
- fr
license: apache-2.0
tags:
- llama
- french
- calcyon
- technical
pipeline_tag: text-generation
---

# cALCYON-1B

Modele de langage francophone technique (1.152B parametres).

## Architecture
- LLaMA-style decoder, 22 couches, GQA 16/8 heads, SwiGLU
- Tokenizer SentencePiece BPE 32k optimise francais
- Contexte 8192 tokens, RoPE theta=500000

## Domaines
Aeronautique, electricite/electrotechnique, hydraulique/hydroelectrique,
developpement Python/C++, hardware, FPV, LiDAR

## Prompt format (ChatML)
```
<|system|>
Tu es cALCYON.<|end|>
<|user|>
Question<|end|>
<|assistant|>
```

## Entrainement
SFT LoRA r=32 sur Wikipedia-FR + OpenHermes-FR + donnees techniques.
GPU : NVIDIA RTX 5080 16GB.

## Usage LM Studio / Ollama
Telecharger `calcyon-1b-q4_k_m.gguf` (709 MB) et charger dans LM Studio ou Ollama.