QuantFactory/Llama-3.1-Literotica-8B-GGUF

This is quantized version of mpasila/Llama-3.1-Literotica-8B created using llama.cpp

Original Model Card

Dataset used: mpasila/Literotica-stories-short which contains only a subset of the stories from the full Literotica dataset and was chunked down to fit within 8192 tokens.

Prompt format is: No formatting

LoRA: mpasila/Llama-3.1-Literotica-LoRA-8B

Trained with regular LoRA (not quantized/QLoRA) and LoRA rank was 128 and Alpha set to 32. Trained for 1 epoch using A40 for about 13 hours.

Uploaded model

• Developed by: mpasila
• License: Llama 3.1 Community License Agreement
• Finetuned from model : unsloth/Meta-Llama-3.1-8B

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.