OpenLLM-France/Lucie-7B-Instruct-v1.1
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
5 derivatives checked
- mradermacher/Lucie-7B-Instruct-v1.1-GGUF: Same weights, converted
- tensorblock/Lucie-7B-Instruct-v1.1-GGUF: Quantization
- DevQuasar-9/OpenLLM-France.Lucie-7B-Instruct-v1.1-GGUF: Same weights, converted
- OpenLLM-France/Lucie-7B-Instruct-v1.1-gguf: Quantization
- PhilSad/Lucie-7B-GRPO-Science-500: LoRA-style