image/png

Llama3.1-Allades-8B

Allades finetunes abliterated Llama 3.1 with 5 datasets to improve creative writing, reasoning, and roleplay.

Datasets

Training

ORPO tuned for 1 epoch with 2x RTX 3090 (sponsored by Schneewolf Labs).

Data was prepared with Llama 3.1 Instruct.

Downloads last month
36
Safetensors
Model size
8.03B params
Tensor type
BF16
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

Model tree for nbeerbower/Llama3.1-Allades-8B

Finetuned
(7)
this model
Merges
7 models
Quantizations
6 models

Datasets used to train nbeerbower/Llama3.1-Allades-8B