ModelVerifiedExternal

Calcyon 1b

Modele de langage francophone technique (1.152B parametres).

Sourcehuggingface.co/MinelaxieFR/calcyon-1b/tree/74eea8ffe1f79041aa025a299c2d6569f703b62d

KindText modelVersionPublisher@MinelaxieFRCgrade

Model source

Kind: Text model
File size: 2.15 GB
Version: vcalcyon-1b-f16
Updated: Oct 3, 2026
Publisher: @MinelaxieFR
Downloads: 34
Parameters: 1B
Tasks: Text generation
Source: Hugging Face

Source description

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.

Sources

1 source

Hugging FacePrimaryVersion 74eea8ffe1f79041aa025a299c2d6569f703b62d

huggingface.co/MinelaxieFR/calcyon-1b/tree/74eea8ffe1f79041aa025a299c2d6569f703b62d

Verified Oct 3

Model artifacts

1 artifact

calcyon-1b-f16.gguf

gguf · 2.15 GB · SHA-256 16d9ec0ad3c3…f4b8 · Hugging Face

Download file

Source excerpts

3 excerpts

ReadmeJul 11huggingface.co/MinelaxieFR/calcyon-1b

--- 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.

NoteOct 3huggingface.co/MinelaxieFR/calcyon-1b

Source context: 34 downloads · 0 likes · Pipeline text-generation · Repo MinelaxieFR/calcyon-1b

NoteJul 17huggingface.co/MinelaxieFR/calcyon-1b

Source context: 155 downloads · 0 likes · Pipeline text-generation · Repo MinelaxieFR/calcyon-1b