Downloads · 30 days
4
8% of all-time downloads
xxggabriel/llama-3.1-8b-legalpt-qlora
llama-3.1-8b-legalpt-qlora is a text generation model from xxggabriel. Use it when you need the model to write or continue text. It is set up for peft.
Modelo ajustado com QLoRA no dataset LegalPT acordaos tcu. Base utilizada: meta-llama/Llama-3.1-8B-Instruct Dataset: eduagarcia/LegalPT
Downloads · 30 days
4
8% of all-time downloads
All-time downloads
48
Public
Repo size
1.4 GB
Likes
0
Public
Click a slice to open those files.
.safetensors1.3 GB · 96%
From the Hugging Face model README
Modelo ajustado com QLoRA no dataset LegalPT acordaos tcu.
Base utilizada: meta-llama/Llama-3.1-8B-Instruct
Dataset: eduagarcia/LegalPT
## Como usar rapido
```python
from transformers import AutoModelForCausalLM, AutoTokenizer
tok = AutoTokenizer.from_pretrained("xxggabriel/llama-3.1-8b-legalpt-qlora")
mdl = AutoModelForCausalLM.from_pretrained("xxggabriel/llama-3.1-8b-legalpt-qlora", device_map="auto")
## Observacoes
Este repositório inclui tokenizer e arquivos de configuracao.
Se somente adaptadores foram publicados, carregue o base e aplique o adaptador PEFT.