OpenLLM-France/Luciole-23B-Instruct-1.1

Full fine-tune vs OpenLLM-France/Luciole-23B-Base. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 152/162, MLP 80/80, Attention 160/160, lm_head 1/1

1 derivatives checked

• OpenLLM-France/Luciole-23B-Instruct-1.1-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse