OpenLLM-France/Luciole-1B-Instruct-1.1

Full fine-tune vs OpenLLM-France/Luciole-1B-Base. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: Embeddings 1/1, Norms 95/98, MLP 48/48, Attention 96/96

1 derivatives checked

• OpenLLM-France/Luciole-1B-Instruct-1.1-GGUF: Same weights, converted

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse