Instructions to use Jacaranda/AfroLlama_V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Jacaranda/AfroLlama_V1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="Jacaranda/AfroLlama_V1")# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Jacaranda/AfroLlama_V1") model = AutoModelForCausalLM.from_pretrained("Jacaranda/AfroLlama_V1") - Notebooks
- Google Colab
- Kaggle
Additional Information about Instruction Tuning
#1
by ToluClassics - opened
Thanks for putting together a detailed model card!
Would you be able to provide additional information about Post-Training Data. I'm referring to "Instruction tuning:[331,400 instruction-response pairs]". Was this synthetically generated or translated??