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

Same weights, converted vs OpenLLM-France/Luciole-1B-Instruct-1.1. Same weights stored in another dtype (BF16 → BF16/F32), plus 1 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/98, MLP 0/48, Attention 0/96

On the Hub · Downloads on Model Pulse