llama-3.1-8B-lexi-uncensored-V2-bcff11

Model Description

Um simples teste onde foi aplicado finetune no modelo para que responda de forma semelhante a um usúario de um fórum de internet baseado no título dos threads.

dataset usado: https://huggingface.co/datasets/fuze-eletrik/ign_user_bcff11_2408_commom_vale-tudo_tags

  • Epochs: 7

  • Developed by: fuze-eletrik

  • License: apache-2.0

  • Finetuned from model : Orenguteng/Llama-3.1-8B-Lexi-Uncensored-V2

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

Downloads last month
199
GGUF
Model size
8.03B params
Architecture
llama

4-bit

16-bit

Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no pipeline_tag.

Model tree for fuze-eletrik/llama-3.1-8B-lexi-uncensored-V2-bcff11-GGUF

Quantized
(35)
this model