Volko76/Lucie-7B-Instruct

Full fine-tune vs OpenLLM-France/Lucie-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Attention 160/160, lm_head 1/1, Embeddings 1/1, Norms 65/65, MLP 96/96

2 derivatives checked

• mradermacher/Lucie-7B-Instruct-GGUF: Same weights, converted
• mradermacher/Lucie-7B-Instruct-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse