PEFT
TensorBoard
Safetensors
llama
african-languages
multilingual
instruction-tuning
transfer-learning
4-bit precision
bitsandbytes
Instructions to use africa-intelligence/llama-8b-south-africa with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use africa-intelligence/llama-8b-south-africa with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3.1-8B-Instruct") model = PeftModel.from_pretrained(base_model, "africa-intelligence/llama-8b-south-africa") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- a08135479e8b019960ea25bf34a5d6a5e5d701ddb0f8a4fcd7419dca32a24f5a
- Size of remote file:
- 168 MB
- SHA256:
- 870f3fc3d4419479b4cf9dc3eca2224ed0fa8e9918b888fe5d4bf4d2ba85f800
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.