- Fine-tuning of Llama-3.1-8B on german datasets. Same datasets used in Nekochu/Llama-2-13B-German-ORPO.
- I've (alway) kept LoRA
QLoRA_German-ORPOso it can be applied to any LLaMA-3.1-8B fine-tuned model but may affect performance. - Quants: exl2 2.4bpw-h6, 4.25bpw-h6, 8.0bpw-h8 | GGUF Q4_K_M,IQ4_XS...
Oh, and I am not a GER speaker. ^^
- Downloads last month
- 13
Safetensors
Model size
8B params
Tensor type
BF16
·
Model tree for Nekochu/Llama-3.1-8B-German-ORPO
Base model
meta-llama/Llama-3.1-8B Finetuned
meta-llama/Llama-3.1-8B-Instruct