This is a merge of mpasila/Llama-3-LimaRP-LoRA-8B.

LoRA trained in 4-bit with 8k context using meta-llama/Meta-Llama-3-8B as the base model for 1 epoch.

Dataset used is a modified version of grimulkan/LimaRP-augmented.

Prompt format: ChatML

Uploaded model

  • Developed by: mpasila
  • License: Llama 3 Community License
  • Finetuned from model : unsloth/llama-3-8b-bnb-4bit

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

Downloads last month
3
Safetensors
Model size
8.03B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for mpasila/Llama-3-LimaRP-8B

Finetuned
(2747)
this model

Datasets used to train mpasila/Llama-3-LimaRP-8B