LoRA trained in 4-bit with 8k context using mistralai/Mistral-Nemo-Base-2407 as the base model for 1 epoch.
Dataset used is mpasila/LimaRP-PIPPA-freedom-rp-Mix-8K which was made using grimulkan/LimaRP-augmented, KaraKaraWitch/PIPPA-ShareGPT-formatted and openerotica/freedom-rp.
Merged LoRA: mpasila/Mistral-freeLiPPA-12B
Prompt format: ChatML
Changed to ChatML since it might be confusing to use Llama 3 Instruct template on a Mistral model...
Uploaded model
- Developed by: mpasila
- License: apache-2.0
- Finetuned from model : unsloth/mistral-nemo-base-2407-bnb-4bit
This mistral model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Downloads last month
- 5